Thanks to visit codestin.com
Credit goes to superbased.app

MODEL PRICING EXPLORER

A field guide to
your AI bill.

Compare model providers, make cache and reasoning assumptions explicit, and reverse a fixed AI budget into a realistic workload.

New to token pricing?
Self-hostingSize a GPU fleet against every provider.

LOWEST ESTIMATE

$9.00

per day

Gemini 3.1 Pro Preview · Google

Usage
Time period
Cost by component per day
  • Fresh input
  • Cache read + write
  • Output + reasoning
Gemini 3.1 Pro Preview lowest$9.00
gpt-5.6-sol$16.30
claude-opus-5$20.38

500 turns per day · 3 offerings compared · Average usage

Gemini 3.1 Pro Preview is the lowest candidate estimate at $9.00.

SIDE BY SIDE

Daily estimate

3 offerings · Average band
Anthropic

claude-opus-5

+$11.38
$20.38

per day

Monthly projection$611.25
Per model turn$0.04 / turn

Estimated cost anatomy

Fresh input$3.00
Cache read + write$6.75
Output + reasoning$10.63
Average range$8.15-$32.56200-799 per day · your scenario (500 per day) is within the Average band
Rests on assumed cache rates
OpenAI

gpt-5.6-sol

+$7.30
$16.30

per day

Monthly projection$489.00
Per model turn$0.03 / turn

Estimated cost anatomy

Fresh input$2.40
Cache read + write$5.40
Output + reasoning$8.50
Average range$6.52-$26.05200-799 per day · your scenario (500 per day) is within the Average band
Rests on assumed cache rates
Google

Gemini 3.1 Pro Preview

Lowest
$9.00

per day

Monthly projection$270.00
Per model turn$0.02 / turn

Cost anatomy

Fresh input$1.20
Cache read + write$2.70
Output + reasoning$5.10
Average range$3.60-$14.38200-799 per day · your scenario (500 per day) is within the Average band
Published rates
Calculation trace · claude-opus-5
Net input$3.00
Cache read$4.50
Cache write$2.25
Visible output$10.63
Reasoning$0.00
Web searchUnknown
Known subtotal: $20.38Cache policy: unknownReasoning: unknown
Vendor endpointFetched from the vendor's own pricing endpoint · Observed Aug 18, 2026

This is an estimate. Where the catalog publishes no rate, it assumes:

  • cache writes billed at the input rate, with no separate write charge

Everything the estimate above rests on. Open a group to change it - each one shows what it is currently set to.

3 selectedInput rate / 1M tokens

One turn is one request/response round-trip. A chat message that triggers three tool calls is four turns. Typing here overrides the usage band above; the band buttons stay where you left them.

Estimate turns from users × messages

Reverses a rough traffic estimate into turns per day. Applying this overwrites the turns field above; it does not add a separate scenario.

1 month = 30 days (720h) throughout this page. Switching period converts your turn count using this calendar, never your token-bucket assumptions.

Cache policy and calendar details
Month length
30 days (720h), fixed
Reasoning
Priced at each offering’s own stated reasoning billing
Buckets
Reasoning and visible output are disjoint; the 1h cache-write field is a subset of cache write
Reset returns every group above to the Coding agent preset.

Showing 1-50 of 1,534 models

TypeCompare
deepinfra/intfloat-e5-base-v2Not statedFastRoutertextOpen110M--$0.005$0$0$0.11 est.
Embed v1 0.6bPerplexityAI RoutertextNot stated---$0.004$0-$0.16 est.
@cf/meta/llama-3.2-1b-instructMetaDeepInfratextOpen1B-$0.005$0.01-$0.28 est.
Privacy FilterOpenAINEAR AI CloudtextClosed---$0.01$0-$0.39 est.
Qwen3 Embedding 0.6BAlibabaAI RoutertextOpen600M-$0.01$0-$0.39 est.
Qwen3 Embedding 8BAlibabaNebius AI StudiotextOpen8B--$0.01$0-$0.39 est.
text-embedding-3-smallOpenAIFastRoutertextNot stated--$0.02$0$0$0.42 est.
Qwen3-Reranker-0.6BAlibabaNEAR AI CloudtextOpen600M-$0.01$0.01-$0.48 est.
Whisper Large v3OpenAINEAR AI CloudmultimodalNot stated--$0.01$0.01-$0.48 est.
Qwen/Qwen2.5-Coder-3B-Instruct@nscaleNot statedHugging FaceUnknownNot stated---$0.01$0.03-$0.65 est.
Qwen/Qwen2.5-Coder-7B-Instruct@nscaleNot statedHugging FaceUnknownNot stated---$0.01$0.03-$0.65 est.
Qwen/Qwen3-4B-Instruct-2507@nscaleNot statedHugging FaceUnknownNot stated---$0.01$0.03-$0.65 est.
Qwen/Qwen3-4B-Thinking-2507@nscaleNot statedHugging FaceUnknownNot stated---$0.01$0.03-$0.65 est.
Qwen3 Embedding 4BAlibabaAI RoutertextNot stated--$0.02$0-$0.78 est.
Titan Text Embeddings V2AmazonAI RoutertextNot stated--$0.02$0-$0.78 est.
Voyage 3.5 LiteVoyage AIAI RoutertextNot stated--$0.02$0-$0.78 est.
Voyage 4 LiteVoyage AIAI RoutertextNot stated--$0.02$0-$0.78 est.
Qwen/Qwen3.5-0.8BAlibabaDeepInfratextOpen800M--$0.01$0.05-$0.82 est.
Ling-2.6-flashAnt Group / InclusionAIOpenRoutertextOpen104B-24.3%$0.01$0.03$0.002$0.83 est.
@cf/meta/llama-3.2-3b-instructMetaDeepInfratextOpen3.2B--$0.02$0.02-$0.95 est.
PaddleOCR-VLBaiduNovitamultimodalOpen97B-$0.02$0.02-$0.95 est.
Text Embedding 005GoogleAI RoutertextNot stated--$0.025$0-$0.98 est.
Text Multilingual Embedding 002GoogleAI RoutertextNot stated--$0.025$0-$0.98 est.
Mistral Nemo 12BMistral AIOpenRoutermultimodalOpen12.2B--$0.019$0.03-$1.00 est.
mistral-nemo-instruct-2407Mistral AIDeepInfratextOpen12B--$0.019$0.03-$1.00 est.
Embed v1 4bPerplexityAI RoutertextNot stated---$0.03$0-$1.17 est.
@cf/meta/llama-3.1-8b-instructMetaDeepInfratextOpen8B-1.5%$0.02$0.05-$1.21 est.
meta-llama-llama-3.1-8b-instructNot statedNovita AIUnknownNot stated---$0.02$0.05-$1.21 est.
meta-llama/llama-3.1-8b-instantMetaFastRoutertextOpen8B--$0.02$0.05-$1.21 est.
meta-llama/Llama-3.1-8B-Instruct@deepinfraNot statedHugging FaceUnknownNot stated---$0.02$0.05-$1.21 est.
meta-llama/Llama-3.1-8B-Instruct@novitaNot statedHugging FaceUnknownNot stated---$0.02$0.05-$1.21 est.
Qwen/Qwen2.5-Coder-7BAlibabaDeepInfraUnknownOpen7B--$0.025$0.05-$1.40 est.
DeepSeek V3.2DeepSeekNovita AIUnknownOpen685.4B-46.8%$0.03$0.03-$1.43 est.
deepseek-ai/DeepSeek-OCRDeepSeekNovitamultimodalOpen3B-$0.03$0.03-$1.43 est.
deepseek-ai/DeepSeek-OCR@novitaNot statedHugging FaceUnknownNot stated---$0.03$0.03-$1.43 est.
deepseek-deepseek-ocr-2DeepSeekNovitaUnknownOpen3B-$0.03$0.03-$1.43 est.
glm-ocrNot statedZhipu AIUnknownNot stated---$0.03$0.03-$1.43 est.
Llama Prompt Guard 2 22MMetaGroqtextNot stated--$0.03$0.03-$1.43 est.
mistralaimistral-nemoNot statedParasail +1 moretextNot stated---$0.03$0.03-$1.43 est.
mistralai-mistral-nemoNot statedNovita AIUnknownNot stated---$0.04$0.17-$3.01 est.
Qwen3 4BAlibabaNovitatextOpen4B-$0.03$0.03-$1.43 est.
@cf/meta/llama-3-8b-instructMetaDeepInfratextOpen8B--$0.03$0.04-$1.51 est.
mistral-7b-instruct-v0.3Mistral AIDeepInfratextOpen7B-$0.028$0.054-$1.55 est.
@cf/ibm-granite/granite-4.0-h-microIBMCloudflare Workers AItextOpen3.2B-$0.017$0.112-$1.62 est.
gemma-4-E4B-itGoogleDeepInframultimodalNot stated-1.9%$0.02$0.1-$1.63 est.
Qwen/Qwen3.5-2BAlibabaDeepInfratextOpen2B--$0.02$0.1-$1.63 est.
google/gemma-2-9b-itGoogleDeepInfratextOpen9B--$0.03$0.06-$1.68 est.
Sao10K/L3-8B-Lunaris-v1Sao10KDeepInfraUnknownOpen8B--$0.03$0.06-$1.68 est.
mistralai/Mistral-Small-24B-Instruct-2501Mistral AIFastRoutertextOpen24B--$0.05$0.08$0$1.73 est.
Nex AGI: Nex-N2-MiniNot statedOpenRoutermultimodalOpen35.1B-$0.025$0.1$0.0025$1.83 est.
Mistral Voxtral Mini 1.0Mistral AIAWS BedrockmultimodalNot stated--$0.04$0.04-$1.90 est.
Prompt Guard 2 86MMetaGroqtextNot stated--$0.04$0.04-$1.90 est.
Voxtral Mini 1.0Not statedAWS BedrockUnknownNot stated---$0.04$0.04-$1.90 est.
Sao10K: Llama 3 8B LunarisSao10KOpenRoutertextOpen8B-$0.04$0.05-$1.99 est.
text-embedding-ada-002OpenAIFastRoutertextNot stated--$0.1$0$0$2.10 est.
LFM2.5-8B-A1BNot statedTogether AIUnknownNot stated---$0.03$0.12-$2.19 est.
LFM2.5-8B-A1BLiquid AITogether AIUnknownOpen8B--$0.03$0.12-$2.19 est.
Gemma 3 4BNot statedAWS BedrockUnknownNot stated--0.4%$0.04$0.08-$2.24 est.
Gemma 4 E2BGoogleAWS BedrockUnknownOpen2.3B-0.4%$0.04$0.08-$2.24 est.
Google Gemma 3 4BGoogleAWS BedrockmultimodalOpen4.3B--$0.04$0.08-$2.24 est.
Qwen 3.7 FlashAlibabaPrime IntellectmultimodalClosed--$0.03$0.13-$2.28 est.
Voyage 3.5Voyage AIAI RoutertextNot stated--$0.06$0-$2.34 est.
Voyage 4Voyage AIAI RoutertextNot stated--$0.06$0-$2.34 est.
GPT OSS 20BOpenAIOpenAIUnknownOpen21.5B13.9%$0.03$0.14$0.003$2.36
openai/gpt-oss-20b@deepinfraNot statedHugging FaceUnknownNot stated---$0.03$0.14-$2.36 est.
deepseek-ai/DeepSeek-R1-Distill-Llama-8B@nscaleNot statedHugging FaceUnknownNot stated---$0.05$0.05-$2.38 est.
L3 8B Stheno V3.2Sao10KNovitatextOpen8B-$0.05$0.05-$2.38 est.
Sao10k L3 8B LunarisSao10KNovitatextOpen8B--$0.05$0.05-$2.38 est.
sao10k-l3-8b-lunarisNot statedNovita AIUnknownNot stated---$0.05$0.05-$2.38 est.
Sao10K/L3-8B-Lunaris-v1@novitaNot statedHugging FaceUnknownNot stated---$0.05$0.05-$2.38 est.
Sao10K/L3-8B-Stheno-v3.2@novitaNot statedHugging FaceUnknownNot stated---$0.05$0.05-$2.38 est.
Qwen/Qwen2.5-7B-InstructAlibabaDeepInfra +4 moretextOpen7B-$0.04$0.1-$2.41 est.
Qwen: Qwen2.5 7B InstructAlibabaOpenRoutertextOpen7.6B-$0.1$0.2-$5.60 est.
Qwen/Qwen3.5-4BAlibabaDeepInfraUnknownOpen4B-$0.03$0.15-$2.45 est.
AutoGLM-Phone-9B-MultilingualZhipu AINovitamultimodalOpen9B-$0.035$0.138-$2.54 est.
Qwen3 8BAlibabaNovita +3 moretextOpen8B-$0.035$0.138-$2.54 est.
qwen3-8bAlibabaAlibabatextNot stated-2.2%$0.18$0.7-$12.97 est.
zai-org-glm-4.7Zhipu AINovita AItextOpen355B-$0.035$0.138-$2.54 est.
Nova MicroAmazonAI RoutertextNot stated--$0.035$0.14-$2.56 est.
nova-micro-v1AmazonOpenRoutermultimodalClosed---$0.035$0.14-$2.56 est.
Qwen 2 7B InstructAlibabaNovitatextOpen7B--$0.054$0.054-$2.57 est.
@cf/meta/llama-guard-3-8bMetaDeepInfratextNot stated--$0.055$0.055-$2.61 est.
@cf/mistral/mistral-7b-instruct-v0.1Mistral AIDeepInfratextOpen7B--$0.055$0.055-$2.61 est.
microsoft/WizardLM-2-7BMicrosoftDeepInfraUnknownClosed7B--$0.055$0.055-$2.61 est.
Mistral Mistral 7BMistral AIDeepInfraUnknownOpen7B--$0.055$0.055-$2.61 est.
openchat/openchat_3.5OpenChatDeepInfraUnknownOpen7B--$0.055$0.055-$2.61 est.
openchat/openchat-3.6-8bOpenChatDeepInfraUnknownOpen8B--$0.055$0.055-$2.61 est.
Qwen/Qwen2-7B-InstructAlibabaDeepInfratextOpen7B--$0.055$0.055-$2.61 est.
Mistral Mixtral 8x7BMistral AIFastRouterUnknownOpen46.7B-$0.05$0.08-$2.63 est.
qwen-flash-2025-07-28:0-token-128kNot statedAlibabaUnknownNot stated---$0.022$0.216-$2.69 est.
qwen-flash:0-token-128kNot statedAlibabaUnknownNot stated---$0.022$0.216-$2.69 est.
text-embedding-3-largeOpenAIFastRoutertextNot stated--$0.13$0$0$2.73 est.
Upstage: Solar Pro 4UpstageOpenRouterUnknownNot stated---$0.03$0.12$0.006$2.73 est.
Cohere: Command R7B (12-2024)CohereOpenRoutertextClosed--$0.0375$0.15-$2.74 est.
google/gemini-1.5-flash-8bGoogleDeepInfraUnknownClosed8B--$0.0375$0.15-$2.74 est.
zai-org/AutoGLM-Phone-9B-Multilingual@novitaNot statedHugging FaceUnknownNot stated---$0.04$0.14-$2.75 est.
Gemma 3 12BGoogleNovitamultimodalOpen12B0%$0.05$0.1-$2.80 est.
Google Gemma 3 12BGoogleNovitamultimodalOpen12.2B--$0.05$0.1-$2.80 est.
google/gemma-3-4b-it@deepinfraNot statedHugging FaceUnknownNot stated---$0.05$0.1-$2.80 est.
microsoft/Phi-4-multimodal-instructMicrosoftDeepInfraUnknownOpen14B--$0.05$0.1-$2.80 est.
mistralai/Mistral-Small-3.1-24B-Instruct-2503Mistral AIDeepInfraUnknownOpen24B--$0.05$0.1-$2.80 est.
Inception: Mercury 2.5 PreviewNot statedOpenRouterUnknownNot stated---$0.04$0.15$0.004$2.84 est.
Nemotron 3 Nano 30B A3BNVIDIANVIDIAtextOpen30B-$0.04$0.15$0.004$2.84
openai/gpt-oss-20b@novitaNot statedHugging FaceUnknownNot stated---$0.04$0.15-$2.84 est.
Gryphe/MythoMax-L2-13bGrypheOpenRoutertextOpen13B--$0.06$0.06-$2.85 est.
meta-llama/Llama-3.1-8B-Instruct@nscaleNot statedHugging FaceUnknownNot stated---$0.06$0.06-$2.85 est.
OpenChat 7BOpenChatNovitatextOpen7B--$0.06$0.06-$2.85 est.
Nemotron Nano 9BNVIDIANVIDIA NIMUnknownOpen9B--$0.04$0.16-$2.92 est.
nvidia/NVIDIA-Nemotron-Nano-9B-v2NVIDIADeepInfratextOpen9B--$0.04$0.16-$2.92 est.
openai/gpt-oss-120b@deepinfraNot statedHugging FaceUnknownNot stated---$0.04$0.17-$3.01 est.
Trinity MiniArcee AIVercel AI GatewaytextNot stated--$0.045$0.15-$3.03 est.
GPT OSS 120BOpenAIOpenAIUnknownOpen116.8B13.9%$0.039$0.18$0.0039$3.05
e2ee-qwen-2-5-7b-pAlibabaVenice AIUnknownOpen7B--$0.05$0.13-$3.05 est.
DeepSeek R1 0528 Qwen3 8BDeepSeekNovitatextOpen671B-$0.06$0.09-$3.11 est.
Gemini Embedding 001GoogleFastRoutertextClosed--$0.15$0$0$3.15 est.
Hy-MT2-LiteNot statedTencent Cloud TokenHubUnknownNot stated---$0.044$0.177-$3.22 est.
Tencent Hy-MT2-LiteNot statedAI RouterUnknownNot stated---$0.044$0.177-$3.22 est.
Tencent: Hy-MT2-1.8BTencentOpenRouterUnknownNot stated---$0.044$0.177-$3.22 est.
BaiChuan M2 32BBaichuanNovitatextOpen32B-$0.07$0.07-$3.32 est.
google/codegemma-7b-itGoogleDeepInfraUnknownOpen7B--$0.07$0.07-$3.32 est.
google/gemma-1.1-7b-itGoogleDeepInfraUnknownOpen7B--$0.07$0.07-$3.32 est.
Gemma 3n 4BGoogleOpenRoutertextOpen4.5B-0.7%$0.06$0.12-$3.36 est.
google/gemma-3n-E4B-it@togetherNot statedHugging FaceUnknownNot stated---$0.06$0.12-$3.36 est.
mistralai/Devstral-Small-2505Mistral AIDeepInfratextOpen24B--$0.06$0.12-$3.36 est.
openai/gpt-oss-20b@ovhcloudNot statedHugging FaceUnknownNot stated---$0.05$0.18-$3.48 est.
tongyi-intent-detect-v3Not statedAlibabatextNot stated---$0.058$0.144-$3.49 est.
Amazon Nova MicroAmazonAWS BedrocktextClosed--$0.035$0.14$0.0088$3.50 est.
Nemotron-3-Nano-Omni-30B-TEENVIDIAChutesUnknownOpen30B-$0.0245$0.0978$0.0123$3.55 est.
unsloth/Mistral-Nemo-Instruct-2407-TEEMistral AIChutestextOpen12B-$0.0245$0.0978$0.0123$3.55 est.
e2ee-gpt-oss-20b-pOpenAIVenice AIUnknownOpen21B--$0.05$0.19-$3.57 est.
Qwen 3.5 FlashAlibabaAlibabamultimodalOpen35B-$0.029$0.287-$3.57 est.
qwen3.5-flash-2026-02-23:0-token-128kNot statedAlibabaUnknownNot stated---$0.029$0.287-$3.57 est.
@cf/qwen/qwen2.5-coder-32b-instructAlibabaDeepInfratextOpen32B-$0.06$0.15-$3.61 est.
NVIDIA Nemotron 3 Nano 30B A3BNVIDIANovita AItextOpen30B6.7%$0.05$0.2-$3.65 est.
openai/gpt-oss-20b@nscaleNot statedHugging FaceUnknownNot stated---$0.05$0.2-$3.65 est.
openai/gpt-oss-20b@togetherNot statedHugging FaceUnknownNot stated---$0.05$0.2-$3.65 est.
qwen-turboAlibabaAlibabatextNot stated---$0.05$0.2-$3.65 est.
Mistral EmbedMistral AIAI RoutertextNot stated--$0.1$0-$3.90 est.
microsoft/phi-4MicrosoftDeepInfratextOpen14.7B--$0.07$0.14-$3.92 est.
microsoft/phi-4@deepinfraNot statedHugging FaceUnknownNot stated---$0.07$0.14-$3.92 est.
deepseek-r1-distill-qwen-7bdeepseekAlibabatextNot stated--$0.072$0.144-$4.03 est.
Qwen/Qwen2.5-Coder-32B-Instruct@nscaleNot statedHugging FaceUnknownNot stated---$0.06$0.2-$4.04 est.
openai/gpt-oss-120b@novitaNot statedHugging FaceUnknownNot stated---$0.05$0.25-$4.08 est.
qwen-vl-ocrAlibabaAlibabamultimodalNot stated--$0.07$0.16-$4.09 est.
Doubao Seed 2 0 MiniByteDanceByteDancetextClosed--$0.029$0.29$0.006$4.15
Muse Spark 1.2 ContributorMetaAI RoutermultimodalNot stated---$0.1$0.2$0.002$4.16 est.
Muse Spark 1.3 ContributorNot statedAI RouterUnknownNot stated---$0.1$0.2$0.002$4.16 est.
Qwen/Qwen3-8B@nscaleNot statedHugging FaceUnknownNot stated---$0.07$0.18-$4.26 est.
NVIDIA Nemotron Nano 2Not statedAWS BedrockUnknownNot stated---$0.06$0.23-$4.30 est.
Nvidia Nemotron Nano 9B V2NVIDIAAI RoutertextNot stated--$0.06$0.23-$4.30 est.
Nemotron-3-Nano-OmniNVIDIANebius AI StudiotextOpen15B-$0.06$0.24-$4.38 est.
Nova LiteAmazonAI RoutermultimodalNot stated--$0.06$0.24-$4.38 est.
nova-lite-v1AmazonOpenRoutermultimodalClosed---$0.06$0.24-$4.38 est.
Nvidia Nemotron Nano 3 30BNVIDIAAWS BedrocktextNot stated--$0.06$0.24-$4.38 est.
GPT OSS Safeguard 20BOpenAIAI RoutertextOpen21.5B-$0.07$0.2-$4.43 est.
Qwen/Qwen3-14B@nscaleNot statedHugging FaceUnknownNot stated---$0.07$0.2-$4.43 est.
Google Gemma 3 27BGoogleDeepInframultimodalOpen27.4B--$0.08$0.16-$4.48 est.
google/gemma-3-27b-it@deepinfraNot statedHugging FaceUnknownNot stated---$0.08$0.16-$4.48 est.
Gemini 2.5 Flash LiteGoogleOpenRouterUnknownClosed--$0.05$0.2$0.01$4.55 est.
NVIDIA Nemotron 3.5 Lightning 30B A3BNVIDIAFireworks AIUnknownNot stated---$0.05$0.2$0.01$4.55 est.
qwen-doc-turboAlibabaAlibabatextNot stated---$0.087$0.144-$4.62 est.
mistral-small-3.2-24b-instruct-2506Mistral AIDeepInframultimodalOpen24B--$0.075$0.2-$4.62 est.
Mistral: Mistral Small 3.2 24BMistral AIOpenRoutermultimodalOpen24B-$0.075$0.2-$4.62 est.
deepseek-ai/DeepSeek-V4-Flash-0731@deepinfraNot statedHugging FaceUnknownNot stated---$0.08$0.18-$4.65 est.
MiMo M2.5XiaomiOpenModel.aimultimodalOpen310.8B-$0.112$0.224$0.0022$4.66 est.
Embed v4.0CohereAI RoutertextNot stated--$0.12$0-$4.68 est.
Voyage 4 LargeVoyage AIAI RoutertextNot stated--$0.12$0-$4.68 est.
Voyage Code 2Voyage AIAI RoutertextNot stated--$0.12$0-$4.68 est.
Voyage Finance 2Voyage AIAI RoutertextNot stated--$0.12$0-$4.68 est.
Voyage Law 2Voyage AIAI RoutertextNot stated--$0.12$0-$4.68 est.
Qwen: Qwen3.5-FlashAlibabaOpenRoutermultimodalOpen35B--$0.065$0.26-$4.75 est.
DeepSeek V4 Flash LatestDeepSeekOpenRoutertextOpen284B-$0.05$0.16$0.013$4.75 est.
ministral-3-3bNot statedMistral AIUnknownNot stated--0%$0.1$0.1$0.01$4.75 est.
ministral-3b-2512Mistral AIOpenRoutermultimodalOpen3B-$0.1$0.1$0.01$4.75 est.
glm-4-32b-0414-128kZhipu AIZhipu AItextNot stated--$0.1$0.1-$4.75 est.
KoboldAI/LLaMA2-13B-TiefighterKoboldAIDeepInfraUnknownOpen13B--$0.1$0.1-$4.75 est.
Meta Llama 3.2 1BMetaAWS BedrockUnknownNot stated---$0.1$0.1-$4.75 est.
Ministral 3 - 3BMistral AIMistral AItextOpen3B-$0.1$0.1-$4.75 est.
Ministral 3BMistral AIAI RouterUnknownNot stated--$0.1$0.1-$4.75 est.
Ministral 3B 3.0Not statedAWS BedrockUnknownNot stated---$0.1$0.1-$4.75 est.
Mistral Ministral 3B 3.0Mistral AIAWS BedrockmultimodalNot stated--$0.1$0.1-$4.75 est.
Reka EdgeReka AIOpenRoutermultimodalOpen7.1B-$0.1$0.1-$4.75 est.
tencent/hy3-previewTencentSiliconFlowtextOpen295B-$0.066$0.26-$4.78 est.
Nemotron 3.5 Lightning 30BNVIDIANVIDIAUnknownNot stated--24.3%$0.08$0.2-$4.82 est.
@cf/qwen/qwen3-30b-a3b-fp8AlibabaCloudflare Workers AItextOpen30B-$0.051$0.335-$4.84 est.
inclusionAI: Ling 3.0 Flash FinNot statedOpenRouterUnknownNot stated---$0.06$0.18$0.012$4.95 est.
glm-4.6v-flashxZhipu AIZhipu AImultimodalNot stated--$0.04$0.4$0.004$4.96 est.
deepseek-ai/DeepSeek-V4-Flash@deepinfraNot statedHugging FaceUnknownNot stated---$0.09$0.18-$5.04 est.
baidu-ernie-4.5-vl-424b-a47bNot statedNovita AIUnknownNot stated---$0.07$0.28-$5.11 est.
ERNIE 4.5 21B A3BBaiduNovitatextOpen21B--$0.07$0.28-$5.11 est.
mistralai/Devstral-Small-2507Mistral AIDeepInfratextOpen24B--$0.07$0.28-$5.11 est.
allenai/olmOCR-2-7B-1025Allen Institute for AI (AI2)DeepInfraUnknownOpen7B--$0.09$0.19-$5.13 est.
XiaomiMiMo/MiMo-V2-FlashXiaomiOpenModel.aitextNot stated-61.8%$0.08$0.24$0.008$5.16 est.
Qwen/Qwen3.5-9B@deepinfraNot statedHugging FaceUnknownNot stated---$0.1$0.15-$5.18 est.
qwen3.5-9bAlibabaDeepInframultimodalOpen9B-21.3%$0.1$0.15-$5.18 est.
Qwen/Qwen3-32B@nscaleNot statedHugging FaceUnknownNot stated---$0.08$0.25-$5.25 est.
qwen-long-2025-01-25Not statedAlibabaUnknownNot stated---$0.072$0.287-$5.25 est.
qwen-long-latestNot statedAlibabaUnknownNot stated---$0.072$0.287-$5.25 est.
OpenAI gpt-oss-20bOpenAIAWS BedrocktextNot stated--$0.07$0.3-$5.28 est.
openai/gpt-oss-20b@fireworks-aiNot statedHugging FaceUnknownNot stated---$0.07$0.3-$5.28 est.
GPT-5 nanoOpenAIOpenAIUnknownClosed--$0.05$0.4$0.005$5.35 est.
qwen-flash-2025-07-28-us:0-token-256kNot statedAlibabaUnknownNot stated---$0.05$0.4-$5.35 est.
qwen-flash-characterNot statedAlibabaUnknownNot stated---$0.05$0.4-$5.35 est.
qwen-flash-us:0-token-256kNot statedAlibabaUnknownNot stated---$0.05$0.4-$5.35 est.
qwen3-vl-flash-2025-10-15-us:0-token-32kNot statedAlibabaUnknownNot stated---$0.05$0.4-$5.35 est.
qwen3-vl-flash-2025-10-15:0-token-32kNot statedAlibabaUnknownNot stated---$0.05$0.4-$5.35 est.
qwen3-vl-flash-2026-01-22-us:0-token-32kNot statedAlibabaUnknownNot stated---$0.05$0.4-$5.35 est.
qwen3-vl-flash-2026-01-22:0-token-32kNot statedAlibabaUnknownNot stated---$0.05$0.4-$5.35 est.
qwen3-vl-flash-us:0-token-32kNot statedAlibabaUnknownNot stated---$0.05$0.4-$5.35 est.
qwen3-vl-flash:0-token-32kNot statedAlibabaUnknownNot stated---$0.05$0.4-$5.35 est.
Hy-MT2-PlusNot statedTencent Cloud TokenHubUnknownNot stated---$0.074$0.295-$5.39 est.
Hy-MT2-ProNot statedTencent Cloud TokenHubUnknownNot stated---$0.074$0.295-$5.39 est.
Tencent Hy-MT2-PlusNot statedAI RouterUnknownNot stated---$0.074$0.295-$5.39 est.
Tencent Hy-MT2-ProNot statedAI RouterUnknownNot stated---$0.074$0.295-$5.39 est.
Tencent: Hy-MT2-30B-A3BTencentOpenRouterUnknownNot stated---$0.074$0.295-$5.39 est.
Tencent: Hy-MT2-7BTencentOpenRouterUnknownNot stated---$0.074$0.295-$5.39 est.
DeepSeek V4 Flash 0731DeepSeekAI RoutertextOpen13B--$0.076$0.153$0.014$5.42 est.
ByteDance Seed: Seed 1.6 FlashByteDanceOpenRoutermultimodalClosed--$0.075$0.3-$5.47 est.
Gemini 2.0 Flash LiteGoogleGooglemultimodalClosed---$0.075$0.3$0.0075$5.47
google/gemini-1.5-flashGoogleDeepInfraUnknownClosed4B--$0.075$0.3-$5.47 est.
Qwen/Qwen3-32B@deepinfraNot statedHugging FaceUnknownNot stated---$0.08$0.28-$5.50 est.
Reka Flash 3Reka AIOpenRoutertextOpen20.9B-$0.1$0.2-$5.60 est.
swiss-ai/Apertus-8B-Instruct-2509@publicaiNot statedHugging FaceUnknownNot stated---$0.1$0.2-$5.60 est.
swiss-ai/Apertus-v1.5-8B@publicaiNot statedHugging FaceUnknownNot stated---$0.1$0.2-$5.60 est.
google/gemma-4-26B-A4B-it@deepinfraNot statedHugging FaceUnknownNot stated---$0.07$0.34-$5.62 est.
microsoft/phi-4-reasoning-plusMicrosoftDeepInfratextOpen14B--$0.07$0.35-$5.70 est.
GLM 4.7 FlashZAICloudflare Workers AItextOpen30B-$0.06$0.4-$5.74 est.
zai-org/GLM-4.7-Flash@deepinfraNot statedHugging FaceUnknownNot stated---$0.06$0.4-$5.74 est.
Deepseek ChatDeepSeekDeepSeektextNot stated--$0.14$0.28$0.0028$5.82
Deepseek ReasonerDeepSeekDeepSeektextOpen671B-$0.14$0.28$0.0028$5.82
DeepSeek V4 FlashDeepSeekDeepSeektextOpen290.9B-78.7%$0.14$0.28$0.0028$5.82
DeepSeek-V4-Flash 0731 Official Release (Vendor Direct)Not statedTencent Cloud TokenHubUnknownNot stated---$0.14$0.28$0.0028$5.82 est.
Codestral EmbedMistral AIAI RoutertextNot stated--$0.15$0-$5.85 est.
meta-llama/Llama-4-Scout-17B-16E-Instruct@nscaleNot statedHugging FaceUnknownNot stated---$0.09$0.29-$5.98 est.
Amazon Nova LiteAmazonAWS BedrockmultimodalClosed--$0.06$0.24$0.015$6.00 est.
Z.ai: GLM Flash LatestNot statedOpenRouterUnknownNot stated---$0.0713$0.2375$0.0143$6.08 est.
qwen3.5-35b-a3b:0-token-128kAlibabaAlibabaUnknownOpen35B-40.8%$0.057$0.459-$6.12 est.
zai-org/GLM-4.7-Flash@novitaNot statedHugging FaceUnknownNot stated---$0.07$0.4-$6.13 est.
Austism/chronos-hermes-13b-v2Not statedDeepInfraUnknownOpen13B--$0.13$0.13-$6.18 est.
meta-llama/Llama-2-13b-chat-hfMetaDeepInfraUnknownOpen13B--$0.13$0.13-$6.18 est.
NovaSky-AI/Sky-T1-32B-PreviewNot statedDeepInfraUnknownOpen32B--$0.12$0.18-$6.21 est.
Qwen/Qwen3.5-9B@ovhcloudNot statedHugging FaceUnknownNot stated---$0.12$0.18-$6.21 est.
Qwen/QwQ-32B-PreviewAlibabaDeepInfratextOpen32B--$0.12$0.18-$6.21 est.
Gemma 3 27BGoogleNovitamultimodalOpen27B4.5%$0.119$0.2-$6.34 est.
Ox AlphaZhipu AIZhipu AIUnknownNot stated---$0.075$0.25$0.015$6.40 est.
Mistral Voxtral Small 1.0Mistral AIOpenRoutermultimodalNot stated--$0.1$0.3$0.01$6.45 est.
StepFun 3.5 FlashStepFunStepFunUnknownOpen199.4B-$0.1$0.3$0.01$6.45
@cf/meta/llama-4-scout-17b-16e-instructmetaDeepInfraUnknownOpen109B--$0.1$0.3-$6.45 est.
cosmos3-super-reasonerNot statedNebiustextNot stated--$0.1$0.3-$6.45 est.
Devstral Small 2Mistral AIAI Router +2 moremultimodalNot stated-29.6%$0.1$0.3-$6.45 est.
Devstral Small 2Mistral AIMistral AIUnknownOpen24B--$0.1$0.3-$6.45 est.
gemma-4-12B-itGoogleSiliconFlowtextOpen12B-27.3%$0.1$0.3-$6.45 est.
Llama 4 Scout 17B InstructMetaOpenRoutermultimodalOpen17B3.7%$0.1$0.3-$6.45 est.
Llama-4-Scout-17B-16EMetaDeepInfraUnknownNot stated---$0.1$0.3-$6.45 est.
meta-llama/Llama-4-Scout-17B-16E-Instruct@deepinfraNot statedHugging FaceUnknownNot stated---$0.1$0.3-$6.45 est.
Mistral Small 3.1 (25.03) (Model Garden)Mistral AIGoogle Vertex AIUnknownOpen24B-26.2%$0.1$0.3-$6.45 est.
nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16NVIDIAPrime IntellecttextNot stated--$0.1$0.3-$6.45 est.
stepfun-ai/Step-3.5-Flash@deepinfraNot statedHugging FaceUnknownNot stated---$0.1$0.3-$6.45 est.
Voxtral Small 1.0Mistral AIAWS BedrockUnknownOpen24B--$0.1$0.3-$6.45 est.
Voxtral Small 1.0Not statedAWS BedrockUnknownNot stated---$0.1$0.3-$6.45 est.
zai-org-glm-4.7-flashZhipu AIVenice AItextOpen355B-$0.06$0.4$0.01$6.46 est.
llama-3.3-70b-instructMetaOpenRouter +17 moretextOpen70.6B-4.9%$0.1$0.32-$6.62 est.
Llama 3.3 70B InstructMetaMicrosoft Azure AI FoundrytextOpen70B-$0.71$0.71-$33.73 est.
Hermes 2 Pro Llama 3 8BNous ResearchNovitatextOpen8B--$0.14$0.14-$6.65 est.
Llama 3 8B Instruct LiteMetaTogether AIUnknownOpen8B--$0.14$0.14-$6.65 est.
microsoft/Phi-3-medium-4k-instructMicrosoftDeepInfratextOpen14B--$0.14$0.14-$6.65 est.
GLM 4.7 FlashXZhipu AIZhipu AItextNot stated---$0.07$0.4$0.01$6.67 est.
NVIDIA Nemotron 3 Super 120B A12BNVIDIADeepInfra +9 moreUnknownNot stated--38.6%$0.085$0.4-$6.72 est.
NVIDIA Nemotron 3 Super 120B A12BNVIDIANVIDIAtextOpen120B-$0.09$0.45$0.009$7.34
Qwen/Qwen3-14B@deepinfraNot statedHugging FaceUnknownNot stated---$0.12$0.24-$6.72 est.
Qwen3-14BAlibabaAI Router +6 moretextNot stated--$0.12$0.24-$6.72 est.
qwen3-14bAlibabaAlibabatextOpen14B-4.9%$0.35$1.4-$25.55 est.
qwen-plus-2024-12-20Not statedAlibabaUnknownNot stated---$0.115$0.287-$6.92 est.
qwen-plus-2025-01-12Not statedAlibabaUnknownNot stated---$0.115$0.287-$6.92 est.
qwen-plus-2025-07-28:0-token-128kAlibabaAlibabaUnknownClosed---$0.115$0.287-$6.92 est.
qwen-plus-2025-09-11:0-token-128kNot statedAlibabaUnknownNot stated---$0.115$0.287-$6.92 est.
qwen-plus-2025-12-01:0-token-128kNot statedAlibabaUnknownNot stated---$0.115$0.287-$6.92 est.
qwen-plus-latest:0-token-128kNot statedAlibabaUnknownNot stated---$0.115$0.287-$6.92 est.
qwen-plus:0-token-128kAlibabaAlibabaUnknownClosed--$0.115$0.287-$6.92 est.
Voyage Code 3Voyage AIAI RoutertextNot stated--$0.18$0-$7.02 est.
voyage-3-largeVoyage AIAI RoutertextNot stated--$0.18$0-$7.02 est.
@cf/meta/llama-3-8b-instruct-awqNot statedCloudflare Workers AItextNot stated---$0.123$0.266-$7.06 est.
@cf/meta/llama-3.1-8b-instruct-awqNot statedCloudflare Workers AItextNot stated---$0.123$0.266-$7.06 est.
bigcode/starcoder2-15b-instruct-v0.1BigCodeDeepInfraUnknownOpen15B--$0.15$0.15-$7.13 est.
deepseek-ai/DeepSeek-R1-Distill-Qwen-7B@nscaleNot statedHugging FaceUnknownNot stated---$0.15$0.15-$7.13 est.
deepseek-r1-distill-qwen-14bdeepseekNovitatextNot stated--$0.15$0.15-$7.13 est.
Meta Llama 3.2 3BMetaAWS BedrockUnknownNot stated---$0.15$0.15-$7.13 est.
Ministral 3 - 8BMistral AIMistral AItextOpen8B-$0.15$0.15-$7.13 est.
Ministral 8BMistral AIAI RouterUnknownNot stated--$0.15$0.15-$7.13 est.
Ministral 8B 3.0Not statedAWS BedrockUnknownNot stated---$0.15$0.15-$7.13 est.
Ministral 8B 3.0Mistral AIAWS BedrockUnknownOpen8B--$0.15$0.15-$7.13 est.
ministral-3-8bNot statedMistral AIUnknownNot stated--4.1%$0.15$0.15$0.015$7.13 est.
ministral-8b-2512Mistral AIOpenRoutermultimodalOpen8B-$0.15$0.15$0.015$7.13 est.
Mistral Ministral 8B 3.0Mistral AIAWS BedrocktextNot stated--$0.15$0.15-$7.13 est.
Mistral NeMoMistral AIMistral AItextOpen12B-$0.15$0.15-$7.13 est.
Pixtral 12B 2409Mistral AIAI RoutermultimodalNot stated--$0.15$0.15-$7.13 est.
Rnj-1 InstructEssential AITogether AItextOpen8.3B--$0.15$0.15-$7.13 est.
deepseek-ai/DeepSeek-V4-Flash-0731@basetenNot statedHugging FaceUnknownNot stated---$0.13$0.26-$7.28 est.
Gemini 2.5 Flash Lite Preview 09 2025GoogleGooglemultimodalClosed1B-$0.1$0.4$0.01$7.30
ByteDance/Seed-2.0-miniByteDanceOpenRoutermultimodalClosed---$0.1$0.4-$7.30 est.
google/gemini-2.0-flash-001GoogleDeepInframultimodalClosed3B-$0.1$0.4-$7.30 est.
Nemotron Super 49BNVIDIANVIDIA NIMUnknownOpen49B--$0.1$0.4-$7.30 est.
openai/gpt-oss-120b@nscaleNot statedHugging FaceUnknownNot stated---$0.1$0.4-$7.30 est.
inference-net/schematron-v2-turboNot statedInference.netUnknownNot stated---$0.03$0.15$0.03$7.31 est.
openai/gpt-oss-120b@ovhcloudNot statedHugging FaceUnknownNot stated---$0.09$0.47-$7.51 est.
Meta Llama 3.2 11BMetaAWS BedrockUnknownNot stated---$0.16$0.16-$7.60 est.
@cf/meta/llama-3.2-11b-vision-instructMetaCloudflare Workers AImultimodalOpen10.6B-$0.049$0.676-$7.66 est.
Qwen 3.8 Flash NextNot statedAI RouterUnknownNot stated---$0.12$0.4$0.01$7.72 est.
Qwen3 32BAlibabaNovita +14 moretextOpen32B-$0.1$0.45-$7.73 est.
Qwen 3 32BAlibabaAI RoutertextNot stated--$0.16$0.64-$11.68 est.
qwen3-32bAlibabaAlibabatextOpen32B-5.2%$0.16$0.64-$11.68 est.
qwen-mt-liteNot statedAlibabaUnknownNot stated---$0.12$0.36-$7.74 est.
Gemini Embedding 2GoogleAI RoutertextNot stated--$0.2$0-$7.80 est.
deepseek-ai/DeepSeek-V4-Flash-0731@novitaNot statedHugging FaceUnknownNot stated---$0.14$0.28-$7.84 est.
deepseek-ai/DeepSeek-V4-Flash-0731@togetherNot statedHugging FaceUnknownNot stated---$0.14$0.28-$7.84 est.
deepseek-ai/DeepSeek-V4-Flash@novitaNot statedHugging FaceUnknownNot stated---$0.14$0.28-$7.84 est.
Qwen/Qwen3-235B-A22B-Instruct-2507-FP8AlibabaGMI CloudtextOpen235B--$0.0875$0.35$0.0175$7.96 est.
Nous Hermes Llama2 13BNous ResearchNovitatextOpen13B--$0.17$0.17-$8.08 est.
Openhermes2.5 Mistral 7BNous ResearchNovitatextOpen7B--$0.17$0.17-$8.08 est.
nvidia/nemotron3-superNVIDIANVIDIA NIMtextOpen120B--$0.1$0.5-$8.15 est.
openai/gpt-oss-120b@basetenNot statedHugging FaceUnknownNot stated---$0.1$0.5-$8.15 est.
openai/gpt-oss-20b@groqNot statedHugging FaceUnknownNot stated---$0.1$0.5-$8.15 est.
Qwen/Qwen3-235B-A22B-Instruct-2507@deepinfraNot statedHugging FaceUnknownNot stated---$0.09$0.55-$8.19 est.
Qwen3 235B A22B 2507AlibabaDeepInfratextOpen235.1B--$0.09$0.55-$8.19 est.
Ling-2.6-flashNot statedNovitatextOpen104B--$0.1$0.3$0.02$8.25 est.
google/gemma-4-31B-it@deepinfraNot statedHugging FaceUnknownNot stated---$0.13$0.38-$8.30 est.
@cf/meta/llama-3.1-8b-instruct-fp8-fastMetaCloudflare Workers AItextNot stated--$0.152$0.287-$8.37 est.
Qwen/Qwen3-235B-A22B-Instruct-2507@novitaNot statedHugging FaceUnknownNot stated---$0.09$0.58-$8.44 est.
Gemma 4 26B A4BgoogleAWS BedrockmultimodalOpen26B39%$0.13$0.4-$8.47 est.
google/gemma-4-26B-A4B-it@novitaNot statedHugging FaceUnknownNot stated---$0.13$0.4-$8.47 est.
Llama-Guard-4-12BMetaDeepInframultimodalOpen12B--$0.18$0.18-$8.55 est.
meta-llama/Llama-Guard-4-12B@deepinfraNot statedHugging FaceUnknownNot stated---$0.18$0.18-$8.55 est.
Qwen/Qwen3.5-9B@togetherNot statedHugging FaceUnknownNot stated---$0.17$0.25-$8.76 est.
Gemma 4 31BGoogleAWS BedrockmultimodalOpen31B29.2%$0.14$0.4-$8.86 est.
google/gemma-4-31B-it@novitaNot statedHugging FaceUnknownNot stated---$0.14$0.4-$8.86 est.
meta-llama/Llama-3.3-70B-Instruct@novitaNot statedHugging FaceUnknownNot stated---$0.14$0.4-$8.86 est.
Qwen/Qwen3-30B-A3B@deepinfraNot statedHugging FaceUnknownNot stated---$0.12$0.5-$8.93 est.
Qwen3-30B-A3BAlibabaAI Router +5 moretextNot stated--$0.12$0.5-$8.93 est.
qwen3-30b-a3bAlibabaAlibabaUnknownNot stated---$0.2$0.8-$14.60 est.
OpenAI: GPT-5.6 Luna Pro (batch)OpenAIOpenRouterUnknownClosed--$0.1$0.6$0.01$9.00 est.
Qwen/Qwen3-VL-4B-InstructAlibabaDeepInfraUnknownOpen4B--$0.1$0.6-$9.00 est.
qwen3.5-27b:0-token-128kAlibabaAlibabaUnknownOpen27B-$0.086$0.688-$9.20 est.
@cf/qwen/qwq-32bAlibabaDeepInfratextOpen32B-$0.15$0.4-$9.25 est.
xiaomimimo-mimo-v2.5XiaomiNovitaUnknownOpen310B--$0.168$0.336-$9.41 est.
ministral-14b-2512Mistral AIOpenRoutermultimodalOpen14B--$0.2$0.2$0.02$9.50 est.
ministral-3-14bNot statedMistral AIUnknownNot stated--9.7%$0.2$0.2$0.02$9.50 est.
deepseek-ai/DeepSeek-R1-Distill-Qwen-14B@nscaleNot statedHugging FaceUnknownNot stated---$0.2$0.2-$9.50 est.
meta-llama/Llama-Guard-4-12B@togetherNot statedHugging FaceUnknownNot stated---$0.2$0.2-$9.50 est.
Ministral 14BMistral AIAI RoutermultimodalNot stated--$0.2$0.2-$9.50 est.
Ministral 14B 3.0Not statedAWS BedrockUnknownNot stated---$0.2$0.2-$9.50 est.
Ministral 3 - 14BMistral AIMistral AIUnknownOpen14B--$0.2$0.2-$9.50 est.
Mistral AINot statedDigitalOceanUnknownNot stated---$0.2$0.2-$9.50 est.
Mistral Ministral 14B 3.0Mistral AIAWS BedrocktextNot stated--$0.2$0.2-$9.50 est.
Ling-2.6-1TAnt Group / InclusionAIOpenRoutertextOpen73B-$0.075$0.625$0.015$9.59 est.
Ring-2.6-1TAnt Group / InclusionAIOpenRoutertextOpen63B-43.1%$0.075$0.625$0.015$9.59 est.
Doubao Seed 2.0 LiteByteDanceByteDancemultimodalClosed--$0.088$0.53$0.018$9.59
e2ee-gemma-3-27b-pGoogleVenice AIUnknownOpen27B--$0.14$0.5-$9.71 est.
Gemini 2.0 FlashGoogleGooglemultimodalClosed---$0.1$0.4$0.025$10.00
GPT-4.1 nanoOpenAIOpenAImultimodalClosed-3.7%$0.1$0.4$0.025$10.00 est.
Qwen: Qwen3.8 FlashNot statedOpenRouterUnknownNot stated---$0.15$0.47$0.016$10.03 est.
Olmo 3 32B ThinkAllen Institute for AI (AI2)OpenRoutertextOpen32.2B--$0.15$0.5-$10.10 est.
ERNIE 4.5 VL 28B A3BBaiduNovitamultimodalOpen28B-$0.14$0.56-$10.22 est.
Qwen 3.8 FlashNot statedAI RouterUnknownNot stated---$0.16$0.47$0.016$10.24 est.
Tencent: Hunyuan A13B InstructTencentOpenRoutertextOpen3B--$0.14$0.57-$10.31 est.
Qwen 3.5 PlusAlibabaAlibabamultimodalOpen397B--$0.115$0.688-$10.33 est.
qwen3.5-plus-2026-02-15:0-token-128kNot statedAlibabaUnknownNot stated---$0.115$0.688-$10.33 est.
qwen3.5-plus-2026-04-20:0-token-128kAlibabaAlibabaUnknownOpen397B-$0.115$0.688-$10.33 est.
tencent/Hy3@deepinfraNot statedHugging FaceUnknownNot stated---$0.14$0.58-$10.39 est.
qwen-mt-flashNot statedAlibabaUnknownNot stated---$0.16$0.49-$10.41 est.
qwen-mt-turboAlibabaAlibabatextNot stated---$0.16$0.49-$10.41 est.
Llama 3.1 8B InstructMetaAI RoutertextOpen8B-$0.22$0.22-$10.45 est.
Meta Llama 3.1 8BMetaAWS BedrocktextNot stated--$0.22$0.22-$10.45 est.
NVIDIA-Nemotron-3.5-LightningNVIDIADeepInfraUnknownNot stated---$0.08$0.2$0.04$10.58 est.
gemma-4-uncensoredGoogleVenice AImultimodalOpen30.7B-$0.1625$0.5-$10.59 est.
e2ee-gpt-oss-120b-pOpenAIVenice AIUnknownOpen117B--$0.13$0.65-$10.60 est.
Granite 4.1 8BIBMOpenRoutertextOpen8.8B-3.4%$0.05$0.1$0.05$10.90 est.
Cohere: Command R (08-2024)CohereOpenRoutertextClosed--$0.15$0.6-$10.95 est.
Gemma 4 26B (Model Garden)GoogleGoogle Vertex AImultimodalOpen26B--$0.15$0.6-$10.95 est.
GPT OSS Safeguard 120BOpenAIAI Router +2 moretextNot stated--$0.15$0.6-$10.95 est.
GPT OSS Safeguard 120BOpenAIAWS BedrocktextOpen120B-$0.15$0.6-$10.95 est.
llama-3.2-3bMetaVenice AItextOpen3B-$0.15$0.6-$10.95 est.
Mistral SmallMistral AIMistral AImultimodalOpen24B-$0.15$0.6$0.015$10.95
Mistral Small 4Mistral AIMistral AImultimodalOpen24B-$0.15$0.6-$10.95 est.
mistral-small-4Mistral AIMistral AImultimodalNot stated-21%$0.15$0.6$0.015$10.95 est.
mistral-small-2603Mistral AIOpenRoutermultimodalOpen24B-$0.15$0.6$0.015$10.95 est.
OpenAI gpt-oss-120bOpenAIAWS BedrocktextNot stated--$0.15$0.6-$10.95 est.
openai/gpt-4o-mini-search-previewOpenAIFastRoutertextClosed5B--$0.15$0.6-$10.95 est.
openai/gpt-oss-120b@fireworks-aiNot statedHugging FaceUnknownNot stated---$0.15$0.6-$10.95 est.
openai/gpt-oss-120b@togetherNot statedHugging FaceUnknownNot stated---$0.15$0.6-$10.95 est.
Palmyra Vision 7BNot statedAWS BedrockUnknownNot stated---$0.15$0.6-$10.95 est.
Qwen 3 Coder 30B A3B InstructAlibabaAI RoutertextNot stated--$0.15$0.6-$10.95 est.
Qwen Qwen3 32BAlibabaAWS BedrocktextNot stated--$0.15$0.6-$10.95 est.
Qwen Qwen3 Coder 30B A3BAlibabaAWS BedrocktextNot stated--$0.15$0.6-$10.95 est.
Qwen/Qwen2.5-VL-32B-InstructAlibabaFastRoutermultimodalOpen32B--$0.15$0.6-$10.95 est.
Qwen/Qwen3-VL-30B-A3B-Instruct@deepinfraNot statedHugging FaceUnknownNot stated---$0.15$0.6-$10.95 est.
Upstage: Solar Pro 3UpstageOpenRoutertextOpen102B-12%$0.15$0.6$0.015$10.95 est.
olafangensan-glm-4.7-flash-hereticNot statedVenice AItextOpen355B-$0.07$0.4$0.035$11.17 est.
aisingapore/Gemma-SEA-LION-v4-27B-IT@publicaiNot statedHugging FaceUnknownNot stated---$0.2$0.4-$11.20 est.
Jamba 1.5 MiniAI21 LabsAWS BedrockUnknownNot stated---$0.2$0.4-$11.20 est.
Jamba Mini 2AI21 LabsAI21 LabstextOpen52B-$0.2$0.4$0.02$11.20
Gemini 3.1 Flash LiteGoogleOpenRouterUnknownClosed--$0.125$0.75$0.0125$11.25 est.
GoogleNot statedDigitalOceanUnknownNot stated---$0.18$0.5-$11.27 est.
Nvidia NVIDIA Nemotron 3 Super 120B A12BNVIDIAAWS BedrocktextNot stated--$0.15$0.65-$11.38 est.
cognitivecomputations/dolphin-2.6-mixtral-8x7bCognitive ComputationsDeepInfraUnknownOpen46.7B--$0.24$0.24-$11.40 est.
DeepSeek V4 Flash Vision ExpDeepSeekAI RouterUnknownNot stated---$0.22$0.66$0.007$11.49 est.
DeepSeek V4 Flash Vision Exp (off-peak)DeepSeekDeepSeekUnknownNot stated--$0.22$0.66$0.007$11.49 est.
DeepSeek-V4-Flash 0731 Official Release (Vendor Direct, New Pricing)Not statedTencent Cloud TokenHubUnknownNot stated---$0.22$0.66$0.007$11.49 est.
DeepSeek-V4-Flash 0731 Official Release (Vendor Direct, New Pricing)Not statedTencent Cloud TokenHubUnknownNot stated---$0.44$1.32$0.014$22.98 est.
deepseek-v4-flash-off-peakNot statedDeepSeekUnknownNot stated---$0.22$0.66$0.007$11.49 est.
e2ee-gemma-4-31bGoogleVenice AIUnknownOpen31B--$0.139$0.43$0.028$11.61 est.
qwen3-vl-32b-instructAlibabaAlibabamultimodalNot stated---$0.16$0.64-$11.68 est.
qwen3-vl-32b-thinkingNot statedAlibabamultimodalNot stated---$0.16$0.64-$11.68 est.
Qwen/Qwen3.6-35B-A3B@deepinfraNot statedHugging FaceUnknownNot stated---$0.1$0.95-$11.98 est.
MiMo V2.5 ProXiaomiGMI CloudtextOpen1T-$0.3045$0.609$0.0025$12.02 est.
Llama 4 Scout InstructMetaNovitaUnknownOpen109B--$0.18$0.59-$12.04 est.
meta-llama-llama-4-maverick-17b-128e-instruct-fp8Not statedNovita AIUnknownNot stated---$0.18$0.59-$12.04 est.
meta-llama/Llama-4-Scout-17B-16E-Instruct@novitaNot statedHugging FaceUnknownNot stated---$0.18$0.59-$12.04 est.
x-ai/grok-4.1-fastxAIFastRoutermultimodalClosed--$0.2$0.5-$12.05 est.
inference-net/schematron-v2-smallNot statedInference.netUnknownNot stated---$0.05$0.25$0.05$12.17 est.
openai/gpt-oss-120b@groqNot statedHugging FaceUnknownNot stated---$0.15$0.75-$12.23 est.
Meta Llama 4 Scout 17BMetaAWS BedrockmultimodalNot stated--$0.17$0.66-$12.24 est.
allenai/olmOCR-2Allen Institute for AI (AI2)DeepInfraUnknownOpen8B--$0.14$0.8-$12.26 est.
allenai/olmOCR-7B-0825Allen Institute for AI (AI2)DeepInfraUnknownOpen7B--$0.14$0.8-$12.26 est.
allenai/olmOCR-7B-1025Allen Institute for AI (AI2)DeepInfraUnknownOpen7B--$0.14$0.8-$12.26 est.
PaddlePaddle/PaddleOCR-VL-0.9BBaiduDeepInfraUnknownOpen900M--$0.14$0.8-$12.26 est.
qwen3.5-122b-a10b:0-token-128kAlibabaAlibabaUnknownOpen122B-47.2%$0.115$0.917-$12.28 est.
zai-org/GLM-4.5-Air@novitaNot statedHugging FaceUnknownNot stated---$0.13$0.85-$12.29 est.
IBM: Granite 4.2 8BNot statedOpenRouterUnknownNot stated---$0.1$0.15$0.05$12.38 est.
Qwen/Qwen3-VL-4B-ThinkingAlibabaDeepInfraUnknownOpen4B--$0.1$1-$12.40 est.
openai/gpt-oss-120b@scalewayNot statedHugging FaceUnknownNot stated---$0.17$0.68-$12.41 est.
gemma3-27b-itNot statedParasailtextNot stated---$0.08$0.45$0.04$12.70 est.
GLM 5.3 FlashNot statedAI RouterUnknownNot stated---$0.15$0.5$0.03$12.80 est.
deepseek-r1-distill-qwen-32bdeepseekDeepInfratextOpen32B--$0.27$0.27-$12.83 est.
google/gemma-2-27b-itGoogleDeepInfratextOpen27.2B--$0.27$0.27-$12.83 est.
Qwen/Qwen3-Next-80B-A3B-Instruct@deepinfraNot statedHugging FaceUnknownNot stated---$0.09$1.1-$12.86 est.
Mistral: SabaMistral AIOpenRoutermultimodalOpen24B-$0.2$0.6$0.02$12.90 est.
allenai/Olmo-3.1-32B-InstructAllen Institute for AI (AI2)DeepInfraUnknownOpen32B--$0.2$0.6-$12.90 est.
Amazon Titan Text ExpressAmazonAWS BedrockUnknownClosed---$0.2$0.6-$12.90 est.
Nemotron Nano 12B VLNVIDIANVIDIA NIMUnknownOpen12B--$0.2$0.6-$12.90 est.
Nvidia Nemotron Nano 12B V2 VLNVIDIAAI RoutermultimodalNot stated--$0.2$0.6-$12.90 est.
NVIDIA Nemotron Nano 2 VLNot statedAWS BedrockUnknownNot stated---$0.2$0.6-$12.90 est.
Nvidia NVIDIA Nemotron Nano 2 VLNVIDIAAWS BedrockmultimodalNot stated--$0.2$0.6-$12.90 est.
nvidia/NVIDIA-Nemotron-Nano-12B-v2-VLNVIDIADeepInfraUnknownOpen12B--$0.2$0.6-$12.90 est.
Qwen/Qwen3-235B-A22B-Instruct-2507@nscaleNot statedHugging FaceUnknownNot stated---$0.2$0.6-$12.90 est.
Qwen/Qwen3-235B-A22B@nscaleNot statedHugging FaceUnknownNot stated---$0.2$0.6-$12.90 est.
qwen3-vl-8b-instructAlibabaAlibabamultimodalOpen8.8B--$0.18$0.7-$12.97 est.
e2ee-qwen3-30b-a3b-pAlibabaVenice AIUnknownOpen30B--$0.19$0.69-$13.28 est.
Mistral Small 3.2 24BNot statedParasailUnknownNot stated---$0.09$0.3$0.05$13.44 est.
qwen-vl-plusAlibabaAlibabamultimodalNot stated--$0.21$0.63-$13.55 est.
Kat Coder Air V2.5KuaishouAI RouterUnknownClosed--$0.15$0.6$0.03$13.65 est.
Llama 4 Maverick 17B InstructMetaOpenRoutermultimodalOpen17B-7.9%$0.2$0.696-$13.72 est.
Qwen/Qwen3-VL-30B-A3B-Instruct@novitaNot statedHugging FaceUnknownNot stated---$0.2$0.7-$13.75 est.
e2ee-deepseek-v4-flashDeepSeekVenice AIUnknownOpen284B--$0.182$0.373$0.038$13.83 est.
deepseek-ai/DeepSeek-V3.2@novitaNot statedHugging FaceUnknownNot stated---$0.27$0.4-$13.93 est.
Qwen/Qwen3.5-35B-A3B@deepinfraNot statedHugging FaceUnknownNot stated---$0.14$1-$13.96 est.
aisingapore/Qwen-SEA-LION-v4-32B-IT@publicaiNot statedHugging FaceUnknownNot stated---$0.25$0.5-$14.00 est.
Qwen/QVQ-72B-PreviewAlibabaDeepInfraUnknownOpen72B--$0.25$0.5-$14.00 est.
Rocinante 12BTheDrummerOpenRoutertextOpen12.2B-$0.25$0.5-$14.00 est.
deepseek-ai/DeepSeek-V3.2-Exp@novitaNot statedHugging FaceUnknownNot stated---$0.27$0.41-$14.01 est.
deepseek-v3.2-expDeepSeekNovitatextOpen685.4B--$0.27$0.41-$14.01 est.
Qwen/Qwen2.5-7B-Instruct@togetherNot statedHugging FaceUnknownNot stated---$0.3$0.3-$14.25 est.
Llama-4-Maverick-17B-128EMetaDeepInfraUnknownNot stated---$0.2$0.8-$14.60 est.
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8metaDeepInframultimodalOpen400B--$0.2$0.8-$14.60 est.
nvidia/Nemotron-3-Nano-Omni-30B-A3B-ReasoningNVIDIADeepInframultimodalOpen30B-$0.2$0.8-$14.60 est.
qwen-qwen-2.5-72b-instructAlibabaNovita AI +5 moreUnknownOpen72.7B--$0.2$0.8-$14.60 est.
Qwen/Qwen2.5-72B-InstructAlibabaDeepInfratextOpen72B--$0.36$0.4-$17.44 est.
qwen-qwen3-235b-a22b-fp8AlibabaNovitaUnknownNot stated--$0.2$0.8-$14.60 est.
Qwen/Qwen3-235B-A22B@novitaNot statedHugging FaceUnknownNot stated---$0.2$0.8-$14.60 est.
qwen3-30b-a3b-instruct-2507AlibabaAlibabatextOpen30B--$0.2$0.8-$14.60 est.
qwen3-vl-30b-a3b-instructAlibabaAlibabamultimodalOpen30B-$0.2$0.8-$14.60 est.
Hy3TencentTencenttextOpen295B64.4%$0.15$0.59$0.037$14.83
e2ee-gemma-4-26b-a4b-uncensored-pGoogleVenice AIUnknownOpen26B--$0.19$0.88-$14.89 est.
Qwen/Qwen3-32B-TEEAlibabaChutestextOpen32B--$0.104$0.416$0.052$15.08 est.
meta-llama/Meta-Llama-3-70B-InstructMetaDeepInfratextOpen70B-$0.3$0.4-$15.10 est.
Qwen/Qwen3-VL-235B-A22B-Instruct@deepinfraNot statedHugging FaceUnknownNot stated---$0.2$0.88-$15.28 est.
venice-uncensored-1-2Not statedVenice AImultimodalOpen24B-$0.2$0.9-$15.45 est.
Venice: UncensoredCognitive ComputationsOpenRoutertextOpen24B-$0.2$0.9-$15.45 est.
qwen3.5-397b-a17b:0-token-128kAlibabaAlibabaUnknownOpen397B-51.3%$0.172$1.032-$15.48 est.
MiniMax M2.5 High SpeedMiniMaxMiniMaxtextOpen228.7B-$0.15$1.15$0.015$15.63
openai/gpt-oss-120b-UltraOpenAIDeepInfraUnknownOpen117B--$0.2$0.95-$15.88 est.
Qwen 3.6 35B A3B FP8AlibabaNEAR AI CloudtextOpen35B-$0.17$1.1-$15.98 est.
Qwen3 Next 80B A3B InstructAlibabaAlibabatextNot stated---$0.15$1.2-$16.05 est.
Qwen3 Next 80B A3B ThinkingAlibabaAlibabatextOpen80B-6.7%$0.15$1.2-$16.05 est.
Qwen3-Next-80B-Instruct (Model Garden)AlibabaGoogle Vertex AIUnknownOpen80B--$0.15$1.2-$16.05 est.
Qwen Qwen3 235B A22B 2507AlibabaAWS BedrocktextNot stated--$0.22$0.88-$16.06 est.
Qwen3 235B A22BAlibabaAI RoutertextNot stated--$0.22$0.88-$16.06 est.
Mercury 2Inception LabsAI RoutertextClosed4B-27.3%$0.25$0.75$0.025$16.13 est.
qwen2.5-vl-72b-instructAlibabaNebius AI StudiomultimodalOpen73.4B-$0.25$0.75-$16.13 est.
openbmb/MiniCPM-Llama3-V-2_5OpenBMBDeepInfraUnknownOpen8B--$0.34$0.34-$16.15 est.
google/gemma-4-26B-A4B-it@scalewayNot statedHugging FaceUnknownNot stated---$0.29$0.57-$16.15 est.
@cf/ai4bharat/indictrans2-en-indic-1BNot statedCloudflare Workers AItextNot stated---$0.342$0.342-$16.24 est.
@cf/meta/m2m100-1.2bNot statedCloudflare Workers AItextNot stated---$0.342$0.342-$16.24 est.
MiniMaxNot statedDigitalOceanUnknownNot stated---$0.225$0.9-$16.43 est.
google/gemma-4-31B-turbo-TEEGoogleChutesmultimodalOpen31B-$0.12$0.37$0.06$16.47 est.
Gemini 3.5 Flash LiteGoogleOpenRoutermultimodalClosed67B53.6%$0.15$1.25$0.015$16.48 est.
Qwen/Qwen3-Coder-30B-A3B-Instruct@scalewayNot statedHugging FaceUnknownNot stated---$0.23$0.91-$16.71 est.
qwen3-235b-a22b-instruct-2507AlibabaAlibabatextOpen235B-12%$0.23$0.92-$16.79 est.
command-lightNot statedCohereUnknownNot stated---$0.3$0.6-$16.80 est.
Meta Llama 3 8BMetaAWS BedrockUnknownNot stated---$0.3$0.6-$16.80 est.
gemma-4-31B-it-UltraGoogleDeepInfraUnknownNot stated---$0.27$0.76-$16.99 est.
deepseek-ai/DeepSeek-V3-0324@deepinfraNot statedHugging FaceUnknownNot stated---$0.24$0.9-$17.01 est.
cognitivecomputations/dolphin-2.9.1-llama-3-70bCognitive ComputationsDeepInfraUnknownOpen70B--$0.35$0.4-$17.05 est.
lizpreciatior/lzlv_70b_fp16_hfNot statedDeepInfraUnknownOpen70B--$0.35$0.4-$17.05 est.
mattshumer/Reflection-Llama-3.1-70BNot statedDeepInfraUnknownOpen70B--$0.35$0.4-$17.05 est.
meta-llama/Llama-3.2-90B-Vision-InstructMetaDeepInframultimodalOpen90B-$0.35$0.4-$17.05 est.
Qwen/Qwen2-72B-InstructAlibabaDeepInfraUnknownOpen72B--$0.35$0.4-$17.05 est.
INTELLECT-3Prime IntellectNebius AI StudiotextOpen100B-$0.2$1.1-$17.15 est.
MiniMax: MiniMax-01MiniMaxOpenRoutermultimodalOpen456.1B-$0.2$1.1-$17.15 est.
DeepSeek V4 Pro 0813DeepSeekDeepSeek +23 moretextOpen1.6T78.7%$0.435$0.87$0.0036$17.18
DeepSeek-V4-Pro-0813DeepSeekGMI CloudtextNot stated---$1.122$3.366$0.0374$58.91 est.
DeepSeek-V4-Pro 0813 Official Release (Vendor Direct)Not statedTencent Cloud TokenHubUnknownNot stated---$0.435$0.87$0.0036$17.18 est.
gemma-4-31b-itNot statedParasailtextNot stated---$0.15$0.4$0.06$17.35 est.
e2ee-qwen3-vl-30b-a3b-pAlibabaVenice AIUnknownOpen30B--$0.25$0.9-$17.40 est.
Qwen/Qwen2.5-72B-Instruct@deepinfraNot statedHugging FaceUnknownNot stated---$0.36$0.4-$17.44 est.
Grok 4.1 Fast Non-ReasoningNot statedAI RouterUnknownNot stated---$0.2$0.5$0.05$17.45 est.
Grok 4.1 Fast ReasoningNot statedAI RoutermultimodalNot stated---$0.2$0.5$0.05$17.45 est.
deepreinforce-ai/Ornith-1.0-35BNot statedDeepInfraUnknownOpen35B--$0.1$0.75$0.05$17.48 est.
Step 3.7 FlashStepfunNovitamultimodalOpen201.4B-39.3%$0.2$1.15-$17.58 est.
stepfun-ai/Step-3.7-Flash@deepinfraNot statedHugging FaceUnknownNot stated---$0.2$1.15-$17.58 est.
Meituan: LongCat 2.0MeituanOpenRoutertextOpen48B50.2%$0.3$1.2$0.006$17.58 est.
Meta Llama 4 Maverick 17BMetaAWS BedrockmultimodalNot stated--$0.24$0.97-$17.61 est.
Llama 4 Maverick InstructMetaNovitaUnknownOpen400B--$0.27$0.85-$17.76 est.
meta-llama-llama-3.3-70b-instructNot statedNovita AIUnknownNot stated---$0.27$0.85-$17.76 est.
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8@novitaNot statedHugging FaceUnknownNot stated---$0.27$0.85-$17.76 est.
deepseek-ai/DeepSeek-V3.1@deepinfraNot statedHugging FaceUnknownNot stated---$0.25$0.95-$17.83 est.
deepseek-ai/DeepSeek-V4-Flash-0731-TEEDeepSeekChutestextOpen284B-$0.14$0.28$0.07$17.92 est.
Qwen3 Omni 30B A3B InstructAlibabaNovitaotherOpen30B-$0.25$0.97-$18.00 est.
Qwen3 Omni 30B A3B ThinkingAlibabaNovitamultimodalOpen30B-$0.25$0.97-$18.00 est.
GPT 5.6 LunaOpenAIOpenAImultimodalClosed--$0.2$1.2$0.02$18.00 est.
Qwen/Qwen2.5-72B-Instruct@novitaNot statedHugging FaceUnknownNot stated---$0.38$0.4-$18.22 est.
Gemma-4-31B-it-PearlGoogleTogether AIUnknownOpen31B--$0.28$0.86-$18.23 est.
pearl-ai/Gemma-4-31B-it-pearl@togetherNot statedHugging FaceUnknownNot stated---$0.28$0.86-$18.23 est.
deepseek-v3DeepSeekSiliconFlowtextOpen671B16.9%$0.25$1-$18.25 est.
DeepSeek: DeepSeek V3 0324DeepSeekOpenRoutertextOpen684.5B-$0.25$1-$18.25 est.
llama-4-maverick-17bNot statedMicrosoft Azure AI FoundryUnknownNot stated---$0.25$1-$18.25 est.
Mercury Coder Small BetaInception LabsAI RoutertextNot stated--$0.25$1-$18.25 est.
MiniMaxAI/MiniMax-M2.7@deepinfraNot statedHugging FaceUnknownNot stated---$0.25$1-$18.25 est.
Qwen3-Coder-480B-A35BAlibabaSiliconFlowUnknownOpen480B--$0.25$1-$18.25 est.
@cf/aisingapore/gemma-sea-lion-v4-27b-itGoogleCloudflare Workers AItextNot stated--$0.351$0.555-$18.41 est.
@cf/mistralai/mistral-small-3.1-24b-instructMistral AICloudflare Workers AItextOpen24B-$0.351$0.555-$18.41 est.
GPT 5.4 NanoOpenAIOpenAIUnknownClosed--$0.2$1.25$0.02$18.43 est.
qwen-coder-turboNot statedAlibabaUnknownNot stated---$0.287$0.861-$18.51 est.
qwen-math-turboAlibabaAlibabatextNot stated--$0.287$0.861-$18.51 est.
Perceptron: Perceptron Mk1Not statedOpenRoutermultimodalClosed--$0.15$1.5-$18.60 est.
Qwen/Qwen3-Next-80B-A3B-Instruct@novitaNot statedHugging FaceUnknownNot stated---$0.15$1.5-$18.60 est.
deepseek-ai/DeepSeek-V3.1-Terminus@deepinfraNot statedHugging FaceUnknownNot stated---$0.27$0.95-$18.61 est.
qwen3-235b-a22b-instruct-2507Not statedParasailtextNot stated---$0.14$0.8$0.05$18.74 est.
GLM 4.5 AirZhipu AIZhipu AItextNot stated---$0.2$1.1$0.03$18.95 est.
babbage-002OpenAIOpenAItextClosed--$0.4$0.4-$19.00 est.
Meta-Llama-3.1-70B-Instruct-TurboMetaDeepInfraUnknownOpen70.6B--$0.4$0.4-$19.00 est.
nvidia/Llama-3.3-Nemotron-Super-49B-v1.5NVIDIADeepInfratextOpen49B-$0.4$0.4-$19.00 est.
speakleash/Bielik-11B-v3.0-Instruct@publicaiNot statedHugging FaceUnknownNot stated---$0.4$0.4-$19.00 est.
TheDrummer: UnslopNemo 12BTheDrummerOpenRoutertextOpen12.2B--$0.4$0.4-$19.00 est.
DeepSeek V3.1DeepSeekSiliconFlowtextOpen671B--$0.27$1-$19.03 est.
DeepSeek V3.1 TerminusDeepSeekSiliconFlowtextOpen684.5B44.9%$0.27$1-$19.03 est.
deepseek-ai/DeepSeek-V3.1-Terminus@novitaNot statedHugging FaceUnknownNot stated---$0.27$1-$19.03 est.
deepseek-ai/DeepSeek-V3.1@novitaNot statedHugging FaceUnknownNot stated---$0.27$1-$19.03 est.
ReMM SLERP 13BUndi95OpenRoutertextOpen13B--$0.35$0.65-$19.17 est.
CodestralMistral AIMistral AItextOpen22B-$0.3$0.9-$19.35 est.
codestral-2508Mistral AIOpenRoutertextOpen22B-$0.3$0.9$0.03$19.35 est.
Mistral CodestralMistral AIMistral AItextNot stated--$0.3$0.9$0.03$19.35 est.
zai-org/GLM-4.6V-Flash@novitaNot statedHugging FaceUnknownNot stated---$0.3$0.9-$19.35 est.
e2ee-venice-uncensored-24b-pVenice.aiVenice AIUnknownOpen24B--$0.25$1.15-$19.53 est.
GPT-4.1 nano (Fast)Not statedAI RouterUnknownNot stated---$0.2$0.8$0.05$20.00 est.
openai/gpt-oss-120b@cerebrasNot statedHugging FaceUnknownNot stated---$0.35$0.75-$20.03 est.
deepseek-ai/DeepSeek-V3@deepinfraNot statedHugging FaceUnknownNot stated---$0.32$0.89-$20.04 est.
deepseek-ai/DeepSeek-V3-0324DeepSeekNovitatextNot stated--13.9%$0.27$1.12-$20.05 est.
deepseek-ai/DeepSeek-V3-0324@novitaNot statedHugging FaceUnknownNot stated---$0.27$1.12-$20.05 est.
@cf/moondream/moondream3.1-9B-A2BNot statedCloudflare Workers AImultimodalNot stated---$0.3$1-$20.20 est.
ERNIE 4.5 300B A47BBaiduNovitatextOpen300B-$0.28$1.1-$20.27 est.
MiniMaxAI/MiniMax-M3@deepinfraNot statedHugging FaceUnknownNot stated---$0.28$1.1-$20.27 est.
Claude 3 HaikuAnthropicAWS Bedrock +3 moreUnknownNot stated---$0.25$1.25-$20.38 est.
Claude 3 HaikuAnthropicAI RoutermultimodalClosed---$0.25$1.25$0.03$21.28 est.
Qwen/Qwen3-Coder-Next@novitaNot statedHugging FaceUnknownNot stated---$0.2$1.5-$20.55 est.
qwen3p5-35b-a3bNot statedParasailtextNot stated---$0.15$1$0.05$20.65 est.
qwen3p6-35b-a3bNot statedParasailtextNot stated---$0.15$1$0.05$20.65 est.
MiniMax M2.7 High SpeedMiniMaxMiniMaxtextOpen228.7B55.4%$0.279$1.2$0.0279$21.08
Qwen 2 VL 72B InstructAlibabaNovitatextOpen72B--$0.45$0.45-$21.37 est.
qwen3-vl-plus-2025-09-23:0-token-32kNot statedAlibabaUnknownNot stated---$0.2$1.6-$21.40 est.
qwen3-vl-plus-2025-12-19:0-token-32kNot statedAlibabaUnknownNot stated---$0.2$1.6-$21.40 est.
qwen3-vl-plus:0-token-32kNot statedAlibabaUnknownNot stated---$0.2$1.6-$21.40 est.
GPT-4o miniOpenAIOpenAImultimodalClosed-5.6%$0.15$0.6$0.075$21.75 est.
openai/gpt-4o-mini-2024-07-18OpenAIFastRoutermultimodalClosed--$0.15$0.6$0.075$21.75 est.
ByteDance: UI-TARS 7BByteDanceOpenRoutermultimodalOpen8.3B--$0.1$0.2$0.1$21.80 est.
MiniMax M2MiniMaxAIMiniMaxtextNot stated---$0.3$1.2$0.03$21.90 est.
MiniMax M2.1 LightningMiniMaxAIMiniMaxtextNot stated---$0.3$1.2$0.03$21.90 est.
MiniMaxAI/MiniMax-M2.1@novitaNot statedHugging FaceUnknownNot stated---$0.3$1.2-$21.90 est.
MiniMaxAI/MiniMax-M2.5@novitaNot statedHugging FaceUnknownNot stated---$0.3$1.2-$21.90 est.
MiniMaxAI/MiniMax-M2.7@fireworks-aiNot statedHugging FaceUnknownNot stated---$0.3$1.2-$21.90 est.
MiniMaxAI/MiniMax-M2.7@novitaNot statedHugging FaceUnknownNot stated---$0.3$1.2-$21.90 est.
MiniMaxAI/MiniMax-M2@novitaNot statedHugging FaceUnknownNot stated---$0.3$1.2-$21.90 est.
MiniMaxAI/MiniMax-M3@fireworks-aiNot statedHugging FaceUnknownNot stated---$0.3$1.2-$21.90 est.
MiniMaxAI/MiniMax-M3@novitaNot statedHugging FaceUnknownNot stated---$0.3$1.2-$21.90 est.
MiniMaxAI/MiniMax-M3@togetherNot statedHugging FaceUnknownNot stated---$0.3$1.2-$21.90 est.
Mancer: Weaver (alpha)Not statedOpenRoutertextClosed--$0.4$0.75-$21.98 est.
Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite)GoogleFastRouterUnknownClosed7B-$0.25$1.5-$22.50 est.
Gemini 3.1 Flash Lite PreviewGoogleGooglemultimodalClosed--$0.25$1.5$0.025$22.50
gemini-api:gemini-3.1-flash-lite-image-nano-banana-2-liteNot statedGoogle Vertex AI / Gemini APIUnknownNot stated---$0.25$1.5-$22.50 est.
qwen3.6-flash-2026-04-16:0-token-256kNot statedAlibabaUnknownNot stated---$0.25$1.5-$22.50 est.
qwen3.6-flash:0-token-256kAlibabaAlibabaUnknownNot stated--$0.25$1.5-$22.50 est.
nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16Not statedPrime IntellecttextNot stated---$0.35$1.05-$22.57 est.
trinity-large-thinkingNot statedParasailtextNot stated---$0.22$0.85$0.06$22.65 est.
microsoft/WizardLM-2-8x22BMicrosoftDeepInfraUnknownClosed176B--$0.48$0.48-$22.80 est.
Muse Glimmer 30BMetaOpenRouterUnknownNot stated---$0.3$1.1$0.04$22.85 est.
zai-org/GLM-4.6VZhipu AIZhipu AImultimodalNot stated--$0.3$0.9$0.05$22.95 est.
DeepSeek V4 Flash Vision Exp (peak)DeepSeekDeepSeekUnknownNot stated--$0.44$1.32$0.014$22.98 est.
deepseek-v4-flash-peakNot statedDeepSeekUnknownNot stated---$0.44$1.32$0.014$22.98 est.
allenai/olmOCR-7B-0725-FP8Allen Institute for AI (AI2)DeepInfraUnknownOpen7B--$0.27$1.5-$23.28 est.
Qwen: Qwen3.5 Plus 2026-02-15AlibabaOpenRoutermultimodalOpen397B--$0.26$1.56-$23.40 est.
google/gemma-4-31B-it@togetherNot statedHugging FaceUnknownNot stated---$0.39$0.97-$23.46 est.
Trinity Large ThinkingArcee AIDigitalOceantextNot stated-20.6%$0.25$0.9$0.06$23.70 est.
meta-llama/Llama-4-Maverick-17B-128E-Instruct-TurboMetaDeepInfraUnknownOpen400B--$0.5$0.5-$23.75 est.
Qwen 3 Next 80BAlibabaParasailtextOpen80B-$0.1$1.1$0.07$24.05 est.
qwen-3-next-80b-instructNot statedParasailtextNot stated---$0.1$1.1$0.07$24.05 est.
Qwen/Qwen3-VL-235B-A22B-Instruct@novitaNot statedHugging FaceUnknownNot stated---$0.3$1.5-$24.45 est.
Qwen3 Coder NextAlibabaAlibabatextOpen79.7B-38.2%$0.3$1.5-$24.45 est.
qwen3-coder-flash-2025-07-28:0-token-32kNot statedAlibabaUnknownNot stated---$0.3$1.5-$24.45 est.
qwen3-coder-flash:0-token-32kAlibabaAlibabaUnknownClosed---$0.3$1.5-$24.45 est.
e2ee-qwen3-6-35b-a3bAlibabaVenice AIUnknownOpen35B--$0.182$1.18$0.06$24.65 est.
Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8AlibabaTensorMeshtextOpen480B--$0.45$1.8$0$24.75 est.
moonshot-v1-8kNot statedMoonshot AIUnknownNot stated---$0.2$2-$24.80 est.
moonshot-v1-8k-vision-previewNot statedMoonshot AIUnknownNot stated---$0.2$2-$24.80 est.
qwen3-vl-8b-thinkingAlibabaAlibabamultimodalNot stated---$0.18$2.1-$24.87 est.
qwen-plus-2025-01-25Not statedAlibabaUnknownNot stated---$0.4$1.2-$25.80 est.
qwen-plus-2025-04-28Not statedAlibabaUnknownNot stated---$0.4$1.2-$25.80 est.
qwen-plus-2025-07-14Not statedAlibabaUnknownNot stated---$0.4$1.2-$25.80 est.
qwen-plus-2025-12-01-us:0-token-256kNot statedAlibabaUnknownNot stated---$0.4$1.2-$25.80 est.
qwen-plus-us:0-token-256kNot statedAlibabaUnknownNot stated---$0.4$1.2-$25.80 est.
Qwen/Qwen3.6-35B-A3B@scalewayNot statedHugging FaceUnknownNot stated---$0.29$1.71-$25.85 est.
meta-models/Muse-Glimmer-30B@togetherNot statedHugging FaceUnknownNot stated---$0.35$1.5-$26.40 est.
deepseek-ai/DeepSeek-R1-Distill-Llama-70BdeepseekNovita AItextOpen70.6B--$0.4$1.3-$26.65 est.
deepseek-ai/DeepSeek-V3@novitaNot statedHugging FaceUnknownNot stated---$0.4$1.3-$26.65 est.
GPT 5.1 Codex MiniOpenAIOpenAIUnknownClosed5B--$0.25$2$0.025$26.75
ByteDance Seed: Seed-2.0-LiteByteDanceOpenRoutermultimodalClosed--$0.25$2-$26.75 est.
GPT-5 miniOpenAIOpenAIUnknownClosed-3.7%$0.25$2$0.025$26.75 est.
Qwen/Qwen3.5-35B-A3B@novitaNot statedHugging FaceUnknownNot stated---$0.25$2-$26.75 est.
Seed 1.6ByteDanceOpenRoutermultimodalNot stated--$0.25$2-$26.75 est.
baidu/ERNIE-4.5-VL-424B-A47B-Base-PT@novitaNot statedHugging FaceUnknownNot stated---$0.42$1.25-$27.01 est.
ERNIE 4.5 VL 424B A47BBaiduNovitamultimodalOpen423.5B-$0.42$1.25-$27.01 est.
Kat Coder ProKuaishouNovitatextClosed--$0.3$1.2$0.06$27.30 est.
Kat Coder Pro V2KuaishouAI RoutertextClosed--70%$0.3$1.2$0.06$27.30 est.
KAT-Coder-Pro V1KuaishouAI RoutertextNot stated--$0.3$1.2$0.06$27.30 est.
KAT-Coder-Pro-V2KwaipilotGMI CloudtextNot stated---$0.3$1.2$0.06$27.30 est.
MiniMax M3MiniMaxMiniMaxmultimodalOpen427B65.2%$0.3$1.2$0.06$27.30 est.
minimax-m3Not statedParasailtextNot stated---$0.3$1.2$0.06$27.30 est.
minimax-m3-previewMiniMaxVenice AImultimodalClosed428B-$0.3$1.2$0.06$27.30 est.
thinkingmachines/Inkling-Small@deepinfraNot statedHugging FaceUnknownNot stated---$0.45$1.2-$27.75 est.
Qwen/Qwen3-Coder-480B-A35B-Instruct@novitaNot statedHugging FaceUnknownNot stated---$0.38$1.55-$28.00 est.
CoBuddyBaiduNovitatextClosed---$0.28$1.13$0.07$28.09 est.
qwen-coder-plusAlibabaAlibabatextNot stated--$0.502$1.004-$28.11 est.
qwen3-30b-a3b-thinking-2507AlibabaAlibabatextNot stated--$0.2$2.4-$28.20 est.
qwen3-vl-30b-a3b-thinkingAlibabaAlibabamultimodalNot stated--$0.2$2.4-$28.20 est.
XiaomiNot statedDigitalOceanUnknownNot stated---$0.4$1.5-$28.35 est.
Phind/Phind-CodeLlama-34B-v2Not statedDeepInfraUnknownOpen34B--$0.6$0.6-$28.50 est.
Qwen/Qwen3-235B-A22B-Thinking-2507@deepinfraNot statedHugging FaceUnknownNot stated---$0.23$2.3-$28.52 est.
qwen3-235b-a22b-thinking-2507AlibabaAlibabatextOpen235B--$0.23$2.3-$28.52 est.
Llama 3.3 70B (FP8)Not statedParasailUnknownNot stated---$0.22$0.5$0.11$28.67 est.
llama-33-70b-fp8Not statedParasailtextNot stated---$0.22$0.5$0.11$28.67 est.
LGAI-EXAONE/K-EXAONE-236B-A23BLG AI ResearchFriendliUnknownOpen236B--$0.2$0.8$0.1$29.00 est.
deepseek-v4-flash-0731-fastNot statedVenice AIUnknownNot stated---$0.35$0.7$0.0875$29.05 est.
Qwen 3.7 PlusAlibabaAlibaba +8 moremultimodalClosed1.4T--$0.4$1.6$0.04$29.20
Qwen 3.7 PlusAlibabaFireworks AImultimodalClosed--$0.4$1.6$0.08$36.40 est.
qwen-3-7-plusAlibabaVenice AImultimodalClosed--$0.5$2$0.05$36.50 est.
Qwen3 VL 235B A22B InstructAlibabaAlibaba +7 moremultimodalNot stated---$0.4$1.6-$29.20 est.
Qwen3 VL 235B A22B InstructAlibabaAI RoutermultimodalNot stated--$0.4$1.6-$29.20 est.
qwen3.7-plus-2026-05-26:0-token-256kNot statedAlibabaUnknownNot stated---$0.4$1.6-$29.20 est.
qwen3.7-plus-us:0-token-256kNot statedAlibabaUnknownNot stated---$0.4$1.6-$29.20 est.
xiaomimimo-mimo-v2.5-proNot statedNovita AIUnknownNot stated---$0.62$0.62-$29.45 est.
thinkingmachines/Inkling-Small@basetenNot statedHugging FaceUnknownNot stated---$0.5$1.2-$29.70 est.
thinkingmachines/Inkling-Small@togetherNot statedHugging FaceUnknownNot stated---$0.5$1.2-$29.70 est.
meta-llama/llama-3.3-70b-versatileMetaFastRoutertextOpen70B-$0.59$0.79-$29.72 est.
zai-org/GLM-4.7@deepinfraNot statedHugging FaceUnknownNot stated---$0.4$1.75-$30.48 est.
Gemini 3.8 FlashGoogleOpenRouterUnknownNot stated---$0.375$1.875$0.0375$30.56 est.
@cf/meta/llama-3.1-70b-instruct-fp8-fastMetaCloudflare Workers AItextOpen70B--$0.293$2.253-$30.58 est.
@cf/meta/llama-3.3-70b-instruct-fp8-fastMetaCloudflare Workers AItextOpen70B-$0.293$2.253-$30.58 est.
e2ee-qwen3-6-35b-a3b-uncensored-pAlibabaVenice AIUnknownOpen35B--$0.38$1.88-$30.80 est.
MetaNot statedDigitalOceanUnknownNot stated---$0.65$0.65-$30.88 est.
mistralai/Mixtral-8x22B-Instruct-v0.1Mistral AIDeepInfratextOpen141B--$0.65$0.65-$30.88 est.
Bytedance Seed 1.8ByteDanceAI RoutermultimodalClosed--$0.25$2$0.05$31.25 est.
qwen-plus-characterAlibabaAlibabatextNot stated---$0.5$1.4-$31.40 est.
qwen-plus-character-jaAlibabaAlibabatextNot stated---$0.5$1.4-$31.40 est.
Qwen/Qwen3.5-122B-A10B@deepinfraNot statedHugging FaceUnknownNot stated---$0.29$2.4-$31.71 est.
Sao10K: Llama 3.3 Euryale 70BSao10KOpenRoutertextOpen70.6B-$0.65$0.75-$31.73 est.
meta-llama/Llama-2-70b-chat-hfMetaDeepInfraUnknownOpen70B--$0.64$0.8-$31.76 est.
mimo-v2-omniXiaomiOpenModel.aimultimodalNot stated--$0.32$1.6$0.064$31.84 est.
Qwen/Qwen3.5-27B@novitaNot statedHugging FaceUnknownNot stated---$0.3$2.4-$32.10 est.
Qwen/Qwen3.5-27B@deepinfraNot statedHugging FaceUnknownNot stated---$0.26$2.6-$32.24 est.
@cf/nvidia/nemotron-3-120b-a12bNVIDIACloudflare Workers AItextOpen120B-$0.5$1.5-$32.25 est.
aya-expanse-32bNot statedCohereUnknownNot stated---$0.5$1.5-$32.25 est.
aya-expanse-8bNot statedCohereUnknownNot stated---$0.5$1.5-$32.25 est.
Cohere Command R (provisioned/per-1,000-query, not per-token)CohereAWS BedrockUnknownNot stated---$0.5$1.5-$32.25 est.
command-r-03-2024Not statedCohereUnknownNot stated---$0.5$1.5-$32.25 est.
GPT-3.5 TurboOpenAIOpenAIUnknownNot stated--$0.5$1.5-$32.25 est.
Magistral Small 1.2Not statedAWS BedrockUnknownNot stated---$0.5$1.5-$32.25 est.
Magistral Small 2509Mistral AIVercel AI GatewayUnknownNot stated--$0.5$1.5-$32.25 est.
Mistral Large 3Mistral AIMistral AI +5 moremultimodalNot stated675B12%$0.5$1.5$0.05$32.25 est.
Mistral Large 3Mistral AIMistral AImultimodalOpen675B-$0.5$1.5-$32.25 est.
Mistral Magistral Small 1.2Mistral AIAWS BedrockmultimodalNot stated-4.5%$0.5$1.5-$32.25 est.
Mistral Mistral Large 3Mistral AIAWS BedrockmultimodalNot stated--$0.5$1.5-$32.25 est.
mistral-large-2512Mistral AIOpenRoutermultimodalOpen41B-$0.5$1.5$0.05$32.25 est.
openai/gpt-3.5-turbo-0125OpenAIOpenAItextClosed--$0.5$1.5-$32.25 est.
Devstral 2Mistral AIAI Router +2 moretextNot stated-30.3%$0.4$2-$32.60 est.
Devstral 2Mistral AIMistral AItextOpen24B-$0.4$2-$32.60 est.
Devstral 2 123BMistral AIAWS BedrockUnknownNot stated--$0.4$2-$32.60 est.
devstral-2512Mistral AIOpenRoutertextOpen24B-$0.4$2$0.04$32.60 est.
Mistral Medium 3.1Mistral AIAI RoutermultimodalNot stated--$0.4$2-$32.60 est.
Mistral: Mistral Medium 3.1Mistral AIOpenRoutermultimodalClosed81B-13.9%$0.4$2$0.04$32.60 est.
XiaomiMiMo/MiMo-V2.5@deepinfraNot statedHugging FaceUnknownNot stated---$0.4$2-$32.60 est.
qwen-omni-turbo-2025-01-19Not statedAlibabaUnknownNot stated---$0.058$3.584-$32.73 est.
Qwen Qwen3 Coder 480B A35BAlibabaAWS BedrocktextNot stated--$0.45$1.8-$32.85 est.
Amazon: Nova 2 LiteAmazonOpenRoutermultimodalClosed47B--$0.3$2.5-$32.95 est.
Gemini 2.5 FlashGoogleGooglemultimodalClosed18B--$0.3$2.5$0.03$32.95
inclusionAI/Ling-2.6-1T@novitaNot statedHugging FaceUnknownNot stated---$0.3$2.5-$32.95 est.
Mixtral 8x7BMistral AIMistral AI +1 moretextOpen46.7B-$0.7$0.7-$33.25 est.
mixtral-8x7bMistral AI-UnknownOpen46.7B-----Not comparable
NousResearch/Hermes-3-Llama-3.1-70BNous ResearchDeepInfratextOpen7B-$0.7$0.7-$33.25 est.
NousResearch/Hermes-3-Llama-3.1-70B@deepinfraNot statedHugging FaceUnknownNot stated---$0.7$0.7-$33.25 est.
qwen3.6-35b-a3b:0-token-256kAlibabaAlibabaUnknownOpen36B41.6%$0.375$2.25-$33.75 est.
Qwen 3.6 27B FP8AlibabaTensorMeshmultimodalOpen27B--$0.32$3.2$0$33.92 est.
Sao10K/L3-70B-Euryale-v2.1Sao10KDeepInfratextOpen70B--$0.7$0.8-$34.10 est.
Llama 3.1 70B InstructMetaAI RoutertextOpen70B-$0.72$0.72-$34.20 est.
Meta Llama 3.1 70BMetaAWS BedrocktextNot stated--$0.72$0.72-$34.20 est.
Meta Llama 3.2 90BMetaAWS BedrockUnknownNot stated---$0.72$0.72-$34.20 est.
Meta Llama 3.3 70BMetaAWS BedrocktextNot stated--$0.72$0.72-$34.20 est.
Qwen2.5 Coder 32B InstructAlibabaOpenRoutertextOpen32.8B-$0.66$1-$34.24 est.
DeepSeek-V4-Pro 0813 Official Release (Vendor Direct, New Pricing)Not statedTencent Cloud TokenHubUnknownNot stated---$0.66$1.98$0.022$34.65 est.
DeepSeek-V4-Pro 0813 Official Release (Vendor Direct, New Pricing)Not statedTencent Cloud TokenHubUnknownNot stated---$1.32$3.96$0.044$69.30 est.
deepseek-v4-pro-off-peakNot statedDeepSeekUnknownNot stated---$0.66$1.98$0.022$34.65 est.
deepinfra/airoboros-70bNot statedDeepInfraUnknownOpen70B--$0.7$0.9-$34.95 est.
deepseek-ai/DeepSeek-Prover-V2-671BdeepseekFastRoutertextOpen671B-$0.2$0.77$0.135$35.05 est.
minicpm-v-4.5OpenBMBNebiustextNot stated--$0.658$1.11-$35.10 est.
meta-llama/Llama-3.3-70B-Instruct@ovhcloudNot statedHugging FaceUnknownNot stated---$0.74$0.74-$35.15 est.
GLM-4-32B-0414Zhipu AINovitatextOpen32B--$0.55$1.66-$35.56 est.
zai-org/GLM-4-32B-0414@novitaNot statedHugging FaceUnknownNot stated---$0.55$1.66-$35.56 est.
GPT 5.6 Luna (Fast)Not statedAI RouterUnknownNot stated---$0.4$2.4$0.04$36.00 est.
DeepSeek: DeepSeek V3.1DeepSeekPrime Intellect +2 moretextOpen684.5B-$0.56$1.68-$36.12 est.
DeepSeek DeepSeek V3.1DeepSeekAWS BedrocktextNot stated--$0.58$1.68-$36.90 est.
GPT-4o mini (Fast)Not statedAI RouterUnknownNot stated---$0.25$1$0.125$36.25 est.
gemini-api:gemini-2.5-flash-native-audio-live-apiNot statedGoogle Vertex AI / Gemini APIUnknownNot stated---$0.5$2-$36.50 est.
moonshotai/Kimi-K2-InstructMoonshot AIDeepInfratextOpen1T-$0.5$2-$36.50 est.
venice-uncensored-role-playNot statedVenice AImultimodalOpen24B-$0.5$2-$36.50 est.
zai-org/GLM-4.6@deepinfraNot statedHugging FaceUnknownNot stated---$0.5$2-$36.50 est.
moonshotai/Kimi-K2.5@deepinfraNot statedHugging FaceUnknownNot stated---$0.45$2.25-$36.68 est.
qwen3-coder-30b-a3b-instruct:0-token-32kAlibabaAlibabaUnknownOpen30B--$0.45$2.25-$36.68 est.
qwen-math-plusAlibabaAlibabatextNot stated--$0.574$1.721-$37.01 est.
qwen-math-plus-2024-08-16Not statedAlibabaUnknownNot stated---$0.574$1.721-$37.01 est.
qwen-math-plus-2024-09-19Not statedAlibabaUnknownNot stated---$0.574$1.721-$37.01 est.
qwen-math-plus-latestNot statedAlibabaUnknownNot stated---$0.574$1.721-$37.01 est.
Qwen/Qwen3-235B-A22B-Thinking-2507@novitaNot statedHugging FaceUnknownNot stated---$0.3$3-$37.20 est.
TheDrummer: Cydonia 24B V4.1TheDrummerOpenRoutertextOpen23.6B-$0.3$0.5$0.15$37.55 est.
Llama 2 Chat (13B)Not statedAWS BedrockUnknownNot stated---$0.75$1-$37.75 est.
Llama 2 Chat 13BMetaAWS BedrockUnknownOpen13B--$0.75$1-$37.75 est.
deepseek-ai/DeepSeek-R1-0528@deepinfraNot statedHugging FaceUnknownNot stated---$0.5$2.15-$37.78 est.
deepseek-ai/DeepSeek-R1-Distill-Llama-70B@novitaNot statedHugging FaceUnknownNot stated---$0.8$0.8-$38.00 est.
deepseek-r1-0528DeepSeekNovita AItextOpen671B--$0.8$0.8-$38.00 est.
llama-3.1-405b-instructMetaDeepInfratextOpen405B-$0.8$0.8-$38.00 est.
DeepSeek-R1deepseekSiliconFlowtextOpen684.5B--$0.5$2.18-$38.03 est.
Nemotron 3 ultraNVIDIANVIDIA NIM +8 moremultimodalOpen550B--$0.5$2.2-$38.20 est.
Nemotron 3 UltraNVIDIANVIDIAtextOpen55B-$0.5$2.5$0.05$40.75
zai-org-glm-4.6Zhipu AIVenice AItextOpen355B-$0.43$1.75$0.08$38.31 est.
qwen3-vl-235b-a22b-instructNot statedParasailtextNot stated---$0.21$1.9$0.1$38.56 est.
llama-3.1-nemotron-ultra-253b-v1NVIDIANebius AI StudiotextOpen253B-$0.6$1.8-$38.70 est.
zai-org/GLM-4.5V@novitaNot statedHugging FaceUnknownNot stated---$0.6$1.8-$38.70 est.
Virtuoso LargeArcee AIOpenRoutertextOpen72B--$0.75$1.2-$39.45 est.
Qwen/Qwen3.6-27B@deepinfraNot statedHugging FaceUnknownNot stated---$0.32$3.2-$39.68 est.
xiaomi-mimo-v2-5XiaomiVenice AImultimodalOpen310B-$0.4$2$0.08$39.80 est.
DeepSeek DeepSeek v3.2DeepSeekAWS BedrocktextNot stated--$0.62$1.85-$39.91 est.
GPT-4.1 miniOpenAIOpenAImultimodalClosed-10.1%$0.4$1.6$0.1$40.00 est.
MiniMax M1MiniMaxNovita +1 moretextOpen456B-$0.55$2.2-$40.15 est.
MiniMax M1MiniMaxNovitatextOpen456B-$0.55$2.2-$40.15 est.
MiniMaxAI/MiniMax-M1-80k@novitaNot statedHugging FaceUnknownNot stated---$0.55$2.2-$40.15 est.
zai-org/GLM-4.6@novitaNot statedHugging FaceUnknownNot stated---$0.55$2.2-$40.15 est.
Sao10K: Llama 3.1 Euryale 70B v2.2Sao10KOpenRoutertextOpen70B-$0.85$0.85-$40.38 est.
Sao10K/L3.1-70B-Euryale-v2.2Sao10KDeepInfratextOpen70B-$0.85$0.85-$40.38 est.
Sao10K/L3.3-70B-Euryale-v2.3Sao10KDeepInfratextOpen70B-$0.85$0.85-$40.38 est.
qwen-omni-turboAlibabaAlibabaotherNot stated--$0.07$4.44-$40.47 est.
qwen-omni-turbo-2025-03-26Not statedAlibabaUnknownNot stated---$0.07$4.44-$40.47 est.
qwen-omni-turbo-latestNot statedAlibabaUnknownNot stated---$0.07$4.44-$40.47 est.
ByteDance Seed: Seed 2.1 TurboByteDanceOpenRoutermultimodalClosed--$0.5$2.5-$40.75 est.
Nova 2 LiteAmazonAI RoutermultimodalClosed-16.1%$0.3$2.5$0.075$41.05 est.
zai-org/GLM-5@deepinfraNot statedHugging FaceUnknownNot stated---$0.6$2.08-$41.08 est.
qwen3.5-omni-flashAlibabaAlibabamultimodalOpen7B-$0.4$3-$41.10 est.
qwen3.5-omni-flash-2026-03-15Not statedAlibabaUnknownNot stated---$0.4$3-$41.10 est.
Nova 2.0 LiteAmazonAWS BedrockmultimodalNot stated--$0.15$2.75$0.0825$41.38 est.
Morph V3 FastNot statedAI RoutertextClosed---$0.8$1.2-$41.40 est.
Kimi K2 InstructMoonshot AIAI RoutertextOpen1T-$0.57$2.3-$41.78 est.
moonshotai-kimi-k2-0905Not statedNovita AIUnknownNot stated---$0.57$2.3-$41.78 est.
moonshotai/Kimi-K2-Instruct@novitaNot statedHugging FaceUnknownNot stated---$0.57$2.3-$41.78 est.
Moonshot-Kimi-K2-InstructNot statedAlibabatextNot stated---$0.574$2.294-$41.89 est.
zai-org/GLM-4.7@basetenNot statedHugging FaceUnknownNot stated---$0.6$2.2-$42.10 est.
zai-org/GLM-4.7@novitaNot statedHugging FaceUnknownNot stated---$0.6$2.2-$42.10 est.
Qwen/Qwen3.5-122B-A10B@novitaNot statedHugging FaceUnknownNot stated---$0.4$3.2-$42.80 est.
Qwen/Qwen3.5-397B-A17B@deepinfraNot statedHugging FaceUnknownNot stated---$0.45$3-$43.05 est.
Qwen/Qwen3.5-397B-A17B-FP8AlibabaTensorMeshtextOpen397B-$0.6$3.6$0$43.20 est.
Qwen/Qwen3-235B-A22B-Thinking-2507-TEEAlibabaChutestextOpen235B--$0.2989$1.1957$0.1495$43.34 est.
Relace: Relace Apply 3Not statedOpenRoutertextClosed--$0.85$1.25-$43.78 est.
NVIDIA Nemotron 3 UltraNVIDIABasetenUnknownOpen550B--$0.6$2.4-$43.80 est.
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4@fireworks-aiNot statedHugging FaceUnknownNot stated---$0.6$2.4-$43.80 est.
OpenAI: GPT Audio MiniOpenAIOpenRouterotherClosed---$0.6$2.4-$43.80 est.
openai/gpt-realtime-miniOpenAIFastRoutermultimodalClosed--$0.6$2.4$0.06$43.80 est.
Kimi K2 0905Moonshot AINovitatextOpen1T--$0.6$2.5-$44.65 est.
moonshotai-kimi-k2-thinkingNot statedNovita AIUnknownNot stated---$0.6$2.5-$44.65 est.
moonshotai/Kimi-K2-Instruct-0905@novitaNot statedHugging FaceUnknownNot stated---$0.6$2.5-$44.65 est.
Qwen3.8 27BAlibabaVenice AItextNot stated---$0.45$3.2-$44.75 est.
AionLabs: Aion-RP 1.0 (8B)Not statedOpenRoutertextClosed8B--$0.8$1.6-$44.80 est.
ByteDance/Seed-2.0-codeByteDanceOpenRouterUnknownClosed---$0.5$3-$45.00 est.
Gemini 3 FlashGoogleAI RoutermultimodalNot stated---$0.5$3$0.05$45.00 est.
Gemini 3 Flash AgentGoogleGoogleUnknownClosed---$0.5$3$0.05$45.00
Gemini 3 Flash HighGoogleGoogleUnknownClosed---$0.5$3$0.05$45.00
Gemini 3 Flash LowGoogleGoogleUnknownClosed---$0.5$3$0.05$45.00
Gemini 3 Flash MediumGoogleGoogleUnknownClosed---$0.5$3$0.05$45.00
Gemini 3.1 Flash Image (Nano Banana 2)GoogleAI Routerimage_generationClosed7B-$0.5$3$0.05$45.00 est.
gemini-api:gemini-3.1-flash-image-nano-banana-2Not statedGoogle Vertex AI / Gemini APIUnknownNot stated---$0.5$3-$45.00 est.
google/gemini-3-flash-previewGoogleGooglemultimodalClosed--$0.5$3$0.05$45.00
Qwen 3.6 PlusAlibabaAlibaba +8 moremultimodalClosed--$0.5$3-$45.00 est.
qwen-3-6-plusAlibabaVenice AImultimodalClosed---$0.625$3.75$0.0625$56.25 est.
Qwen3.6 Plus 2026-04-02AlibabaGMI CloudtextNot stated---$0.5$3-$45.00 est.
qwen3.6-plus-2026-04-02:0-token-256kNot statedAlibabaUnknownNot stated---$0.5$3-$45.00 est.
Qwen/Qwen3.6-27B@ovhcloudNot statedHugging FaceUnknownNot stated---$0.47$3.19-$45.45 est.
Ernie 5.1BaiduBaidutextClosed--$0.59$2.65$0.059$45.54
Z.aiNot statedDigitalOceanUnknownNot stated---$0.7$2.2-$46.00 est.
Tencent Hy4 PreviewNot statedAI RouterUnknownNot stated---$0.834$2.501$0.042$46.33 est.
Llama 4 Maverick (FP8)Not statedParasailUnknownNot stated---$0.35$1$0.17$46.45 est.
llama-4-maverick-instruct-fp8Not statedParasailtextNot stated---$0.35$1$0.17$46.45 est.
Doubao Seed 2.0 CodeByteDanceByteDancemultimodalClosed--$0.47$2.35$0.094$46.77
Doubao Seed 2.0 ProByteDanceByteDancemultimodalClosed--$0.47$2.35$0.094$46.77
NVIDIA-Nemotron-3-Ultra-550B-A55BNVIDIADeepInfratextOpen550B53.9%$0.5$2.2$0.1$47.20 est.
FLUX.2-klein-4BBlack Forest LabsNEAR AI Cloudimage_generationOpen4B-$1$1-$47.50 est.
hermes-4-405bNous ResearchNous ResearchtextOpen405.9B-$1$1$0.1$47.50
hermes-4-70bNous ResearchNous ResearchtextOpen70.6B-$1$1$0.1$47.50
NousResearch/Hermes-3-Llama-3.1-405BNous ResearchNous ResearchtextOpen405.9B-$1$1$0.1$47.50
perplexity/sonarPerplexityFastRoutermultimodalClosed---$1$1-$47.50 est.
GLM 4.5VZhipu AIZhipu AImultimodalNot stated---$0.6$1.8$0.11$47.70 est.
Qwen/Qwen2.5-VL-72B-Instruct@ovhcloudNot statedHugging FaceUnknownNot stated---$1.01$1.01-$47.98 est.
GPT-5 mini (Fast)Not statedAI RouterUnknownNot stated---$0.45$3.6$0.045$48.15 est.
qwen-omni-turbo-realtimeAlibabaAlibabaotherNot stated--$0.27$4.44-$48.27 est.
qwen-omni-turbo-realtime-2025-05-08Not statedAlibabaUnknownNot stated---$0.27$4.44-$48.27 est.
qwen-omni-turbo-realtime-latestNot statedAlibabaUnknownNot stated---$0.27$4.44-$48.27 est.
e2ee-qwen3-8-27bNot statedVenice AIUnknownNot stated---$0.47$3.53$0.047$48.34 est.
deepseek-ai/DeepSeek-R1-0528@novitaNot statedHugging FaceUnknownNot stated---$0.7$2.5-$48.55 est.
deepseek-ai/DeepSeek-R1@novitaNot statedHugging FaceUnknownNot stated---$0.7$2.5-$48.55 est.
moonshotai/Kimi-K2.5@novitaNot statedHugging FaceUnknownNot stated---$0.6$3-$48.90 est.
meta-llama/Llama-3.3-70B-Instruct@scalewayNot statedHugging FaceUnknownNot stated---$1.03$1.03-$48.93 est.
qwen3-omni-flashAlibabaAlibabaotherNot stated--$0.43$3.81-$49.16 est.
qwen3-omni-flash-2025-09-15Not statedAlibabaUnknownNot stated---$0.43$3.81-$49.16 est.
qwen3-omni-flash-2025-12-01Not statedAlibabaUnknownNot stated---$0.43$3.81-$49.16 est.
Qwen/Qwen3-235B-A22B-Thinking-2507-FP8AlibabaGMI CloudtextNot stated---$0.35$4.2-$49.35 est.
meta-llama/Llama-3.3-70B-Instruct@togetherNot statedHugging FaceUnknownNot stated---$1.04$1.04-$49.40 est.
NVIDIANot statedDigitalOceanUnknownNot stated---$0.9$1.7-$49.55 est.
Qwen3 VL 235B A22B ThinkingAlibabaAI Router +13 moremultimodalNot stated--$0.4$4-$49.60 est.
qwen3-vl-235b-a22b-thinkingAlibabaAlibabamultimodalOpen235B-$0.4$4-$49.60 est.
Qwen3 VL 235B A22B ThinkingAlibabaAlibabamultimodalOpen235B--$0.7$2.8-$51.10 est.
zai-org/GLM-5.2@deepinfraNot statedHugging FaceUnknownNot stated---$0.75$2.4-$49.65 est.
Nemotron 3 Ultra 550B (NVFP4)Not statedParasailUnknownNot stated---$0.5$2.5$0.1$49.75 est.
Qwen/Qwen3.6-27B-TEEAlibabaChutesmultimodalOpen27B-$0.3$2$0.15$50.30 est.
GLM 4.5Zhipu AIZhipu AItextNot stated---$0.6$2.2$0.11$51.10 est.
GLM 4.6ZAIZhipu AItextNot stated355B49.4%$0.6$2.2$0.11$51.10 est.
GLM 4.7Zhipu AIZhipu AI +14 moretextOpen355B45.3%$0.6$2.2$0.11$51.10 est.
GLM-4.7Zhipu AINovitatextOpen355B--$0.6$2.2$0.11$51.10 est.
qwen-audio-3.0-realtime-flashNot statedAlibabaUnknownNot stated---$0.413$4.126-$51.18 est.
Morph V3 LargeNot statedAI RoutertextClosed8B--$0.9$1.9-$51.25 est.
google/gemma-4-31B-it@cerebrasNot statedHugging FaceUnknownNot stated---$0.99$1.49-$51.28 est.
MiMo V2.5 Pro UltraSpeedNot statedAI RoutertextNot stated---$1.305$2.61$0.0108$51.53 est.
qwq-plusNot statedAlibabatextNot stated--$0.8$2.4-$51.60 est.
moonshotai/Kimi-K2-Instruct-0905Moonshot AIDeepInfratextOpen1T--$0.4$2$0.15$52.40 est.
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4@togetherNot statedHugging FaceUnknownNot stated---$0.6$3.6-$54.00 est.
Qwen 3.6 27BAlibabaAlibabamultimodalOpen27.8B-51.3%$0.6$3.6-$54.00 est.
Qwen/Qwen3.5-397B-A17B@novitaNot statedHugging FaceUnknownNot stated---$0.6$3.6-$54.00 est.
ByteDance/Seed-2.0-proByteDanceDeepInfraUnknownClosed---$0.5$3$0.1$54.00 est.
Qwen3.8 27BNot statedAI RoutertextNot stated---$0.5$3$0.1$54.00 est.
NVIDIA Nemotron 3 Ultra (Preview)NVIDIAFireworks AIUnknownOpen550B--$0.6$2.4$0.12$54.60 est.
Qwen/Qwen3-235B-A22B-Instruct-2507@scalewayNot statedHugging FaceUnknownNot stated---$0.86$2.57-$55.39 est.
moonshotai/Kimi-K2.7-Code@deepinfraNot statedHugging FaceUnknownNot stated---$0.68$3.4-$55.42 est.
commandNot statedCohereUnknownNot stated---$1$2-$56.00 est.
openai/gpt-3.5-turbo-1106OpenAIOpenAItextClosed--$1$2-$56.00 est.
x-ai/grok-build-0.1xAIxAImultimodalClosed6B--$1$2$0.1$56.00
Kimi K2.5Moonshot AIMoonshot AIUnknownOpen1.1T45.7%$0.6$3$0.1$56.10 est.
GLM 5.3Not statedAI RouterUnknownNot stated---$0.7$2.2$0.13$56.80 est.
GLM 5.3 (50% off)Not statedAI RouterUnknownNot stated---$0.7$2.2$0.13$56.80 est.
swiss-ai/Apertus-70B-Instruct-2509@publicaiNot statedHugging FaceUnknownNot stated---$0.82$2.92-$56.80 est.
swiss-ai/Apertus-v1.5-70B@publicaiNot statedHugging FaceUnknownNot stated---$0.82$2.92-$56.80 est.
GLM-5.2-NVFP4zai-orgMakoraUnknownNot stated---$0.72$2.38$0.12$56.95 est.
mistralai/Mixtral-8x22B-Instruct-v0.1@nscaleNot statedHugging FaceUnknownNot stated---$1.2$1.2-$57.00 est.
Nemotron 70B InstructNVIDIANVIDIA NIMUnknownOpen70B--$1.2$1.2-$57.00 est.
nvidia/Llama-3.1-Nemotron-70B-InstructNVIDIADeepInfratextOpen70B--$1.2$1.2-$57.00 est.
Nova ProAmazonAI RoutermultimodalNot stated--$0.8$3.2-$58.40 est.
nova-pro-v1AmazonOpenRoutermultimodalClosed--$0.8$3.2-$58.40 est.
qwen-vl-maxAlibabaAlibabamultimodalNot stated--$0.8$3.2-$58.40 est.
AionLabs: Aion-3.0-MiniNot statedOpenRouter +1 moretextClosed--$0.7$1.4$0.18$59.00 est.
aion-labs-aion-3-0-miniNot statedVenice AItextClosed--$0.875$1.75$0.225$73.75 est.
moonshotai/Kimi-K2.6@deepinfraNot statedHugging FaceUnknownNot stated---$0.75$3.5-$59.00 est.
qwen3-omni-flash-realtimeAlibabaAlibabaotherNot stated--$0.52$4.57-$59.13 est.
qwen3-omni-flash-realtime-2025-09-15Not statedAlibabaUnknownNot stated---$0.52$4.57-$59.13 est.
qwen3-omni-flash-realtime-2025-12-01Not statedAlibabaUnknownNot stated---$0.52$4.57-$59.13 est.
Cogito v2.1 671BDeep CogitoOpenRoutertextOpen671B--$1.25$1.25-$59.38 est.
deepcogito/cogito-671b-v2.1-FP8@togetherNot statedHugging FaceUnknownNot stated---$1.25$1.25-$59.38 est.
deepcogito/cogito-671b-v2.1@togetherNot statedHugging FaceUnknownNot stated---$1.25$1.25-$59.38 est.
qwen3.5-omni-flash-realtimeNot statedAlibabaUnknownNot stated---$0.55$4.5-$59.70 est.
qwen3.5-omni-flash-realtime-2026-03-15Not statedAlibabaUnknownNot stated---$0.55$4.5-$59.70 est.
moonshotai/Kimi-K2.6@novitaNot statedHugging FaceUnknownNot stated---$0.8$3.4-$60.10 est.
Gemini 3.6 FlashGoogleGooglemultimodalClosed7B77.5%$0.75$3.75$0.075$61.13
Gemini 3.7 FlashGoogleGoogleUnknownNot stated--78.3%$0.75$3.75$0.075$61.13
gemini-3.6-flash (intro through 2026-12-31)Not statedGoogle Vertex AI / Gemini APIUnknownNot stated---$0.75$3.75$0.075$61.13 est.
gemini-3.7-flash (intro through 2026-12-31)Not statedGoogle Vertex AI / Gemini APIUnknownNot stated---$0.75$3.75$0.075$61.13 est.
Google Gemini Flash LatestGoogleOpenRoutermultimodalClosed---$0.75$3.75$0.075$61.13 est.
qwen2.5-omni-7bNot statedAlibabaotherNot stated---$0.1$6.76-$61.36 est.
Qwen/Qwen3.5-397B-A17B@scalewayNot statedHugging FaceUnknownNot stated---$0.68$4.1-$61.37 est.
Skyfall 31B v4.2Not statedParasailmultimodalNot stated---$0.55$0.8$0.25$63.35 est.
Skyfall 36B v2 (FP8)Not statedParasailUnknownNot stated---$0.55$0.8$0.25$63.35 est.
skyfall-36b-v2-fp8Not statedParasailtextNot stated---$0.55$0.8$0.25$63.35 est.
TheDrummer: Skyfall 36B V2TheDrummerOpenRoutertextOpen36.9B--$0.55$0.8$0.25$63.35 est.
Qwen/Qwen3.5-397B-A17B@ovhcloudNot statedHugging FaceUnknownNot stated---$0.71$4.25-$63.82 est.
Mistral Medium 3Mistral AIMistral AImultimodalClosed--$1$3$0.1$64.50
Mistral Mistral SmallMistral AIAWS BedrockUnknownNot stated---$1$3-$64.50 est.
moonshot-v1-32kNot statedMoonshot AIUnknownNot stated---$1$3-$64.50 est.
moonshot-v1-32k-vision-previewNot statedMoonshot AIUnknownNot stated---$1$3-$64.50 est.
Relace: Relace SearchNot statedOpenRoutertextClosed---$1$3-$64.50 est.
XiaomiMiMo/MiMo-V2.5-Pro@deepinfraNot statedHugging FaceUnknownNot stated---$1$3-$64.50 est.
claude-haiku-3.5Not statedAnthropicmultimodalNot stated---$0.8$4$0.08$65.20 est.
XiaomiMiMo/MiMo-V2-ProXiaomiOpenModel.aitextNot stated--$0.8$2.4$0.16$66.00 est.
zai-org/GLM-5@novitaNot statedHugging FaceUnknownNot stated---$1$3.2-$66.20 est.
AionLabs: Aion-2.0Not statedOpenRoutertextClosed---$0.8$1.6$0.2$66.40 est.
lukealonso/GLM-5.1-NVFP4-MTPZhipu AITensorMeshtextOpen754B--$1.4$4.4$0$66.80 est.
qwen3-livetranslate-flashNot statedAlibabaUnknownNot stated---$1.577$0.631-$66.87 est.
qwen3-livetranslate-flash-2025-12-01Not statedAlibabaUnknownNot stated---$1.577$0.631-$66.87 est.
Claude 3 5 HaikuAnthropicAnthropic +1 moremultimodalClosed-10.1%$0.8$4$0.08$67.00
Claude 3.5 HaikuAnthropicAWS BedrockUnknownNot stated---$0.8$4$0.1$68.80 est.
e2ee-qwen3-6-27bAlibabaVenice AIUnknownOpen27B--$0.346$3.46$0.171$67.46 est.
gemini-api:gemini-3.1-flash-live-previewNot statedGoogle Vertex AI / Gemini APIUnknownNot stated---$0.75$4.5-$67.50 est.
GPT 5.4 MiniOpenAIOpenAIUnknownClosed16B-$0.75$4.5$0.075$67.50 est.
OpenAI GPT Mini LatestOpenAIOpenRoutermultimodalClosed9B--$0.75$4.5$0.075$67.50 est.
Kat Coder Pro V2.5KuaishouAI RouterUnknownClosed119B-$0.74$2.96$0.15$67.70 est.
Composer 2.5 FastCursorCursortextClosed--$0.5$2.5$0.2$67.75
deepseek-v4-pro-peakNot statedDeepSeekUnknownNot stated---$1.32$3.96$0.044$69.30 est.
Kimi K2.6Moonshot AIMoonshot AI +24 moremultimodalOpen1.1T65.9%$0.684$3.42$0.144$69.35
Kimi K2.6Moonshot AIFireworks AImultimodalOpen1T-$0.95$4$0.16$82.75 est.
GPT-4.1 mini (Fast)Not statedAI RouterUnknownNot stated---$0.7$2.8$0.175$70.00 est.
Grok 4.3xAIxAImultimodalClosed--34.1%$1.25$2.5$0.125$70.00
SpaceXAI: Grok 4.20xAIxAImultimodalClosed--$1.25$2.5$0.125$70.00
x-ai/grok-code-fast-1xAIxAItextClosed--$1.25$2.5$0.125$70.00
L3 70B Euryale V2.1Sao10KNovitatextOpen70B--$1.48$1.48-$70.30 est.
Sao10K-L3-8B-Stheno-v3.2Not statedNovita AIUnknownNot stated---$1.48$1.48-$70.30 est.
moonshotai/Kimi-K2.6@basetenNot statedHugging FaceUnknownNot stated---$0.95$4-$71.05 est.
moonshotai/Kimi-K2.6@fireworks-aiNot statedHugging FaceUnknownNot stated---$0.95$4-$71.05 est.
moonshotai/Kimi-K2.7-Code@basetenNot statedHugging FaceUnknownNot stated---$0.95$4-$71.05 est.
moonshotai/Kimi-K2.7-Code@fireworks-aiNot statedHugging FaceUnknownNot stated---$0.95$4-$71.05 est.
moonshotai/Kimi-K2.7-Code@novitaNot statedHugging FaceUnknownNot stated---$0.95$4-$71.05 est.
moonshotai/Kimi-K2.7-Code@togetherNot statedHugging FaceUnknownNot stated---$0.95$4-$71.05 est.
thinkingmachines/Inkling@deepinfraNot statedHugging FaceUnknownNot stated---$0.95$4.05-$71.48 est.
Qwen/Qwen3-VL-235B-A22B-Thinking@novitaNot statedHugging FaceUnknownNot stated---$0.98$3.95-$71.80 est.
deepseek-ai/DeepSeek-V4-Pro@deepinfraNot statedHugging FaceUnknownNot stated---$1.3$2.6-$72.80 est.
InklingThinking Machines LabThinking Machines LabUnknownClosed41B55.1%$1$4.05$0.1$73.43
thinkingmachines/Inkling@basetenNot statedHugging FaceUnknownNot stated---$1$4.05-$73.43 est.
thinkingmachines/Inkling@togetherNot statedHugging FaceUnknownNot stated---$1$4.05-$73.43 est.
qwen-audio-3.0-realtime-plusNot statedAlibabaUnknownNot stated---$0.688$5.501-$73.59 est.
x-ai/grok-3-mini-betaxAIFastRoutertextClosed183B--$0.6$4$0.15$73.60 est.
Grok Build 0.1Not statedAI RoutermultimodalNot stated---$1$2$0.2$74.00 est.
Palmyra X5WriterAWS Bedrock +1 moretextNot stated---$0.6$6-$74.40 est.
Palmyra X5WriterAWS BedrocktextNot stated--$0.6$6-$74.40 est.
Qwen/Qwen3.5-397B-A17B-TEEAlibabaChutesmultimodalOpen397B-$0.45$3$0.225$75.45 est.
gpt-3.5-turbo-instructOpenAIOpenAItextClosed--$1.5$2-$75.50 est.
Gpt 3.5 0301OpenAIOpenAItextClosed--$1.5$2$0.15$75.50
Gpt 3.5 Turbo 0613OpenAIOpenAItextClosed--$1.5$2$0.15$75.50
zai-org/GLM-5.2-FP8zai-orgMakoratextNot stated--$0.94$2.8$0.18$75.94 est.
gemini-3-7-flashNot statedVenice AIUnknownNot stated---$0.9375$4.6875$0.0938$76.41 est.
claude-haiku-4-5-20251001AnthropicOpenModel.aimultimodalNot stated--$0.95$4.75$0.095$77.43 est.
Qwen3 MaxAlibabaAlibabatextClosed--$0.78$3.9$0.156$77.61
e2ee-glm-4-7-pZhipu AIVenice AIUnknownOpen355B--$1.1$4.15-$78.18 est.
e2ee-glm-5-1Zhipu AIVenice AIUnknownOpen744B--$1.1$4.15-$78.18 est.
@cf/meta/llama-2-7b-chat-fp16MetaCloudflare Workers AItextOpen7B--$0.556$6.667-$78.35 est.
Amazon Nova ProAmazonAWS BedrockmultimodalClosed--$0.8$3.2$0.2$80.00 est.
Sakana NamazuNot statedAI RouterUnknownNot stated---$0.95$4$0.15$80.95 est.
Sakana: Sakana NamazuSakana AIOpenRouterUnknownNot stated---$0.95$4$0.15$80.95 est.
Anthropic Claude Haiku LatestAnthropicOpenRoutermultimodalClosed---$1$5$0.1$81.50 est.
Claude Haiku 4.5AnthropicAnthropic +12 moremultimodalClosed-44.2%$1$5$0.1$81.50 est.
Claude Haiku 4.5AnthropicAWS BedrockmultimodalNot stated--$1$5$0.1$81.50 est.
gemini-api:gemini-robotics-er-1.6-previewNot statedGoogle Vertex AI / Gemini APIUnknownNot stated---$1$5-$81.50 est.
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16@deepinfraNot statedHugging FaceUnknownNot stated---$1$5-$81.50 est.
OpenAI: GPT-5.6 Sol Pro (batch)OpenAIOpenRouterUnknownClosed--$1$5$0.1$81.50 est.
Qwen3 Coder PlusAlibabaAlibabatextOpen480B--$1$5-$81.50 est.
qwen3-coder-plus-2025-07-22:0-token-32kNot statedAlibabaUnknownNot stated---$1$5-$81.50 est.
qwen3-coder-plus-2025-09-23:0-token-32kNot statedAlibabaUnknownNot stated---$1$5-$81.50 est.
Grok 4.20 Beta Non-ReasoningNot statedAI RoutermultimodalNot stated---$1.25$2.5$0.2$83.50 est.
Grok 4.20 Beta Non-ReasoningxAIVercel AI GatewaymultimodalNot stated--$1.25$2.5$0.2$83.50 est.
Grok 4.20 Beta ReasoningNot statedAI RoutermultimodalNot stated---$1.25$2.5$0.2$83.50 est.
Grok 4.20 Beta ReasoningxAIVercel AI GatewaymultimodalNot stated--$1.25$2.5$0.2$83.50 est.
Grok 4.20 Multi Agent BetaNot statedAI RoutermultimodalNot stated---$1.25$2.5$0.2$83.50 est.
Grok 4.20 Multi Agent BetaxAIVercel AI GatewaymultimodalNot stated--$1.25$2.5$0.2$83.50 est.
Grok 4.20 Multi-AgentNot statedAI RoutermultimodalNot stated---$1.25$2.5$0.2$83.50 est.
Grok 4.20 Non-ReasoningNot statedAI RouterUnknownNot stated---$1.25$2.5$0.2$83.50 est.
Grok 4.20 ReasoningNot statedAI RouterUnknownNot stated---$1.25$2.5$0.2$83.50 est.
Grok 4.3Not statedAI RoutermultimodalNot stated---$1.25$2.5$0.2$83.50 est.
grok-4.20-0309-non-reasoning (<200k prompt tokens)Not statedxAIUnknownNot stated---$1.25$2.5$0.2$83.50 est.
grok-4.20-multi-agent-0309 (≥200k prompt tokens)Not statedxAIUnknownNot stated---$1.25$2.5$0.2$83.50 est.
SpaceXAI: Grok 4.20 Multi-AgentxAIOpenRoutermultimodalClosed---$1.25$2.5$0.2$83.50 est.
x-ai/grok-4.20-betaxAIFastRoutermultimodalClosed---$1.25$2.5$0.2$83.50 est.
GLM 5Zhipu AIZhipu AItextOpen753.9B--$1$3.2$0.2$84.20 est.
zai-org-glm-5Zhipu AIVenice AItextOpen744B-$1$3.2$0.2$84.20 est.
moonshotai/Kimi-K2.6@togetherNot statedHugging FaceUnknownNot stated---$1.2$4.5-$85.05 est.
deepseek-ai/DeepSeek-V4-Pro-0813@basetenNot statedHugging FaceUnknownNot stated---$1.32$3.96-$85.14 est.
deepseek-ai/DeepSeek-V4-Pro-0813@novitaNot statedHugging FaceUnknownNot stated---$1.32$3.96-$85.14 est.
deepseek-ai/DeepSeek-V4-Pro-0813@togetherNot statedHugging FaceUnknownNot stated---$1.32$3.96-$85.14 est.
qvq-maxNot statedAlibabamultimodalNot stated---$1.2$4.8-$87.60 est.
Kimi K2.7 CodeMoonshot AIFireworks AImultimodalOpen1T-$0.95$4$0.19$88.15 est.
Kimi K2.7 Code High SpeedMoonshot AIMoonshot AIUnknownOpen1T67.4%$0.95$4$0.19$88.15 est.
Interfaze BetaNot statedAI RoutermultimodalNot stated--$1.5$3.5-$88.25 est.
Muse Spark 1.1MetaMetamultimodalClosed---$1.25$4.25$0.15$89.38
Muse Spark 1.2Not statedAI RoutermultimodalNot stated--80.1%$1.25$4.25$0.15$89.38 est.
deepseek-ai/DeepSeek-V4-Pro@novitaNot statedHugging FaceUnknownNot stated---$1.6$3.2-$89.60 est.
OpenAI: GPT-5.6 Terra Pro (batch)OpenAIOpenRouterUnknownClosed--$1$6$0.1$90.00 est.
Z.ai: GLM LatestNot statedOpenRoutertextNot stated---$1.12$3.52$0.208$90.88 est.
GLM 5.1Zhipu AINEAR AI Cloud +21 moretextOpen754B--$1.4$4.4-$92.00 est.
GLM 5.1Zhipu AIZhipu AItextOpen753.9B-61.8%$1.4$4.4$0.26$113.60 est.
GLM 5.1Zhipu AIFireworks AIUnknownOpen69B--$1.4$4.4$0.26$113.60 est.
GLM 5.2Zhipu AIFireworks AItextOpen744B-$1.4$4.4$0.14$92.00 est.
glm-5.2-usNot statedAlibabaUnknownNot stated---$1.4$4.4-$92.00 est.
zai-org/GLM-5.2@basetenNot statedHugging FaceUnknownNot stated---$1.4$4.4-$92.00 est.
zai-org/GLM-5.2@fireworks-aiNot statedHugging FaceUnknownNot stated---$1.4$4.4-$92.00 est.
zai-org/GLM-5.2@novitaNot statedHugging FaceUnknownNot stated---$1.4$4.4-$92.00 est.
zai-org/GLM-5.2@togetherNot statedHugging FaceUnknownNot stated---$1.4$4.4-$92.00 est.
davinci-002OpenAIOpenAItextClosed--$2$2-$95.00 est.
qwen35-397b-a17bNot statedParasailtextNot stated---$0.5$3.6$0.3$95.10 est.
Qwen2.5-VL 72BNot statedParasailUnknownNot stated---$0.8$1$0.4$97.30 est.
qwen25-vl-72b-instructNot statedParasailtextNot stated---$0.8$1$0.4$97.30 est.
deepseek-ai/DeepSeek-V4-Pro@basetenNot statedHugging FaceUnknownNot stated---$1.74$3.48-$97.44 est.
deepseek-ai/DeepSeek-V4-Pro@fireworks-aiNot statedHugging FaceUnknownNot stated---$1.74$3.48-$97.44 est.
deepseek-ai/DeepSeek-V4-Pro@togetherNot statedHugging FaceUnknownNot stated---$1.74$3.48-$97.44 est.
Qwen3 Max PreviewAlibabaAlibabatextNot stated--$1.2$6-$97.80 est.
qwen3-max-2025-09-23:0-token-32kNot statedAlibabaUnknownNot stated---$1.2$6-$97.80 est.
qwen3-max-2026-01-23:0-token-32kNot statedAlibabaUnknownNot stated---$1.2$6-$97.80 est.
Llama 2 Chat (70B)Not statedAWS BedrockUnknownNot stated---$1.95$2.56-$97.81 est.
Llama 2 Chat 70BMetaAWS BedrockUnknownOpen70B--$1.95$2.56-$97.81 est.
DeepSeek R1DeepSeekAWS BedrocktextNot stated--$1.35$5.4-$98.55 est.
glm-4.5-airxZhipu AIZhipu AItextNot stated---$1.1$4.5$0.22$100.95 est.
GLM 5V TurboZhipu AIZhipu AImultimodalOpen744B-$1.2$4$0.24$102.40 est.
z-ai-glm-5-turboZhipu AIVenice AItextOpen744B-$1.2$4$0.24$102.40 est.
moonshotai/Kimi-K2.6-TEEMoonshot AIChutesmultimodalOpen1T-$0.66$3.5$0.33$103.01 est.
Qwen3.8 Max PreviewAlibabaAlibabamultimodalOpen2.4T-$1.25$3.75$0.25$103.13
gemini-api:gemini-2.5-flash-preview-ttsNot statedGoogle Vertex AI / Gemini APIUnknownNot stated---$0.5$10-$104.50 est.
deepseek-v4-pro-0813Not statedVenice AItextNot stated---$1.65$4.95$0.165$106.43 est.
Z.ai: GLM 5.3Zhipu AIWaferUnknownNot stated---$1.19$4.4$0.26$109.19 est.
LGAI-EXAONE/K-EXAONE-2.0-750B-A37BNot statedFriendliUnknownNot stated---$1.2$4.8$0.24$109.20 est.
o4-miniOpenAIOpenAIUnknownClosed--$1.1$4.4$0.275$110.00 est.
openai/o4-mini-highOpenAIFastRoutermultimodalClosed---$1.1$4.4$0.275$110.00 est.
Z.ai GLM 4.7Zhipu AICerebrastextOpen355B-$2.25$2.75-$111.13 est.
GLM 5.2 FastZhipu AIZhipu AItextOpen753.3B-51.7%$1.4$4.4$0.26$113.60 est.
GLM-5.3Zhipu AITencent Cloud TokenHubUnknownNot stated--83.9%$1.4$4.4$0.26$113.60 est.
glm-51Not statedParasailtextNot stated---$1.4$4.4$0.26$113.60 est.
glm-52Not statedParasailtextNot stated---$1.4$4.4$0.26$113.60 est.
zai-org-glm-5.2Zhipu AIVenice AItextOpen744B-$1.4$4.4$0.26$113.60 est.
GPT-5-CodexOpenAIOpenAIUnknownClosed---$1.07$8.5$0.107$113.98
GPT-5.1-CodexOpenAIOpenAImultimodalClosed---$1.07$8.5$0.107$113.98
Meta Llama 3.1 405BMetaAWS BedrockUnknownNot stated---$2.4$2.4-$114.00 est.
OpenAI: GPT-5 Image MiniOpenAIOpenRouterimage_generationClosed--$2.5$2$0.25$114.50 est.
qwen-maxAlibabaAlibabatextNot stated--$1.6$6.4-$116.80 est.
qwen3.6-max-preview:0-token-128kAlibabaAlibabaUnknownNot stated--$1.3$7.8-$117.00 est.
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16NVIDIADeepInfratextOpen550B-$1$5$0.3$117.50 est.
deepseek-ai/DeepSeek-V3.2-TEEDeepSeekChutestextOpen671B--$1$1$0.5$119.50 est.
Magistral Medium 2509Mistral AIVercel AI GatewayUnknownNot stated--$2$5-$120.50 est.
moonshot-v1-128kNot statedMoonshot AIUnknownNot stated---$2$5-$120.50 est.
moonshot-v1-128k-vision-previewNot statedMoonshot AIUnknownNot stated---$2$5-$120.50 est.
gemini-3.6-flash (standard from 2027-01-01)Not statedGoogle Vertex AI / Gemini APIUnknownNot stated---$1.5$7.5$0.15$122.25 est.
gemini-3.7-flash (standard from 2027-01-01)Not statedGoogle Vertex AI / Gemini APIUnknownNot stated---$1.5$7.5$0.15$122.25 est.
Mistral Medium 3.5Mistral AIMistral AImultimodalOpen128B-$1.5$7.5-$122.25 est.
Mistral Medium LatestMistral AIMistral AImultimodalClosed128B50.6%$1.5$7.5$0.15$122.25 est.
qwen3-coder-480b-a35b-instruct:0-token-32kAlibabaAlibabaUnknownNot stated---$1.5$7.5-$122.25 est.
Claude InstantAnthropicAWS BedrockUnknownNot stated---$0.8$11.02-$124.87 est.
zai-org-glm-5.1Zhipu AIVenice AItextOpen744B-$1.54$4.84$0.286$124.96 est.
z-ai-glm-5v-turboZhipu AIVenice AImultimodalOpen744B-$1.5$5$0.3$128.00 est.
AlibabaNot statedDigitalOceanUnknownNot stated---$2$6-$129.00 est.
Mistral LargeMistral AIMistral AImultimodalOpen123B-$2$6$0.2$129.00
Mistral Large 2407Mistral AIOpenRoutermultimodalOpen123B-$2$6$0.2$129.00 est.
Mistral Mistral Large 2407Mistral AIAWS BedrockUnknownNot stated---$2$6-$129.00 est.
Mistral Pixtral Large 25.02Mistral AIAWS BedrockmultimodalNot stated--$2$6-$129.00 est.
Mistral: Mixtral 8x22B InstructMistral AIOpenRoutermultimodalOpen140.6B-$2$6$0.2$129.00 est.
Mixtral 8x22BMistral AIMistral AItextOpen141B-$2$6-$129.00 est.
x-ai/grok-4.5xAIxAImultimodalClosed--81.6%$2$6$0.2$129.00
e2ee-kimi-k2-6Not statedVenice AIUnknownNot stated---$0.87$4.12$0.44$132.49 est.
Meta Llama 3 70BMetaAWS BedrockUnknownNot stated---$2.65$3.5-$133.10 est.
zai-org/GLM-5.2@scalewayNot statedHugging FaceUnknownNot stated---$2.05$6.27-$133.24 est.
Composer 1CursorCursortextClosed---$1.25$10$0.125$133.75
Gemini 2.5 ProGoogleGooglemultimodalClosed---$1.25$10$0.125$133.75
gemini-api:gemini-2.5-computer-use-previewNot statedGoogle Vertex AI / Gemini APIUnknownNot stated---$1.25$10-$133.75 est.
Google: Gemini 2.5 Pro Preview 05-06GoogleOpenRoutermultimodalClosed---$1.25$10$0.125$133.75 est.
Google: Gemini 2.5 Pro Preview 06-05GoogleOpenRoutermultimodalClosed--$1.25$10$0.125$133.75 est.
GPT 5.1 Codex MaxOpenAIOpenAImultimodalClosed--$1.25$10$0.125$133.75
GPT 5.1 ThinkingOpenAIOpenAIUnknownClosed15B--$1.25$10$0.125$133.75 est.
GPT-5OpenAIOpenAIUnknownClosed--35.2%$1.25$10$0.125$133.75 est.
gpt-5-search-apiOpenAIOpenAIUnknownNot stated---$1.25$10$0.125$133.75 est.
GPT-5.1 InstantOpenAIVercel AI GatewaymultimodalNot stated--$1.25$10$0.13$134.65 est.
zai-org/GLM-5.1-TEEZhipu AIChutestextOpen754B-$0.98$3.08$0.49$134.96 est.
Gemini 3.5 FlashGoogleGooglemultimodalClosed-78.7%$1.5$9$0.15$135.00
Gemini Omni FlashGoogleGoogle Vertex AIUnknownClosed---$1.5$9-$135.00 est.
Gemini Omni Flash PreviewGoogleGoogleUnknownClosed--$1.5$9$0.15$135.00
GPT 5.4 Mini (Fast)Not statedAI RouterUnknownNot stated---$1.5$9$0.15$135.00 est.
Qwen 3.8 MaxAlibabaAlibabamultimodalNot stated--81.3%$2$6$0.25$138.00
Qwen: Qwen3.8 2.4T A95B (batch)Not statedOpenRouterUnknownNot stated--82%$2$6$0.25$138.00 est.
Qwen: Qwen3.8 Max (0902)Not statedOpenRouterUnknownNot stated---$2$6$0.25$138.00 est.
Qwen3.8 2.4T A95BNot statedAI RouterUnknownNot stated---$2$6$0.25$138.00 est.
Qwen3.8 Max 0902Not statedAI RouterUnknownNot stated---$2$6$0.25$138.00 est.
GLM 5.3 FastNot statedAI RouterUnknownNot stated---$2.1$6.6$0.21$138.00 est.
e2ee-glm-5-2-pZhipu AIVenice AIUnknownOpen744B--$1.75$5.75$0.3$139.63 est.
Magnum v4 72BAnthraciteOpenRoutertextOpen72.7B--$2.5$5-$140.00 est.
Qwen 3.6 Max PreviewAlibabaAI RoutertextNot stated--$1.3$7.8$0.26$140.40 est.
e2ee-glm-5-3-pNot statedVenice AIUnknownNot stated---$1.75$5.5$0.325$142.00 est.
Jamba 1.5 LargeAI21 LabsAWS BedrockUnknownNot stated---$2$8-$146.00 est.
Jamba Large 1.7AI21 LabsOpenRoutertextOpen398.6B--$2$8-$146.00 est.
perplexity/sonar-deep-researchPerplexityFastRoutertextClosed---$2$8-$146.00 est.
perplexity/sonar-reasoning-proPerplexityFastRoutermultimodalClosed---$2$8-$146.00 est.
Grok 4.5Not statedAI RoutermultimodalNot stated---$2$6$0.3$147.00 est.
qwen3.5-omni-plusAlibabaAlibabamultimodalOpen808B-$1.4$11-$148.10 est.
qwen3.5-omni-plus-2026-03-15Not statedAlibabaUnknownNot stated---$1.4$11-$148.10 est.
Qwen3 Coder 480B A35B InstructAlibabaAlibabatextOpen480.2B-$1.5$7.5$0.3$149.25
Qwen/Qwen3.8-2.4T-A95B@togetherNot statedHugging FaceUnknownNot stated---$2.5$6.25-$150.63 est.
Gpt 3.5 Turbo 16k 0613OpenAIOpenAItextClosed--$3$4$0.3$151.00
openai/gpt-3.5-turbo-16kOpenAIFastRoutertextClosed7B-$3$4-$151.00 est.
qwen-mt-plusAlibabaAlibabatextNot stated--$2.46$7.37-$158.59 est.
o1-miniOpenAIOpenAItextClosed--$1.1$4.4$0.55$159.50
o3-miniOpenAIOpenAIUnknownClosed--4.5%$1.1$4.4$0.55$159.50 est.
openai/o3-mini-highOpenAIFastRoutertextClosed68B-4.5%$1.1$4.4$0.55$159.50 est.
Qwen 3.7 MaxAlibabaAlibaba +11 moretextNot stated-74.5%$2.5$7.5-$161.25 est.
qwen-3-7-maxAlibabaVenice AImultimodalClosed--$2.7$8.05$0.27$173.73 est.
qwen3.7-max-2026-05-17:0-token-1mNot statedAlibabaUnknownNot stated---$2.5$7.5-$161.25 est.
qwen3.7-max-2026-05-20:0-token-1mNot statedAlibabaUnknownNot stated---$2.5$7.5-$161.25 est.
qwen3.7-max-2026-06-08:0-token-1mNot statedAlibabaUnknownNot stated---$2.5$7.5-$161.25 est.
qwen3.7-max-preview:0-token-1mNot statedAlibabaUnknownNot stated---$2.5$7.5-$161.25 est.
qwen3.7-max-us:0-token-1mNot statedAlibabaUnknownNot stated---$2.5$7.5-$161.25 est.
Anthropic Claude Sonnet LatestAnthropicOpenRoutermultimodalClosed80B--$2$10$0.2$163.00 est.
Claude Sonnet 5AnthropicAnthropicmultimodalClosed--75.3%$2$10$0.2$163.00 est.
gemini-api:gemini-robotics-er-2-previewNot statedGoogle Vertex AI / Gemini APIUnknownNot stated---$2$10-$163.00 est.
gemini-api:gemini-robotics-er-2-streaming-previewNot statedGoogle Vertex AI / Gemini APIUnknownNot stated---$2$10-$163.00 est.
OpenAI GPT LatestOpenAIOpenRoutermultimodalClosed---$2$10$0.2$163.00 est.
openai/gpt-image-1-miniOpenAIFastRoutertextClosed---$2.5$8$0.25$165.50 est.
zai-org/GLM-5.2-TEEZhipu AIChutestextOpen744B-$1.25$3.95$0.625$172.33 est.
qwen-3-8-maxNot statedVenice AIUnknownNot stated---$2.5$7.5$0.3125$172.50 est.
qwen3-omni-30b-a3b-captionerNot statedAlibabaUnknownNot stated---$3.81$3.06-$174.60 est.
Gemini 3 Pro HighGoogleGooglemultimodalClosed--$2$12$0.2$180.00
Gemini 3 Pro LowGoogleGooglemultimodalClosed--$2$12$0.2$180.00
Gemini 3 Pro MediumGoogleGooglemultimodalClosed--$2$12$0.2$180.00
Gemini 3.1 Pro HighGoogleGoogleUnknownClosed---$2$12$0.2$180.00
Gemini 3.1 Pro LowGoogleGoogleUnknownClosed---$2$12$0.2$180.00
Gemini 3.1 Pro MediumGoogleGoogleUnknownClosed---$2$12$0.2$180.00
Gemini 3.1 Pro PreviewGoogleGooglemultimodalClosed-73.8%$2$12$0.2$180.00
Gemini Pro AgentGoogleGoogleUnknownClosed---$2$12$0.2$180.00
gemini-3.1-proGoogle DeepMindDeepInframultimodalClosed--$2$12-$180.00 est.
gemini-api:gemini-3-pro-image-nano-banana-proNot statedGoogle Vertex AI / Gemini APIUnknownNot stated---$2$12-$180.00 est.
Google Gemini Pro LatestGoogleOpenRoutermultimodalClosed--$2$12$0.2$180.00 est.
Google: Gemini 3.1 Pro Preview Custom ToolsGoogleOpenRoutermultimodalClosed---$2$12$0.2$180.00 est.
GPT 5.6 TerraOpenAIOpenAImultimodalClosed--$2$12$0.2$180.00 est.
Nano Banana Pro (Gemini 3 Pro Image)GoogleAI Routerimage_generationClosed--$2$12$0.2$180.00 est.
Command ACohereAI RoutertextOpen111.1B-$2.5$10-$182.50 est.
command-r-plus-08-2024CohereCoheretextNot stated--$2.5$10-$182.50 est.
OpenAI: GPT AudioOpenAIOpenRouterotherClosed---$2.5$10-$182.50 est.
openai/gpt-4o-search-previewOpenAIFastRoutertextClosed5B--$2.5$10-$182.50 est.
Palmyra X4Not statedAWS BedrocktextNot stated---$2.5$10-$182.50 est.
Palmyra X4WriterAWS BedrocktextNot stated--$2.5$10-$182.50 est.
Grok 4.6Not statedAI Router +1 moreUnknownNot stated---$2$6$0.5$183.00 est.
grok-4-6Not statedVenice AIUnknownNot stated---$2.27$6.8$0.57$208.07 est.
Grok 4.6xAIxAIUnknownNot stated--88.4%$2$6$0.5$183.00 est.
xAI: Grok LatestxAIOpenRoutermultimodalClosed--$2$6$0.5$183.00 est.
glm-5.2-fast-previewNot statedAlibabaUnknownNot stated---$2.8$8.8-$184.00 est.
GPT 5.2OpenAIOpenAI +10 moremultimodalNot stated---$1.75$14$0.175$187.25 est.
GPT 5.2OpenAIOpenAImultimodalClosed--$21$168-$2,247.00 est.
GPT 5.2 CodexOpenAIOpenAImultimodalClosed---$1.75$14$0.175$187.25
GPT 5.3 CodexOpenAIOpenAIUnknownNot stated--$1.75$14$0.175$187.25 est.
Gpt 5.3 Codex SparkOpenAIOpenAImultimodalClosed--$1.75$14$0.175$187.25
openai/gpt-5.3-chatOpenAIFastRoutermultimodalClosed---$1.75$14$0.175$187.25 est.
nvidia/Nemotron-4-340B-InstructNVIDIADeepInfraUnknownOpen340B--$4.2$4.2-$199.50 est.
GPT-4.1OpenAIOpenAImultimodalClosed6B-$2$8$0.5$200.00 est.
o3OpenAIOpenAIUnknownClosed--$2$8$0.5$200.00 est.
o4-mini (Fast)Not statedAI RouterUnknownNot stated---$2$8$0.5$200.00 est.
glm-4.5-xZhipu AIZhipu AItextNot stated---$2.2$8.9$0.45$202.85 est.
MoonshotAI Kimi LatestNot statedOpenRoutermultimodalClosed--$2.55$12.75$0.256$208.00 est.
gemini-api:gemini-2.5-pro-preview-ttsNot statedGoogle Vertex AI / Gemini APIUnknownNot stated---$1$20-$209.00 est.
gemini-api:gemini-3.1-flash-tts-previewNot statedGoogle Vertex AI / Gemini APIUnknownNot stated---$1$20-$209.00 est.
qwen3.5-omni-plus-realtimeNot statedAlibabaUnknownNot stated---$2.1$16.5-$222.15 est.
qwen3.5-omni-plus-realtime-2026-03-15Not statedAlibabaUnknownNot stated---$2.1$16.5-$222.15 est.
gemini-api:gemini-2.5-computer-use-preview-long-contextNot statedGoogle Vertex AI / Gemini APIUnknownNot stated---$2.5$15-$225.00 est.
gemini-api:gemini-2.5-pro-long-contextNot statedGoogle Vertex AI / Gemini APIUnknownNot stated---$2.5$15-$225.00 est.
GPT 5.4OpenAIOpenAIUnknownClosed9B-$2.5$15$0.25$225.00 est.
openai/gpt-4o-2024-11-20OpenAIVenice AImultimodalClosed8B-$3.125$12.5-$228.12 est.
Moonshot AINot statedDigitalOceanUnknownNot stated---$2.85$14.25-$232.27 est.
moonshotai/Kimi-K3@deepinfraNot statedHugging FaceUnknownNot stated---$2.85$14.25-$232.27 est.
Claude 3 SonnetAnthropicAWS BedrockUnknownNot stated---$3$15-$244.50 est.
Claude 3.5 SonnetAnthropicAWS Bedrock +1 moreUnknownNot stated---$3$15-$244.50 est.
Claude 3 5 SonnetAnthropicAnthropicmultimodalClosed--$3$15$0.3$251.25
Cohere Command R+CohereAWS BedrockUnknownNot stated---$3$15-$244.50 est.
command-r-plus-04-2024Not statedCohereUnknownNot stated---$3$15-$244.50 est.
Kimi K3Moonshot AINovitaUnknownOpen2.8T--$3$15-$244.50 est.
moonshotai/Kimi-K3@basetenNot statedHugging FaceUnknownNot stated---$3$15-$244.50 est.
moonshotai/Kimi-K3@fireworks-aiNot statedHugging FaceUnknownNot stated---$3$15-$244.50 est.
moonshotai/Kimi-K3@togetherNot statedHugging FaceUnknownNot stated---$3$15-$244.50 est.
Perplexity: Sonar Pro SearchPerplexityOpenRoutermultimodalClosed---$3$15-$244.50 est.
perplexity/sonar-proPerplexityFastRoutermultimodalClosed---$3$15-$244.50 est.
Claude 3.5 Sonnet v2AnthropicAWS BedrockUnknownNot stated---$3$15$0.3$244.50 est.
Claude 3.7 SonnetAnthropicAWS BedrockUnknownNot stated---$3$15$0.3$244.50 est.
Claude Sonnet 4AnthropicAnthropic +7 moremultimodalClosed--$3$15$0.3$244.50 est.
Claude Sonnet 4AnthropicAWS BedrockUnknownNot stated---$3$15$0.3$244.50 est.
Claude Sonnet 4.5AnthropicAnthropic +10 moremultimodalClosed--$3$15$0.3$244.50 est.
Claude Sonnet 4.5AnthropicAWS BedrockmultimodalNot stated--$3$15$0.3$244.50 est.
Claude Sonnet 4.6AnthropicAnthropicUnknownClosed-71.2%$3$15$0.3$244.50 est.
claude-4-5-sonnetAnthropicFastRoutermultimodalClosed-55.8%$3$15$0.3$244.50 est.
Kimi K3 FastMoonshot AIMoonshot AImultimodalOpen2.8T82.4%$3$15$0.3$244.50 est.
AionLabs: Aion-3.0Not statedOpenRouter +1 moretextClosed--$3$6$0.75$249.00 est.
aion-labs-aion-3-0Not statedVenice AItextClosed--$3.75$7.5$0.9375$311.25 est.
Claude Sonnet 3 7AnthropicAnthropicmultimodalClosed--$3$15$0.3$251.25
Mistral Mistral LargeMistral AIAWS BedrockUnknownNot stated---$4$12-$258.00 est.
GPT 5.1 Thinking (Fast)Not statedAI RouterUnknownNot stated---$2.5$20$0.25$267.50 est.
GPT-5 (Fast)Not statedAI RouterUnknownNot stated---$2.5$20$0.25$267.50 est.
anthropic/claude-3-7-sonnet-latestAnthropicDeepInfraUnknownClosed---$3.3$16.5$0.33$268.95 est.
anthropic/claude-4-sonnetAnthropicDeepInfraUnknownClosed---$3.3$16.5-$268.95 est.
Amazon Nova Premier 1.0AmazonAWS Bedrock +1 moreUnknownClosed---$2.5$12.5$0.625$271.25 est.
Amazon: Nova Premier 1.0AmazonOpenRoutermultimodalClosed---$2.5$12.5$0.625$271.25 est.
Composer 1.5CursorCursortextClosed4B--$3.5$17.5$0.35$285.25
openai/gpt-realtime-1.5OpenAIFastRouterUnknownClosed---$4$16$0.4$292.00 est.
qwen3.5-livetranslate-flash-realtimeNot statedAlibabaUnknownNot stated---$7.5$0.55-$297.18 est.
qwen3.5-livetranslate-flash-realtime-2026-05-19Not statedAlibabaUnknownNot stated---$7.5$0.55-$297.18 est.
gemini-api:gemini-3.1-pro-preview-long-contextNot statedGoogle Vertex AI / Gemini APIUnknownNot stated--$4$18-$309.00 est.
openai/gpt-realtimeOpenAIFastRoutermultimodalClosed---$4$16$0.5$310.00 est.
gemini-api:gemini-3.5-live-translateNot statedGoogle Vertex AI / Gemini APIUnknownNot stated---$3.5$21-$315.00 est.
GPT-4 TurboOpenAIOpenRoutermultimodalNot stated--$5$15-$322.50 est.
openai/gpt-4o-2024-05-13OpenAIOpenAImultimodalClosed--$5$15-$322.50 est.
x-ai/grok-4-fastxAIFastRoutermultimodalClosed--$3$15$0.75$325.50 est.
GPT 5.6 Sol (Fast)Not statedAI RouterUnknownNot stated---$4$20$0.4$326.00 est.
gpt-5.6-solOpenAIOpenAImultimodalClosed--$4$20$0.4$326.00 est.
Claude Fable 5.1Not statedOpenRouterUnknownNot stated---$5$25$0.125$340.00 est.
GPT-4.1 (Fast)Not statedAI RouterUnknownNot stated---$3.5$14$0.875$350.00 est.
o3 (Fast)Not statedAI RouterUnknownNot stated---$3.5$14$0.875$350.00 est.
GPT 5.6 Terra (Fast)Not statedAI RouterUnknownNot stated---$4$24$0.4$360.00 est.
GPT-4oOpenAIOpenAImultimodalClosed--$2.5$10$1.25$362.50 est.
openai/gpt-4o-2024-08-06OpenAIFastRoutermultimodalClosed--$2.5$10$1.25$362.50 est.
kimi-k3-fast-apiNot statedVenice AIUnknownNot stated---$4.5$22.5$0.45$366.75 est.
GPT Image 1.5OpenAIDigitalOceanimage_generationNot stated--$5$10$1$370.00 est.
GPT 5.2 (Fast)Not statedAI RouterUnknownNot stated---$3.5$28$0.35$374.50 est.
GPT 5.3 Codex (Fast)Not statedAI RouterUnknownNot stated---$3.5$28$0.35$374.50 est.
qwen3-livetranslate-flash-realtimeAlibabaAlibabaotherNot stated--$10$1.3-$401.05 est.
qwen3-livetranslate-flash-realtime-2025-09-22Not statedAlibabaUnknownNot stated---$10$1.3-$401.05 est.
Anthropic: Claude Opus LatestAnthropicOpenRoutermultimodalClosed---$5$25$0.5$407.50 est.
Claude Opus 4.5AnthropicAnthropic +10 moremultimodalClosed--$5$25$0.5$407.50 est.
Claude Opus 4.5AnthropicAWS BedrockmultimodalNot stated--$5$25$0.5$407.50 est.
Claude Opus 4.6AnthropicAnthropic +13 moreUnknownClosed---$5$25$0.5$407.50 est.
Claude Opus 4.6AnthropicAWS BedrockmultimodalNot stated--$5$25$0.5$407.50 est.
Claude Opus 4.7AnthropicAnthropicUnknownClosed--83.1%$5$25$0.5$407.50 est.
claude-opus-4-8AnthropicAnthropicmultimodalClosed-84.6%$5$25$0.5$407.50 est.
claude-opus-5AnthropicAnthropicmultimodalClosed-76.4%$5$25$0.5$407.50 est.
GPT-6 AstraNot statedOpenRouterUnknownNot stated---$5$25$0.5$407.50 est.
chat-latestNot statedOpenAIUnknownNot stated---$5$30$0.5$450.00 est.
daybreak-blue-latestNot statedOpenAIUnknownNot stated---$5$30$0.5$450.00 est.
GPT 5.4 (Fast)Not statedAI RouterUnknownNot stated---$5$30$0.5$450.00 est.
GPT 5.5OpenAIOpenAIUnknownClosed--$5$30$0.5$450.00 est.
OpenAI: GPT Chat LatestOpenAIOpenRoutermultimodalClosed---$5$30$0.5$450.00 est.
Sakana: Fugu UltraSakana AISakana AIUnknownClosed---$5$30$0.5$450.00
moonshotai/Kimi-K3-TEEMoonshot AIChutesmultimodalOpen2.8T-$3$15$1.5$460.50 est.
Gpt 5 6 ThinkingOpenAIOpenAIUnknownNot stated---$5$30$0.5$461.25
GPT Image 2OpenAIDigitalOceanimage_generationNot stated--$5$0$2$465.00 est.
Claude 3.5 Sonnet (Public Extended Access, Effective 1 Dec 2025)Not statedAWS BedrockUnknownNot stated---$6$30-$489.00 est.
Claude 3.5 Sonnet v2 (extended access)AnthropicAWS BedrockUnknownClosed---$6$30-$489.00 est.
Claude 3.5 Sonnet v2 (Public Extended Access, Effective 1 Dec 2025)Not statedAWS BedrockUnknownNot stated---$6$30$0.6$489.00 est.
qwen-deep-researchAlibabaAlibabatextNot stated---$7.742$23.367-$500.56 est.
OpenAI: GPT-5 ImageOpenAIOpenRouterimage_generationClosed--$10$10$1.25$520.00 est.
x-ai/grok-3-betaxAIFastRoutertextClosed---$5$25$1.25$542.50 est.
sarvam/bulbul:v2Sarvam AIFastRoutertextOpen6B--$15$0-$585.00 est.
GPT-4o (Fast)Not statedAI RouterUnknownNot stated---$4.25$17$2.125$616.25 est.
Gpt 4 0125 PreviewOpenAIOpenAItextClosed--$10$30$1$645.00
Gpt 4 1106 PreviewOpenAIOpenAItextClosed--$10$30$1$645.00
Gpt 4 1106 Vision PreviewOpenAIOpenAImultimodalClosed--$10$30$1$645.00
gpt-4-turbo-2024-04-09OpenAIOpenAImultimodalClosed--$10$30-$645.00 est.
OpenAI: GPT-4 Turbo PreviewOpenAIOpenRoutertextClosed---$10$30-$645.00 est.
OpenAI: GPT-5.4 Image 2OpenAIOpenRouterimage_generationClosed--$8$15$2$655.50 est.
GPT-image-1OpenAIDigitalOceanimage_generationNot stated--$5$40$1.25$670.00 est.
Anthropic: Claude Fable LatestAnthropicOpenRoutermultimodalClosed--$10$50$0.25$680.00 est.
claude-mythos-5.1Not statedAnthropicUnknownNot stated---$10$50$0.25$680.00 est.
Claude Fable 5AnthropicAnthropicmultimodalClosed--84.6%$10$50$1$815.00 est.
claude-mythos-5AnthropicAnthropicmultimodalClosed--$10$50$1$815.00 est.
o3-deep-researchOpenAIVercel AI GatewaymultimodalNot stated---$10$40$2.5$1,000.00 est.
daybreak-red-latestNot statedOpenAIUnknownNot stated---$12.5$75$1.25$1,125.00 est.
GPT 5.5 (Fast)Not statedAI RouterUnknownNot stated---$12.5$75$1.25$1,125.00 est.
gpt-5.6-cyberNot statedOpenAIUnknownNot stated---$12.5$75$1.25$1,125.00 est.
Claude 3 OpusAnthropicAWS Bedrock +1 moreUnknownNot stated---$15$75-$1,222.50 est.
Claude 3 OpusAnthropicAnthropicmultimodalClosed--$15$75$1.5$1,256.25
Claude Opus 4AnthropicAnthropic +4 moremultimodalNot stated--$15$75$1.5$1,222.50 est.
Claude Opus 4AnthropicAWS BedrockUnknownNot stated---$15$75$1.5$1,222.50 est.
Claude Opus 4 1AnthropicAnthropic +4 moremultimodalClosed--$15$75$1.5$1,222.50 est.
Claude Opus 4.1AnthropicAWS BedrockmultimodalNot stated--$15$75$1.5$1,222.50 est.
Claude Opus 4 0AnthropicAnthropicmultimodalClosed--$15$75$1.5$1,256.25
anthropic/claude-4-opusAnthropicDeepInfraUnknownClosed---$16.5$82.5-$1,344.75 est.
o3 ProOpenAIOpenAImultimodalClosed--$20$80-$1,460.00 est.
GPT-5 proOpenAIOpenAImultimodalClosed--$15$120-$1,605.00 est.
GPT-6 Astra (Fast)Not statedAI RouterUnknownNot stated---$20$100$2$1,630.00 est.
Gpt 4 0314OpenAIOpenAItextClosed--$30$60$3$1,680.00
gpt-4-0613OpenAIOpenAItextClosed--$30$60-$1,680.00 est.
openai/gpt-4OpenAIFastRoutertextClosed---$30$60-$1,680.00 est.
o1OpenAIOpenAIUnknownClosed--$15$60$7.5$2,175.00 est.
o1-previewNot statedMicrosoft Azure AI FoundrytextNot stated---$15$60$7.5$2,175.00 est.
Claude Mythos PreviewAnthropicAWS BedrockUnknownNot stated---$27.5$137.5$2.75$2,241.25 est.
GPT 5.4 ProOpenAIOpenAIUnknownClosed262B-$30$180-$2,700.00 est.
GPT 5.5 ProOpenAIOpenAIUnknownClosed--$30$180-$2,700.00 est.
Gpt 4 32kOpenAIOpenAItextClosed--$60$120$6$3,360.00
o1-proOpenAIOpenAImultimodalClosed--$150$600-$10,950.00 est.
inclusionai-ling-3.0-flashNot statedNovita AIUnknownNot stated---$0.06$0.18$120$21,602.79 est.
zai-org-glm-4.5vNot statedNovita AIUnknownNot stated---$0.13$0.85$250$45,009.96 est.
tencent-hy3Not statedNovita AIUnknownNot stated---$0.14$0.58$350$63,007.87 est.
stepfun-step-3.7-flashNot statedNovita AIUnknownNot stated---$0.2$1.15$400$72,013.98 est.
zai-org-autoglm-phone-9b-multilingualNot statedNovita AIUnknownNot stated---$0.3$0.9$550$99,013.95 est.
kwaipilot-kat-coder-proNot statedNovita AIUnknownNot stated---$0.3$1.2$600$108,016.50 est.
inclusionai-ling-2.6-flashNot statedNovita AIUnknownNot stated---$0.3$2.5$600$108,027.55 est.
baidu-cobuddyNot statedNovita AIUnknownNot stated---$0.28$1.13$700$126,015.49 est.
moonshotai-kimi-k2.6Not statedNovita AIUnknownNot stated---$0.6$3$1,000$180,038.10 est.
zai-org-glm-4.6vNot statedNovita AIUnknownNot stated---$0.55$2.2$1,100$198,030.25 est.
moonshotai-kimi-k2.5Not statedNovita AIUnknownNot stated---$0.6$2.5$1,500$270,033.85 est.
moonshotai-kimi-k2.7-codeNot statedNovita AIUnknownNot stated---$0.8$3.4$1,600$288,045.70 est.
mindai-macaron-v1-ventiNot statedNovita AIUnknownNot stated---$1.5$4.5$3,000$540,069.75 est.
moonshotai-kimi-k3Not statedNovita AIUnknownNot stated---$3$15$3,000$540,190.50 est.
ace-step/prompt-to-audioNot statedFastRoutertextOpen---$0$0-Published as $0
black-forest-labs/flux-devBlack Forest LabsFastRoutertextOpen12B--$0$0-Published as $0
black-forest-labs/flux-pro-2.0Black Forest LabsFastRoutertextOpen12B--$0$0-Published as $0
BunnyNot statedNovitatextClosed---$0$0-Published as $0
bytedance/seedream-4.0ByteDanceFastRoutertextClosed--$0$0-Published as $0
bytedance/seedream-4.5ByteDanceFastRoutertextClosed--$0$0-Published as $0
Dots Studio: Dots3-Note Preview (free)Dots StudioOpenRouterUnknownNot stated---$0$0-Published as $0
fastrouter/autoNot statedFastRoutermultimodalClosed---$0$0-Published as $0
Flux Kontext ProBFLFastRouterimage_generationNot stated--$0$0-Published as $0
Free Models RouterNot statedOpenRoutermultimodalClosed--$0$0-Published as $0
Gemini 3.1 Flash Image Preview (Nano Banana 2)GoogleFastRouterUnknownClosed--$0$0-Published as $0
Gemma 4 31B ITGoogleFastRouterUnknownOpen31.3B-$0$0-Published as $0
GLM-4.6V-FlashZhipu AIVercel AI GatewaymultimodalNot stated--$0$0-Published as $0
Google Gemma 4 26B A4BGoogleFastRouterUnknownOpen26.5B-$0$0-Published as $0
Google: Lyria 3 Clip PreviewGoogleOpenRouterotherClosed---$0$0-Published as $0
Google: Lyria 3 Pro PreviewGoogleOpenRouterotherClosed---$0$0-Published as $0
google/gemini-3-pro-image-previewGoogleFastRouterUnknownClosed10B-$0$0-Published as $0
google/imagen-4.0-fastGoogleFastRouterUnknownClosed--$0$0-Published as $0
google/imagen-4.0-ultraGoogleFastRouterUnknownClosed--$0$0-Published as $0
gt-4pNot statedNovitamultimodalClosed---$0$0-Published as $0
inclusionAI: Ling 3.0 Flash Fin (free)Not statedOpenRouterUnknownNot stated---$0$0-Published as $0
inclusionAI: Ling 3.0 Flash Sante (free)Not statedOpenRouterUnknownNot stated---$0$0-Published as $0
Inkling SmallThinking Machines LabOpenRoutermultimodalClosed12B55.1%$0$0-Published as $0
Laguna S 2.1PoolsideOpenRoutertextOpen117.6B--$0$0-Published as $0
Laguna S 2.1 FreePoolsideVercel AI GatewaytextNot stated--$0$0-Published as $0
leonardo-ai/lucid-originLeonardo.AiFastRouterUnknownClosed--$0$0-Published as $0
leonardo-ai/lucid-realismLeonardo.AiFastRouterUnknownClosed--$0$0-Published as $0
leonardo-ai/phoenixLeonardo.AiFastRoutertextClosed---$0$0-Published as $0
Ling 3.0 FlashAnt Group / InclusionAINovitatextOpen7.9B55.4%$0$0-Published as $0
LiquidAI: LFM2.5-2.6B (free)Liquid AIOpenRouterUnknownNot stated---$0$0-Published as $0
M2-herMiniMaxNovitatextOpen230B--$0$0-Published as $0
Macaron V1 TallNot statedNovitatextClosed---$0$0-Published as $0
Macaron V1 VentiNot statedNovitatextClosed---$0$0-Published as $0
Nano Banana (Gemini 2.5 Flash Image)GeminiFastRouterUnknownClosed---$0$0-Published as $0
Nemotron Nano 12B 2 VL (free)NVIDIAOpenRoutermultimodalOpen13.2B-$0$0-Published as $0
Nemotron Nano 9B V2 (free)NVIDIAOpenRoutertextOpen8.9B-$0$0-Published as $0
Nemotron-Content-Safety-3.5NVIDIAOpenRouterUnknownOpen4.3B-$0$0-Published as $0
Nex-N2-ProNot statedNovitamultimodalOpen396.8B67.8%$0$0-Published as $0
North Mini Code 1 0CohereCoheretextOpen30.5B35.6%$0$0$0Published as $0
NVIDIA: Nemotron 3 Nano Omni (free)NVIDIAOpenRoutermultimodalOpen33B-$0$0-Published as $0
openai/omni-moderation-latestOpenAIFastRoutertextClosed---$0$0-Published as $0
Poolside: Laguna XS 2.1 (free)PoolsideOpenRoutertextOpen33.4B-$0$0-Published as $0
prism-ml/Ternary-Bonsai-27B-AWQ-4bit@togetherNot statedHugging FaceUnknownNot stated---$0$0-Published as $0
prism-ml/Ternary-Bonsai-27B-gguf@togetherNot statedHugging FaceUnknownNot stated---$0$0-Published as $0
sarvam/sarvam-105bSarvam AISarvam AItextOpen105B-$0$0$0Published as $0
sarvam/sarvam-30bSarvam AISarvam AItextOpen30B-$0$0$0Published as $0
Ternary Bonsai 27BNot statedTogether AIUnknownNot stated---$0$0-Published as $0
@cf/baai/bge-base-en-v1.5Not stated-textNot stated------Not comparable
@cf/baai/bge-large-en-v1.5Not stated-textNot stated------Not comparable
@cf/baai/bge-m3Not stated-textNot stated------Not comparable
@cf/baai/bge-reranker-baseNot stated-textNot stated------Not comparable
@cf/baai/bge-small-en-v1.5Not stated-textNot stated------Not comparable
@cf/huggingface/distilbert-sst-2-int8Not stated-textNot stated------Not comparable
@cf/pfnet/plamo-embedding-1bNot stated-textNot stated------Not comparable
AI_CLASSIFY (all models)Not stated-UnknownClosed------Not comparable
Anthropic Claude 2.0Anthropic-UnknownNot stated------Not comparable
Anthropic Claude 2.1Anthropic-UnknownNot stated------Not comparable
apertus-70bSwiss AI Initiative (EPFL / ETH Zurich / CSCS)-textOpen70B-----Not comparable
bge-m3Not stated-textNot stated------Not comparable
bge-multilingual-gemma2Not stated-textNot stated-----Not comparable
bria-eraserBria-image_generationNot stated------Not comparable
bria-extract-objectBria-image_generationNot stated------Not comparable
bria-fiboBria-image_generationNot stated------Not comparable
bria-fibo-editBria-image_generationNot stated------Not comparable
bria-fibo-image-blendBria-image_generationNot stated------Not comparable
bria-fibo-recolorBria-image_generationNot stated------Not comparable
bria-fibo-relightBria-image_generationNot stated------Not comparable
bria-fibo-reseasonBria-image_generationNot stated------Not comparable
bria-fibo-restoreBria-image_generationNot stated------Not comparable
bria-fibo-restyleBria-image_generationNot stated------Not comparable
bria-fibo-sketch-to-imageBria-image_generationNot stated------Not comparable
bria-genfillBria-image_generationNot stated------Not comparable
bria-image-increase-resolutionBria-image_generationNot stated------Not comparable
bria-image-remove-backgroundBria-image_generationNot stated------Not comparable
bria-product-dimensionsBria-image_generationNot stated------Not comparable
bria-video-eraserBria-video_generationNot stated------Not comparable
bria-video-increase-resolutionBria-video_generationNot stated------Not comparable
bria-video-remove-backgroundBria-video_generationNot stated------Not comparable
Chatterbox-ttsResemble-otherNot stated------Not comparable
claude-4-6-sonnetAnthropic-multimodalClosed-----Not comparable
Cohere Embed 3 Model - EnglishCohere-UnknownNot stated------Not comparable
Cohere Embed Model 3 - MultilingualCohere-UnknownNot stated------Not comparable
FLUX 1.1 [pro]Not stated-image_generationNot stated------Not comparable
FLUX 1.1 [pro] UltraNot stated-UnknownNot stated------Not comparable
FLUX.1 Fill [pro]Black Forest Labs-image_generationNot stated-----Not comparable
FLUX.1 Kontext [max]Not stated-UnknownNot stated------Not comparable
FLUX.1 Kontext [pro]Not stated-UnknownNot stated------Not comparable
FLUX.1 Kontext MaxBlack Forest Labs-image_generationNot stated-----Not comparable
FLUX.1-devNot stated-image_generationNot stated------Not comparable
FLUX1.1 [pro]Black Forest Labs-image_generationNot stated-----Not comparable
FLUX1.1 [pro] UltraBlack Forest Labs-image_generationNot stated-----Not comparable
Flux2-DevFlux2-image_generationNot stated------Not comparable
Flux2-KleinFlux2-image_generationNot stated------Not comparable
gemini-3.1-pro-long-contextGoogle-UnknownClosed------Not comparable
gemini-api:gemini-2.5-flash-lite-previewNot stated-UnknownNot stated------Not comparable
gemini-api:gemini-embeddingNot stated-UnknownNot stated------Not comparable
Gemini-batch-inferenceGoogle-textNot stated------Not comparable
GLM-ImageGLM-image_generationNot stated------Not comparable
GMI-Halloween-HauntedYou-WorkflowGMI-video_generationNot stated------Not comparable
GMI-MiniMeTalks-WorkflowGMI-video_generationNot stated------Not comparable
googlegemma-3-4b-itNot stated-textNot stated------Not comparable
gpt-image-2-editOpenAI-image_generationNot stated------Not comparable
gpt-image-2-generateOpenAI-image_generationNot stated------Not comparable
Grok Imagine ImagexAI-image_generationNot stated-----Not comparable
grok-4.20-long-contextxAI-UnknownClosed------Not comparable
grok-4.3-long-contextxAI-UnknownClosed7B-----Not comparable
happyhorse-1.0-i2vAliyun-video_generationNot stated------Not comparable
happyhorse-1.0-t2vAliyun-video_generationNot stated------Not comparable
happyhorse-1.1-i2vAliyun-video_generationNot stated-----Not comparable
happyhorse-1.1-r2vAliyun-video_generationNot stated-----Not comparable
happyhorse-1.1-t2vAliyun-video_generationNot stated-----Not comparable
heygen-avatar-4HeyGen-video_generationNot stated------Not comparable
holo2-30b-a3bNot stated-multimodalOpen30B-----Not comparable
hunyuan-3d-proHunyuan-multimodalNot stated------Not comparable
hunyuan-image-to-imageHunyuan-image_generationNot stated------Not comparable
Hunyuan1.5Hunyuan-video_generationNot stated------Not comparable
Imagen 4Google-image_generationNot stated-----Not comparable
Imagen 4 FastGoogle-image_generationNot stated-----Not comparable
Imagen 4 UltraGoogle-image_generationNot stated-----Not comparable
kling-2.6-motion-controlKling-video_generationNot stated------Not comparable
kling-3-motion-controlKling-video_generationNot stated------Not comparable
kling-custom-voiceKling-multimodalNot stated------Not comparable
kling-identify-faceKling-multimodalNot stated------Not comparable
Kling-Image2Video-V1.6-ProKling-video_generationNot stated------Not comparable
Kling-Image2Video-V1.6-StandardKling-video_generationNot stated------Not comparable
Kling-Image2Video-V2-MasterKling-video_generationNot stated------Not comparable
Kling-Image2Video-V2.1-MasterKling-video_generationNot stated------Not comparable
Kling-Image2Video-V2.1-ProKling-video_generationNot stated------Not comparable
Kling-Image2Video-V2.1-StandardKling-video_generationNot stated------Not comparable
kling-lip-syncKling-video_generationNot stated------Not comparable
kling-o1-edit-videoKling-video_generationNot stated------Not comparable
kling-o1-flfvKling-video_generationNot stated------Not comparable
kling-o1-image-to-videoKling-video_generationNot stated------Not comparable
kling-o1-reference-to-videoKling-video_generationNot stated------Not comparable
Kling-Text2Video-V1.6-StandardKling-video_generationNot stated------Not comparable
Kling-Text2Video-V2-MasterKling-video_generationNot stated------Not comparable
Kling-Text2Video-V2.1-MasterKling-video_generationNot stated------Not comparable
kling-v2-5-turboKling-video_generationNot stated------Not comparable
kling-v2-6Kling-video_generationNot stated-----Not comparable
kling-v3-image-to-videoKling-video_generationNot stated------Not comparable
kling-v3-text-to-videoKling-video_generationNot stated------Not comparable
Krea-Realtime-14BKrea-video_generationNot stated------Not comparable
LTX-2LTX-video_generationNot stated------Not comparable
LTX-2-KeyframeInterpolationLTX-video_generationNot stated------Not comparable
LTX2-DistilledLTX2-video_generationNot stated------Not comparable
LTX2-ICLoRALTX2-video_generationNot stated------Not comparable
LTX2-Ti2VidTwoStagesLTX2-video_generationNot stated------Not comparable
luma-ray-3-2-editLuma-video_generationNot stated------Not comparable
luma-ray-3-2-generateLuma-video_generationNot stated------Not comparable
luma-ray-3-2-reframeLuma-video_generationNot stated------Not comparable
luma-uni-1.1Luma-image_generationNot stated------Not comparable
minimax-audio-voice-clone-speech-2.6-hdMiniMax-otherNot stated------Not comparable
minimax-audio-voice-clone-speech-2.6-turboMiniMax-otherNot stated------Not comparable
minimax-audio-voice-clone-speech-2.8-hdMiniMax-otherNot stated------Not comparable
minimax-audio-voice-clone-speech-2.8-turboMiniMax-otherNot stated------Not comparable
MiniMax-H3Minimax-video_generationNot stated------Not comparable
Minimax-Hailuo-02Minimax-video_generationNot stated------Not comparable
Minimax-Hailuo-2.3MiniMax-video_generationNot stated------Not comparable
Minimax-Hailuo-2.3-FastMiniMax-video_generationNot stated------Not comparable
minimax-music-2.5MiniMax-otherNot stated------Not comparable
minimax-music-3.0MiniMax-otherNot stated------Not comparable
minimax-tts-speech-01-hdMiniMax-otherNot stated------Not comparable
minimax-tts-speech-01-turboMiniMax-otherNot stated------Not comparable
minimax-tts-speech-02-hdMiniMax-otherNot stated------Not comparable
minimax-tts-speech-02-turboMiniMax-otherNot stated------Not comparable
minimax-tts-speech-2.5-hd-previewMiniMax-otherNot stated------Not comparable
minimax-tts-speech-2.5-turbo-previewMiniMax-otherNot stated------Not comparable
minimax-tts-speech-2.6-hdMiniMax-otherNot stated------Not comparable
minimax-tts-speech-2.6-turboMiniMax-otherNot stated------Not comparable
minimax-tts-speech-2.8-hdMiniMax-otherNot stated------Not comparable
minimax-tts-speech-2.8-turboMiniMax-otherNot stated------Not comparable
mistral-7bMistral AI-UnknownOpen7B-----Not comparable
mistral-large-2402Mistral AI-textOpen123B-----Not comparable
mistral-large2Mistral AI-multimodalOpen123B----Not comparable
mistral-medium-2508Mistral AI-multimodalOpen128B----Not comparable
mistral-medium-3.5-128bMistral AI-multimodalNot stated-----Not comparable
mistral-small-2503Mistral AI-multimodalOpen24B----Not comparable
NanobananaNot stated-image_generationNot stated------Not comparable
nemotron-nano-v2-12bNVIDIA-multimodalOpen12B-----Not comparable
nvidia-nemotron-3-nano-omniNVIDIA-textOpen30B-----Not comparable
openai-gpt-5.4-long-contextOpenAI-UnknownClosed------Not comparable
openai-gpt-5.5-long-contextOpenAI-UnknownClosed------Not comparable
pixtral-12b-2409Not stated-multimodalOpen12B-----Not comparable
pixtral-largeMistral AI-UnknownOpen124B-----Not comparable
pixtral-large-2502Mistral AI-multimodalOpen124B-----Not comparable
pixverse-v5-i2vPixVerse-video_generationNot stated------Not comparable
pixverse-v5-t2vPixVerse-video_generationNot stated------Not comparable
pixverse-v5-transitionPixVerse-video_generationNot stated------Not comparable
pixverse-v5.5-i2vPixVerse-video_generationNot stated------Not comparable
pixverse-v5.5-t2vPixVerse-video_generationNot stated------Not comparable
pixverse-v5.5-transitionPixVerse-video_generationNot stated------Not comparable
pixverse-v5.6-i2vPixVerse-video_generationNot stated------Not comparable
pixverse-v5.6-t2vPixVerse-video_generationNot stated------Not comparable
pixverse-v5.6-transitionPixVerse-video_generationNot stated------Not comparable
pixverse-v6-extendPixVerse-video_generationNot stated------Not comparable
pixverse-v6-i2vPixVerse-video_generationNot stated------Not comparable
pixverse-v6-t2vPixVerse-video_generationNot stated------Not comparable
pixverse-v6-transitionPixVerse-video_generationNot stated------Not comparable
PrismML Ternary Bonsai 27BPrismML-UnknownOpen27B-----Not comparable
Qwen 3.5 122BAlibaba-multimodalOpen122B----Not comparable
Qwen 3.5 122B (Priority)Alibaba-UnknownOpen122B-----Not comparable
Qwen-Image-2512Alibaba-image_generationNot stated------Not comparable
qwen3-embedding-4bNot stated-textNot stated------Not comparable
qwen3-embedding-8bNot stated-textNot stated------Not comparable
qwen3guard-gen-0.6bAlibaba-textOpen600M----Not comparable
qwen3guard-gen-8bAlibaba-textOpen8B----Not comparable
Realtime-tts-1.5-maxInworld-otherNot stated------Not comparable
Realtime-tts-1.5-miniInworld-otherNot stated------Not comparable
Realtime-tts-2Inworld-otherNot stated------Not comparable
Recraft V2Recraft-image_generationNot stated-----Not comparable
Recraft V3Recraft-image_generationNot stated-----Not comparable
Recraft V4Recraft-image_generationNot stated-----Not comparable
Recraft V4 ProRecraft-image_generationNot stated-----Not comparable
Recraft V4.1Recraft-image_generationNot stated-----Not comparable
Recraft V4.1 ProRecraft-image_generationNot stated-----Not comparable
Recraft V4.1 UtilityRecraft-image_generationNot stated-----Not comparable
Recraft V4.1 Utility ProRecraft-image_generationNot stated-----Not comparable
Resemble TTS (English)Not stated-UnknownNot stated------Not comparable
reve-2-1Reve AI-image_generationNot stated------Not comparable
seedance-1-0-pro-250528ByteDance-video_generationNot stated------Not comparable
seedance-1-0-pro-fast-251015ByteDance-video_generationNot stated------Not comparable
seedance-1-5-pro-251215ByteDance-video_generationNot stated------Not comparable
seedance-2-0-260128ByteDance-video_generationNot stated------Not comparable
seedance-2-0-260128-upscaleByteDance-video_generationNot stated------Not comparable
seedance-2-0-fast-260128ByteDance-video_generationNot stated------Not comparable
seedance-2-5-260628BytePlus-video_generationNot stated------Not comparable
seededit-3-0-i2i-250628BytePlus-image_generationNot stated------Not comparable
Seedream V4Not stated-UnknownNot stated------Not comparable
seedream-3-0-t2i-250415BytePlus-image_generationNot stated------Not comparable
seedream-4-0-250828BytePlus-image_generationNot stated------Not comparable
seedream-5.0-liteBytePlus-image_generationNot stated-----Not comparable
seedream-5.0-proByteDance-image_generationNot stated-----Not comparable
skyreels-v4-image-to-videoSkywork-video_generationNot stated------Not comparable
skyreels-v4-omniSkywork-video_generationNot stated------Not comparable
skyreels-v4-text-to-videoSkywork-video_generationNot stated------Not comparable
Step-Audio-EditXStep-otherNot stated------Not comparable
TwelveLabs Pegasus 1.2Not stated-UnknownNot stated------Not comparable
veo-3.1-fast-generate-001VertexAI-video_generationNot stated------Not comparable
veo-3.1-fast-generate-previewVertexAI-video_generationNot stated-----Not comparable
veo-3.1-generate-001VertexAI-video_generationNot stated------Not comparable
veo-3.1-generate-previewVertexAI-video_generationNot stated-----Not comparable
veo-3.1-lite-generate-001VertexAI-video_generationNot stated------Not comparable
vidu-q2-pro-flfvVidu-video_generationNot stated------Not comparable
vidu-q2-pro-i2vVidu-video_generationNot stated------Not comparable
vidu-q2-t2vVidu-video_generationNot stated------Not comparable
vidu-q3-pro-i2vVidu-video_generationNot stated------Not comparable
vidu-q3-pro-t2vVidu-video_generationNot stated------Not comparable
voxtral-small-2507Not stated-multimodalOpen24B-----Not comparable
Voyage Rerank 2.5Voyage AI-textNot stated-----Not comparable
Voyage Rerank 2.5 LiteVoyage AI-textNot stated-----Not comparable
Wan-AI_Wan2.1-FLF2V-14B-720PWan-video_generationNot stated------Not comparable
Wan-AI_Wan2.1-I2V-14B-480PWan-video_generationNot stated------Not comparable
Wan-AI_Wan2.1-I2V-14B-720PWan-video_generationNot stated------Not comparable
Wan-AI_Wan2.1-T2V-14BWan-video_generationNot stated------Not comparable
Wan-AI_Wan2.2-I2V-A14BWan-video_generationNot stated------Not comparable
Wan-AI_Wan2.2-T2V-A14BWan-video_generationNot stated------Not comparable
Wan2.2-Animate-14BWan2.2-video_generationNot stated------Not comparable
Wan2.2-I2V-A14BNot stated-UnknownNot stated------Not comparable
Wan2.2-T2V-A14BNot stated-video_generationNot stated------Not comparable
wan2.5-i2v-previewAliyun-video_generationNot stated------Not comparable
wan2.6-i2vAliyun-video_generationNot stated------Not comparable
wan2.6-r2vAliyun-video_generationNot stated------Not comparable
wan2.6-t2vAliyun-video_generationNot stated------Not comparable
wan2.7-i2vAliyun-video_generationNot stated------Not comparable
wan2.7-imageAliyun-image_generationNot stated-----Not comparable
wan2.7-image-proAliyun-image_generationNot stated-----Not comparable
wan2.7-r2vAliyun-video_generationNot stated------Not comparable
wan2.7-t2vAliyun-video_generationNot stated------Not comparable
wan2.7-videoeditAliyun-video_generationNot stated------Not comparable
wan3.0-videoAliyun-video_generationNot stated------Not comparable
Z-ImageZ-image_generationNot stated------Not comparable
Z-Image-TurboZ-image_generationNot stated------Not comparable
Z-Image-Turbo-Fun-Controlnet-Union-2.1Z-image_generationNot stated------Not comparable

METHODOLOGY

How SuperBased measures what you actually spend

List-price planning cannot reveal real fan-out, retries, cache misses, routing, or tool use. SuperBased Observer measures those behaviors inside actual AI application and coding-agent sessions.

How SuperBased tracks cost →