modelbenchmark.io

Dollars per million tokens

AI model pricing comparison

Input, output and cache-read in US dollars per million tokens. Blended is a 3:1 input mix. It is not a billed rate. Cost a workload or see what prompt caching saves.

Price
View

2,274 models

Active Speaker DetectionNVIDIAfreefreefree0
Agentic Chat (Claude Fable 5.1)freefreefreefree1M
Agentic Chat (Claude Fable 5)freefreefreefree1M
Agentic Chat (Claude Haiku 4.5)freefreefreefree200K
Agentic Chat (Claude Opus 4.5)freefreefreefree200K
Agentic Chat (Claude Opus 4.6)freefreefreefree1M
Agentic Chat (Claude Opus 4.7)freefreefreefree1M
Agentic Chat (Claude Opus 4.8)freefreefreefree1M
Agentic Chat (Claude Opus 5)freefreefreefree1M
Agentic Chat (Claude Sonnet 4.5)freefreefreefree200K
Agentic Chat (Claude Sonnet 4.6)freefreefreefree1M
Agentic Chat (Claude Sonnet 5)freefreefreefree1M
Agentic Chat (GPT-5 Codex)freefreefree400K
Agentic Chat (GPT-5 Mini)freefreefree400K
Agentic Chat (GPT-5.1)freefreefree400K
Agentic Chat (GPT-5.2 Codex)freefreefree400K
Agentic Chat (GPT-5.2)freefreefree400K
Agentic Chat (GPT-5.3 Codex)freefreefree400K
Agentic Chat (GPT-5.4 Mini)freefreefree400K
Agentic Chat (GPT-5.4 Nano)freefreefree400K
Agentic Chat (GPT-5.4)freefreefree1.1M
Agentic Chat (GPT-5.5)freefreefree1.1M
Agentic Chat (GPT-5.6 Luna)freefreefreefree1.1M
Agentic Chat (GPT-5.6 Sol)freefreefreefree1.1M
Agentic Chat (GPT-5.6 Terra)freefreefreefree1.1M
Agentic Chat (GPT-6 Astra)freefreefreefree1.1M
Agents-A1freefreefree262K
Agnes 2.0 Flashfreefreefree512K
Agnes 2.5 Flashfreefreefree512K
ai-defaultfreefreefree
alia-40b-instruct-q8-0freefreefree8K
All-MiniLM-L12-v2freefreefree128
ALLaM-2-7bfreefreefree4K
Atria Dawn Preview (Atria)freefreefree262K
bevformerNVIDIAfreefreefree128K
Big Picklefreefreefreefree200K
Body Builder (beta)freefreefree128K
Brick v1 Betafreefreefree100K
Cerebras-Llama-4-Scout-17B-16E-InstructMetafreefreefree128K
Claude Sonnet 5 (Free)Anthropicfreefreefreefree1M
claude-mythosAnthropicfreefree$1.00free1M
codegeex4freefreefree33K
codegemmafreefreefree8K
codellamafreefreefree4K
Coding GLM 5.1 (free)freefreefree200K
Coding MiniMax M2.7 (Free)freefreefree205K
Cohere: North Mini Code (free)Coherefreefreefree256K
Cosmos Reason2 8BNVIDIAfreefreefree131K
cosmos-predict1-5bNVIDIAfreefreefree0
cosmos-transfer1-7bNVIDIAfreefreefree0
cosmos-transfer2.5-2bNVIDIAfreefreefree0
DeepSeek OCR 2DeepSeekfreefree$0.0924free4K
DeepSeek R1 Distill Llama 8BDeepSeekfreefreefree33K
DeepSeek R1 Distill Qwen 1.5BDeepSeekfreefreefree33K
DeepSeek V4 Flashfreefreefreefree1M
DeepSeek V4 Flash (free)DeepSeekfreefreefreefree1M
DeepSeek V4 Profreefreefreefree1M
deepseek-ai/DeepSeek-OCRDeepSeekfreefreefree8K
deepseek-coder-v2-baseDeepSeekfreefreefree8K
deepseek-coder-v2-lite-baseDeepSeekfreefreefree8K
deepseek-coder-v2-lite-instructDeepSeekfreefreefree33K
Deepseek/DeepSeek-V3.2DeepSeekfreefreefree128K
Devstral Small 2Mistralfreefreefree256K
Devstral-2-123B-Instruct-2512-int4-AutoRoundMistralfreefreefree128K
Dots Studio: Dots3-Note Preview (free)freefreefree512K
dracarys-llama-3.1-70b-instructfreefreefree128K
esm2-650mMetafreefreefree128K
esmfoldMetafreefreefree128K
Gemma 2 2b ItGooglefreefreefree128K
Gemma 3 27BGooglefreefreefree128K
Gemma 3n E2b ItGooglefreefreefree128K
Gemma 3n E4b ItGooglefreefreefree128K
Gemma 4 31B IT (free)Googlefreefree$0.05free262K
Gemma 4 31B IT FP8Googlefreefreefree262K
Gemma 4 E4B Instruct (IQ4_XS)Googlefreefreefree33K
Gemma 4 E4B Instruct (MLX 4-bit)Googlefreefreefree33K
gemma-2b-it-loraGooglefreefreefree8K
gemma-3-4b-it-ggufGooglefreefreefree128K
gemma-7b-it-loraGooglefreefreefree4K
gigachat-2freefreefree128K
gigachat-2-maxfreefreefree128K
gigachat-2-profreefreefree128K
gliner-piiNVIDIAfreefreefree128K
GLM 4.6V Flash (Free)Zhipufreefreefree200K
GLM 4.7 Flash (Free)Zhipufreefreefree200K
GLM 5.2freefreefreefree406K
GLM 5.2 (Free)Zhipufreefreefreefree1M
glm-4-7-251222Zhipufreefreefree205K
GLM-4.5-FlashZhipufreefreefreefree131K
GLM-4.7 FreeZhipufreefreefreefree205K
GLM-5 FreeZhipufreefreefreefree205K
GLM-5.2 HighspeedZhipufreefreefreefree1M
GLM-5.3freefreefree1M
GLM-5.3 (free)Zhipufreefreefree1M
GLM-5.3 HighspeedZhipufreefreefreefree1M
GLM-5.3-Flashfreefreefree1M
GLM-5.3-Flash (free)Zhipufreefreefree1M
GPT-5.3-Codex-SparkOpenAIfreefree$0.175free128K
GPT-Image-2OpenAIfreefree$1.2626free272K
gpt-oss-120b-mxfp-ggufOpenAIfreefreefree131K
gpt-oss-20b-mxfp4-ggufOpenAIfreefreefree131K
Grok Code Fast 1xAIfreefreefreefree256K
Grok Imagine Image 2.0xAIfreefreefree8K
Groq-Llama-4-Maverick-17B-128E-InstructMetafreefreefree128K
HappyHorse 1.1 Image-to-Videofreefreefree0
HappyHorse 1.1 Reference-to-Videofreefreefree0
HappyHorse 1.1 Text-to-Videofreefreefree0
Hunyuan-T1Tencentfreefreefreefree131K
Hunyuan-TurboSTencentfreefreefreefree131K
Hy3 (free)freefreefreefree256K
Hy3 preview Freefreefreefreefree256K
internlm2-5-20b-chatfreefreefree33K
Kimi For Coding HighSpeedKimifreefreefreefree262K
Kimi K2Kimifreefree$0.40free128K
Kimi K2.5 FreeKimifreefreefreefree262K
Kimi K2.7 Codefreefreefreefree262K
Kimi K2.7 Code (Free)Kimifreefreefreefree262K
Kimi K3freefreefreefree1M
Kimi K3freefreefreefree1M
Kimi K3 (Free)Kimifreefreefreefree1M
Kimi K3-256Kfreefreefreefree262K
kimi-for-codingKimifreefreefreefree1M
kimi-k2-thinking-251104Kimifreefreefree229K
Kimi-K2.5-FWKimifreefreefree262K
labs-leanstral-1-5Mistralfreefreefree262K
labs-leanstral-1-5-1Mistralfreefreefree262K
Laguna M.1freefreefreefree262K
Laguna S 2.1 Freefreefreefreefree256K
Laguna XS 2.1freefreefreefree262K
Laguna XS.2freefreefree33K
leanstral-1-5freefreefree262K
leanstral-1-5@eufreefreefree262K
learnlm-1-5-proGooglefreefreefree33K
Ling 2.6 Flash FreeInclusionAIfreefreefree262K
Ling 3.0 Flash FinInclusionAIfreefree$0.012free256K
Ling 3.0 Flash Fin (Free)InclusionAIfreefreefreefree256K
Ling 3.0 Flash SanteInclusionAIfreefreefree256K
Ling 3.0 Flash Sante (Free)InclusionAIfreefreefree256K
Ling 3.0 Flash VL (Free)InclusionAIfreefreefree256K
Ling-3.0-flash FreeInclusionAIfreefreefreefree262K
ling-3.0-tinyInclusionAIfreefreefree262K
Ling-3.0-tiny FreeInclusionAIfreefreefree262K
Llama 3.1 Nemotron 70B InstructNVIDIAfreefreefree128K
Llama 3.1 Nemotron Nano 8B v1NVIDIAfreefreefree131K
Llama 3.1 Nemotron Nano VL 8B v1NVIDIAfreefreefree33K
Llama 3.1 Nemotron Ultra 253BNVIDIAfreefreefree128K
Llama 3.2 11b Vision InstructMetafreefreefree128K
llama-2-7b-chat-hf-loraMetafreefreefree8K
llama-3-1-70b-instruct-maasMetafreefreefree128K
llama-3-1-8b-instruct-maasMetafreefreefree128K
llama-3-2-90b-vision-instruct-maasMetafreefreefree128K
llama-3-3-70b-instruct-turbo-freeMetafreefreefree
Llama-3.2-90B-Vision-InstructMetafreefree$0.175free128K
Llama-3.3-70B-InstructMetafreefreefree128K
Llama-3.3-70B-Instructfreefreefree128K
Llama-3.3-8B-InstructMetafreefreefree128K
Llama-4-Scout-17B-16E-Instruct-FP8Metafreefreefree128K
llama2freefreefree4K
llama2-uncensoredfreefreefree4K
llama3freefreefree8K
llama3-1freefreefree8K
llama3-405b-instruct-maasfreefreefree32K
llama3-70b-instruct-maasfreefreefree32K
llama3-8b-instruct-maasfreefreefree32K
LongCat-2.0 Freefreefreefreefree1M
Lynkr Auto (complexity routing)freefreefree128K
Lyria 3 Clip PreviewGooglefreefreefree1M
Lyria 3 Pro PreviewGooglefreefreefree1M
lyria-3-5Googlefreefreefree1M
lyria-3-5-clipGooglefreefreefree131K
lyria-3-5-proGooglefreefreefree131K
Meta Llama 3.1 8B Instruct (GGUF)Metafreefreefree131K
meta-textgeneration-llama-2-13bfreefreefree4K
meta-textgeneration-llama-2-13b-ffreefreefree4K
meta-textgeneration-llama-2-70bfreefreefree4K
meta-textgeneration-llama-2-70b-b-ffreefreefree4K
meta-textgeneration-llama-2-7bfreefreefree4K
meta-textgeneration-llama-2-7b-ffreefreefree4K
MiMo V2 Flash Freefreefreefreefree262K
MiMo V2 Omni Freefreefreefreefree262K
MiMo V2 Pro Freefreefreefreefree1M
MiMo V2.5 Freefreefreefreefree200K
MiMo-V2-Profreefreefreefree1M
MiMo-V2.5-Profreefreefreefree1M
mimo-v25freefreefree1M
MiniMax-M2.1 FreeMiniMaxfreefreefreefree205K
MiniMax-M2.5 FreeMiniMaxfreefreefreefree205K
MiniMax-M3 FreeMiniMaxfreefreefreefree200K
mistralMistralfreefreefree8K
Mistral Medium 3Mistralfreefreefree131K
mistral-7b-instruct-v0-2-loraMistralfreefreefree15K
mistral-nemotronMistralfreefreefree128K
Mistral: Mixtral 8x7B InstructMistralfreefree$0.50free33K
Muse Spark 1.2 Freefreefreefreefree1M
Muse Spark 1.3 Freefreefreefreefree1M
NanoGPT Helpfreefreefree6K
Nemotron 3 Nano Omni 30B A3B ReasoningNVIDIAfreefreefree131K
Nemotron 3 Super FreeNVIDIAfreefreefreefree205K
Nemotron 3 Ultra (free)NVIDIAfreefree$0.25free1M
Nemotron 3 Ultra FreeNVIDIAfreefreefreefree1M
Nemotron 3.5 Content SafetyNVIDIAfreefreefree131K
Nemotron 3.5 Lightning FreeNVIDIAfreefreefreefree262K
nemotron-3-content-safetyNVIDIAfreefreefree128K
nemotron-3.5-lightning-30b-a3bNVIDIAfreefree$0.0011free1M
nemotron-content-safety-reasoning-4bNVIDIAfreefreefree128K
nemotron-mini-4b-instructNVIDIAfreefreefree128K
nemotron-voicechatNVIDIAfreefreefree128K
Nex AGI: Nex-N2.5-Mini (free)freefreefree262K
Nex AGI: Nex-N2.5-Pro (free)freefreefree262K
North Mini CodeCoherefreefreefree256K
North Mini Code Freefreefreefree256K
Nova 2 LiteAmazonfreefreefree1M
Nova 2 ProAmazonfreefreefree1M
nvidia-nemotron-nano-9b-v2NVIDIAfreefreefree131K
olmo-3-32b-thinkAi2freefreefree33K
olmo-3-7b-instructAi2freefreefree33K
olmo-3-7b-thinkAi2freefreefree33K
orca-miniMicrosoftfreefreefree4K
Ornith-1.0-35B-FP8freefreefree262K
Ox Alpha Free (Unlimited)freefreefreefree1M
Ox Alpha Free (Unlimited)freefreefreefree1M
PaddlePaddle/PaddleOCR-VL-1.5freefreefree16K
paligemmaGooglefreefreefree128K
Pareto Code Routerfreefreefree200K
pplx-70b-onlinePerplexityfree$2.80$0.704K
pplx-7b-onlinePerplexityfree$0.28$0.074K
Qwen 3.5 9B (MLX 4-bit)Alibabafreefreefree33K
Qwen 3.5 9B (Q4_K_M)Alibabafreefreefree33K
Qwen Image 2.0Alibabafreefreefree8K
Qwen Image 2.0 ProAlibabafreefreefree8K
Qwen Image EditAlibabafreefreefree0
qwen-sea-lion-v4-32b-itAlibabafreefreefree33K
Qwen3 Coder 30BAlibabafreefreefree262K
Qwen3 Coder Next FP8Alibabafreefreefree256K
Qwen3-235B-A22BAlibabafreefreefree128K
qwen3-4b-instruct-2507-ggufAlibabafreefreefree262K
qwen3-coder-30b-a3b-instruct-ggufAlibabafreefreefree262K
Qwen3-Coder-Next-FP8-no-thinkingAlibabafreefreefree260K
Qwen3-VL-PlusAlibabafreefree$0.04free256K
Qwen3.6 27BAlibabafreefreefree262K
Qwen3.6 27B FP8Alibabafreefreefreefree262K
Qwen3.6 35B A3Bfreefreefreefree262K
Qwen3.6 35B A3B FP8Alibabafreefree$0.056free262K
Qwen3.6 Plus FreeAlibabafreefreefreefree262K
Qwen3.6-35B-A3B-fp8-no-thinkingAlibabafreefreefree262K
Ring 2.6 1T FreeInclusionAIfreefreefree262K
riva-translate-4b-instruct-v1_1NVIDIAfreefreefree128K
salamandra-7b-instruct-tools-16kfreefreefree16K
sarvam-mfreefreefreefree128K
SenseNova 6.8 Flash Litefreefreefreefree262K
solar-10.7b-instructfreefreefree128K
sonar-medium-onlinePerplexityfree$1.80$0.4512K
sonar-small-onlinePerplexityfree$0.28$0.0712K
sparsedriveNVIDIAfreefreefree128K
Standard Computefreefreefree1M
Step 3.7 Flash (Free)freefreefree256K
streampetrNVIDIAfreefreefree128K
studiovoiceNVIDIAfreefreefree128K
synthetic-video-detectorNVIDIAfreefreefree0
Tencent HY 2.0 InstructTencentfreefreefreefree131K
Tencent HY 2.0 ThinkTencentfreefreefreefree131K
ternary-bonsai-27bfreefreefree262K
Trinity Large Previewfreefreefree131K
Umans Coderfreefreefreefree262K
Umans Flashfreefreefreefree262K
usdcodeNVIDIAfreefreefree128K
usdvalidateNVIDIAfreefreefree0
vicunafreefreefree2K
Wan2.7 Imagefreefreefree8K
Wan2.7 Image Profreefreefree8K
Xiaomi MiMo-V2.5 (free)freefreefreefree1M
Xiaomi MiMo-V2.5-Pro (free)freefreefreefree1M
ZDevfreefreefree1M
Green S$0.0044free$0.00330
Green S Pro$0.0044free$0.00330
Voxtral Mini 3BMistral$0.0046free$0.003432K
All-MiniLM-L6-v2$0.009free$0.0067256
Multi-QA-mpnet-base-dot-v1$0.009free$0.00671K
Google Gemma 2$0.01$0.03$0.0158K
qwen2-5-coder-3b-instructAlibaba$0.01$0.03$0.01533K
qwen2-5-coder-7bAlibaba$0.01$0.03$0.01533K
llama3-2-11b-vision-instruct$0.015$0.025$0.0175131K
nemotron-3-superNVIDIA$0.015$0.60$0.015$0.1613262K
IBM: Granite 4.0 MicroIBM$0.017$0.112$0.0408131K
BGE M3$0.02free$0.0158K
E5 Large v2$0.02free$0.0151K
E5 Mistral 7B$0.02$0.02$0.024K
Gemma 4 E2B InstructGoogle$0.02$0.10$0.01$0.04131K
Llama 3.1 8B (decentralized)Meta$0.02$0.03$0.01$0.0225128K
Llama 3.1 8B InstructMeta$0.02$0.05$0.15$0.0275128K
Manta Flash 1.0$0.02$0.16$0.01$0.05516K
Manta Mini 1.0$0.02$0.16$0.01$0.0558K
Meta Llama 3.1 8B Instruct TurboMeta$0.02$0.03$0.0225128K
meta-llama-3-1-8b-instruct-turboMeta$0.02$0.04$0.025131K
PaddleOCR-VL$0.02$0.02$0.0216K
qwen2-1-5b-instructAlibaba$0.02$0.02$0.02
qwen2-vl-7b-instructAlibaba$0.02$0.06$0.03131K
Sarvam 30B$0.02$0.10$0.04128K
voyage-3.5-lite$0.02free$0.0158K
voyage-4-lite$0.02free$0.01532K
Seed 1.6 Flash$0.0223$0.2226$0.0044$0.0724256K
Mistral Nemo Instruct 2407 TEEMistral$0.0245$0.0978$0.0024$0.0428131K
Nemotron 3 Nano Omni 30B TEENVIDIA$0.0245$0.0978$0.0024$0.0428131K
hermes3-8b$0.025$0.04$0.0288131K
lfm-7b$0.025$0.04$0.0288131K
amazon--nova-micro$0.03$0.10$0.0475128K
Doubao Seed 2.0 Mini 260428$0.03$0.28$0.0056$0.0925256K
Doubao-Seed 1.6 Flash$0.03$0.22$0.0043$0.0775256K
gemma-4-26bGoogle$0.03$0.165$0.0638131K
gemma3-4b$0.03$0.08$0.0425128K
granite-3-3-8b-instructIBM$0.03$0.25$0.0858K
LFM2 24B A2B$0.03$0.12$0.03$0.052533K
Qwen2.5 Coder 7B fastAlibaba$0.03$0.09$0.04532K
Qwen3 4BAlibaba$0.03$0.03$0.03128K
Qwen3.7 Flash ThinkingAlibaba$0.03$0.13$0.006$0.055984K
Schematron V2 Turbo$0.03$0.15$0.015$0.06128K
Solar Pro 4$0.03$0.12$0.006$0.0525524K
Llama 3.2 3b InstructMeta$0.0306$0.0493$0.0153$0.0353131K
Qwen3-ASR FlashAlibaba$0.032$0.032$0.03253K
AutoGLM-Phone-9B-Multilingual$0.035$0.138$0.060866K
Nova MicroAmazon$0.035$0.14$0.0088$0.0613128K
Qwen3 8BAlibaba$0.035$0.138$0.0608128K
Doubao Seed 1.6 Flash$0.0374$0.374$0.0187$0.1216256K
Command R7BCohere$0.0375$0.15$0.0656128K
Command R7B ArabicCohere$0.0375$0.15$0.0656128K
Mistral Nemo 12B InstructMistral$0.038$0.10$0.053516K
Gemma 3 4B IT (Amazon Bedrock, US)Amazon$0.04$0.08$0.05128K
Gemma 4 E2B ITGoogle$0.04$0.08$0.05131K
Gemma 4 E4B InstructGoogle$0.04$0.20$0.02$0.08131K
GLM-4.6V FlashX (Z AI)Zhipu$0.04$0.40$0.004$0.13128K
gpt-oss-20bOpenAI$0.04$0.15$0.02$0.0675128K
l3-8b-lunaris-v1-turbo$0.04$0.05$0.04258K
Llama 3 8B InstructMeta$0.04$0.04$0.048K
Mercury 2.5 Preview$0.04$0.15$0.004$0.0675260K
meta-llama-3-2-1b-instructMeta$0.04$0.08$0.0516K
Mistral NemoMistral$0.04$0.17$0.072560K
nova-micro-v1Amazon$0.04$0.159$0.0698128K
Sao10K: Llama 3 8B Lunaris$0.04$0.05$0.04258K
Voxtral Mini 3B 2507 (Amazon Bedrock, US)Amazon$0.04$0.04$0.04128K
Tencent Hy-MT2-LiteTencent$0.044$0.177$0.07728K
Tencent: Hy-MT2-1.8BTencent$0.044$0.177$0.07728K
Trinity Mini$0.045$0.15$0.0713131K
Doubao Seed 2.0 Mini$0.0493$0.4845$0.0246$0.1581256K
Agnes 3.0 Flash$0.05$0.15$0.005$0.075524K
Gemma 4 12B InstructGoogle$0.05$0.25$0.025$0.10262K
Gemma 4 12B SemancerGoogle$0.05$0.25$0.025$0.10131K
Gemma 4 12B StationKeeperGoogle$0.05$0.25$0.025$0.10131K
Gemma 4 26B-A4BGoogle$0.05$0.29$0.025$0.11262K
GPT 5 NanoOpenAI$0.05$0.40$0.005$0.1375400K
Granite 4.1 8BIBM$0.05$0.10$0.05$0.0625131K
l3-8b-stheno$0.05$0.05$0.058K
Llama 3.1 8BMeta$0.05$0.08$0.0575131K
llama-2-7bMeta$0.05$0.25$0.104K
llama-2-7b-chatMeta$0.05$0.25$0.104K
llama-3-8bMeta$0.05$0.25$0.108K
Mellum2 12B A2.5B$0.05$0.10$0.05$0.0625131K
mistral-7b-v0-1Mistral$0.05$0.25$0.104K
Nemotron 3 Nano 30B A3BNVIDIA$0.05$0.20$0.05$0.0875262K
nemotron-lightning-3.5-30b-a3bNVIDIA$0.05$0.20$0.01$0.0875262K
Nvidia Nemotron 3 Super 120B ThinkingNVIDIA$0.05$0.25$0.025$0.10262K
Nvidia Nemotron 3.5 LightningNVIDIA$0.05$0.20$0.01$0.08751M
OpenAI GPT-5 Nano$0.05$0.40$0.005$0.1375400K
OpenAI GPT-oss-20b$0.05$0.45$0.15128K
Qwen 2.5 VL 32B InstructAlibaba$0.05$0.22$0.025$0.092532K
Qwen Flash (Alibaba Cloud)Alibaba$0.05$0.40$0.01$0.13751M
Qwen-TurboAlibaba$0.05$0.2006$0.025$0.08771M
Qwen/Qwen2.5-7B-InstructAlibaba$0.05$0.05$0.0533K
qwen25-coder-32b-instruct$0.05$0.10$0.0625131K
Qwen3 14B InstructAlibaba$0.05$0.22$0.05$0.092533K
Qwen3 VL Flash (Alibaba Cloud)Alibaba$0.05$0.40$0.01$0.1375262K
Qwen3.5 9BAlibaba$0.05$0.15$0.025$0.075256K
Sao10k L3 8B Lunaris $0.05$0.05$0.058K
Schematron V2 Small$0.05$0.23$0.025$0.095128K
Gemini 2.0 Flash LiteGoogle$0.052$0.21$0.0187$0.09151M
Sarvam 105B$0.054$0.2124$0.0336$0.0936131K
Llama 3.1 8b InstructMeta$0.0544$0.085$0.0272$0.062131K
GPT-5 Nano (EU)OpenAI$0.055$0.44$0.0055$0.1512200K
OpenAI GPT-oss-120b$0.055$0.385$0.02$0.1375128K
Qwen3-Omni FlashAlibaba$0.058$0.23$0.10166K
Tongyi Intent Detect V3Alibaba$0.058$0.144$0.07958K
Amazon Nova Lite 1.0Amazon$0.0595$0.238$0.0297$0.1041300K
codellama-7b$0.06$0.12$0.07516K
Coding GLM 5.1$0.06$0.22$0.013$0.10200K
DeepSeek R1 0528 Qwen3 8BDeepSeek$0.06$0.09$0.0675128K
deepseek-coder-6-7bDeepSeek$0.06$0.12$0.07516K
Doubao Seed 2.0 Mini$0.06$0.56$0.02$0.185256K
fw-nemotron-lightning-3-5-30b-a3b$0.06$0.22$0.01$0.10262K
GLM 4.7 Flash$0.06$0.40$0.01$0.145128K
GPT-5.6 LunaOpenAI$0.06$0.37$0.02$0.13751.1M
Ling 3.0 Flash VLInclusionAI$0.06$0.18$0.012$0.09262K
ling-3-0-flash-fastInclusionAI$0.06$0.18$0.012$0.09262K
Manta Pro 1.0$0.06$0.50$0.03$0.1766K
Mistral Devstral Small 2505Mistral$0.06$0.06$0.03$0.0633K
mistral-small-3-2Mistral$0.06$0.18$0.09131K
Nemotron 3 Nano 30B A3B FP8NVIDIA$0.06$0.25$0.10751M
nemotron-3-nano-omni@euNVIDIA$0.06$0.24$0.06$0.105300K
nemotron-3-nano:30bNVIDIA$0.06$0.24$0.1051M
nova-sonicAmazon$0.06$0.24$0.105
NVIDIA Nemotron Nano 3 30BNVIDIA$0.06$0.24$0.105262K
Nvidia Nemotron Nano 9B V2NVIDIA$0.06$0.23$0.1025131K
Qwen3.5 0.8BAlibaba$0.06$0.12$0.03$0.075262K
voyage-3.5$0.06free$0.0458K
voyage-4$0.06free$0.04532K
Granite-4.0-H-SmallIBM$0.0636$0.265$0.114131K
Qwen: Qwen3.5-FlashAlibaba$0.065$0.26$0.11381M
Tencent Hy3$0.066$0.26$0.029$0.1145262K
Deepseek V4 FlashDeepSeek$0.0679$0.168$0.0168$0.09291M
nova-lite-v1Amazon$0.069$0.275$0.1205300K
baichuan-m2-32b$0.07$0.07$0.07131K
ERNIE 4.5 21B A3BBaidu$0.07$0.28$0.1225120K
ERNIE-4.5-21B-A3B-ThinkingBaidu$0.07$0.28$0.1225131K
GLM 4.7 Flash Heretic$0.07$0.40$0.035$0.1525200K
GLM 4.7 Flash OriginalZhipu$0.07$0.40$0.035$0.1525200K
GLM 4.7 Flash ThinkingZhipu$0.07$0.40$0.035$0.1525200K
GLM-4.7 FlashX (Z AI)Zhipu$0.07$0.40$0.01$0.1525200K
GLM-4.7-FlashAmazon$0.07$0.40$0.1525200K
GLM-4.7-Flash (Amazon Bedrock, US)Amazon$0.07$0.40$0.1525200K
GPT OSS 20BOpenAI$0.07$0.25$0.007$0.115131K
GPT OSS 20B (Databricks, EU)OpenAI$0.07$0.30$0.007$0.1275131K
gpt-oss-20bOpenAI$0.07$0.30$0.1275128K
gpt-oss:20bOpenAI$0.07$0.30$0.035$0.1275131K
Greg 1 Mini$0.07$0.15$0.01$0.09229K
Llama 3.2 11B Instruct (Inference.net)Meta$0.07$0.33$0.135128K
mistralai--mistral-small$0.07$0.28$0.1225128K
Nemotron 3.5 LightningNVIDIA$0.07$0.20$0.04$0.1025262K
Phi 4 MultimodalMicrosoft$0.07$0.11$0.035$0.08128K
pplx-7b-chatPerplexity$0.07$0.28$0.12258K
Seed 1.6 Flash (250715) (ByteDance)$0.07$0.30$0.015$0.1275256K
sonar-small-chatPerplexity$0.07$0.28$0.122516K
DeepSeek R1 Distill Qwen 7BDeepSeek$0.072$0.144$0.0933K
gov-nvidia-nemotron-nano-3-30b$0.072$0.288$0.126262K
gov-nvidia-nemotron-nano-9b-v2$0.072$0.276$0.123128K
Hy-MT2 Plus (Tencent Cloud)Tencent$0.074$0.295$0.12928K
Tencent Hy-MT2-ProTencent$0.074$0.295$0.12928K
Tencent: Hy-MT2-30B-A3BTencent$0.074$0.295$0.12928K
Tencent: Hy-MT2-7BTencent$0.074$0.295$0.12928K
ByteDance Seed: Seed 1.6 Flash$0.075$0.30$0.1312262K
gemini-2-0-flash-lite-001Google$0.075$0.30$0.0187$0.13121M
GLM-5.3-FlashZhipu$0.075$0.025$0.015$0.06251M
Ling 3.0 FlashInclusionAI$0.075$0.22$0.015$0.1112262K
NVIDIA Nemotron 3 Nano 30BNVIDIA$0.075$0.30$0.03$0.1312128K
Phi-4-miniMicrosoft$0.075$0.30$0.1312128K
Phi-4-mini-reasoningMicrosoft$0.075$0.30$0.1312128K
Z.ai: GLM Flash LatestZhipu$0.075$0.25$0.015$0.11871M
Coding Xiaomi MiMo-V2.5$0.08$0.40$0.016$0.161M
deepseek-r1-7b-qwenDeepSeek$0.08$0.15$0.0975131K
dolphin3-8b$0.08$0.15$0.0975128K
Doubao Seed 2.0 Lite 260428$0.08$0.51$0.0169$0.1875256K
meta-llama-3-2-3b-instructMeta$0.08$0.16$0.104K
nvidia-nemotron-3-5-lightning$0.08$0.20$0.04$0.11262K
openthinker-7b$0.08$0.15$0.097533K
Phi-4-multimodalMicrosoft$0.08$0.32$0.14128K
Qwen 3 14bAlibaba$0.08$0.24$0.04$0.1241K
Qwen: Qwen3 32BAlibaba$0.08$0.28$0.13131K
qwen3-4bAlibaba$0.08$0.24$0.1233K
Qwen3.5 2BAlibaba$0.08$0.16$0.04$0.10262K
gpt-oss-20b (GovCloud)Amazon$0.084$0.36$0.153128K
Llama 4 ScoutMeta$0.085$0.46$0.0425$0.1788328K
Qwen Doc TurboAlibaba$0.087$0.144$0.1013131K
Qwen2.5-Omni 7BAlibaba$0.087$0.345$0.151533K
Qwen: Qwen3 235B A22B Instruct 2507Alibaba$0.0875$0.35$0.0175$0.1531262K
Gemma 3 12B IT (Amazon Bedrock, US)Amazon$0.09$0.29$0.14128K
gemma-4-31b-it-turboGoogle$0.09$0.34$0.05$0.1525262K
GPT OSS 120BOpenAI$0.09$0.36$0.1575131K
GPT OSS 120B High ThroughputOpenAI$0.09$0.36$0.1575131K
GTE Large (v1.5)$0.09free$0.06758K
Nemotron 3 Super 120B A12BNVIDIA$0.09$0.45$0.09$0.18256K
Qwen3 30B A3BAlibaba$0.09$0.45$0.1841K
DeepSeek V4 Flash FlexDeepSeek$0.091$0.182$0.0182$0.11381M
DeepSeek V4 FlashDeepSeek$0.098$0.196$0.028$0.12251M
Apertus 8B Instruct$0.10$0.20$0.12566K
BGE Multilingual Gemma2$0.10free$0.0758K
ByteDance: UI-TARS 7B $0.10$0.20$0.10$0.125128K
codegemma-2b$0.10$0.10$0.108K
cogito-v1-preview-llama-3b$0.10$0.10$0.10131K
cosmos3-super-reasoner$0.10$0.30$0.15262K
DarkIdolGoogle$0.10$0.45$0.05$0.1875262K
DeepSeek V3/Chat CheaperDeepSeek$0.10$0.425$0.05$0.1813128K
DeepSeek V3/Deepseek ChatDeepSeek$0.10$0.425$0.05$0.1813128K
deepseek-coder-1b-baseDeepSeek$0.10$0.10$0.1016K
deepseek-r1-8bDeepSeek$0.10$0.20$0.12566K
Devstral Small 2Mistral$0.10$0.30$0.10$0.15256K
ernie-4-5-21b-a3b-ptBaidu$0.10$0.10$0.104K
ernie-4-5-300b-a47b-ptBaidu$0.10$0.10$0.104K
FabledGoogle$0.10$0.45$0.05$0.1875262K
GarnetGoogle$0.10$0.45$0.05$0.1875262K
GembrainGoogle$0.10$0.45$0.05$0.1875262K
Gemini 2.0 FlashGoogle$0.10$0.42$0.025$0.181M
Gemini 2.5 Flash LiteGoogle$0.10$0.40$0.01$0.1751M
Gemini 2.5 Flash Lite Preview (09/2025)Google$0.10$0.40$0.01$0.1751M
Gemini 2.5 Flash Lite Preview (09/2025) – ThinkingGoogle$0.10$0.40$0.01$0.1751M
Gemini 2.5 Flash-Lite (EU)Google$0.10$0.40$0.01$0.1751M
gemini-2-0-flash-001Google$0.10$0.40$0.0375$0.1751M
Gemma 4 26B A4B IT$0.10$0.50$0.20256K
Gemma 4 31B MeroMero v2 ThinkingGoogle$0.10$0.45$0.05$0.1875262K
gemma-2b-itGoogle$0.10$0.10$0.108K
GemsicleGoogle$0.10$0.45$0.05$0.1875262K
GLM-4 32B (0414-128k) (Z AI)Zhipu$0.10$0.10$0.10128K
GPT 4.1 NanoOpenAI$0.10$0.40$0.025$0.1751M
GPT OSS 120B$0.10$0.10$0.10$0.10131K
Granite 4.2 8BIBM$0.10$0.15$0.05$0.1125131K
granite-vision-3-2-2bIBM$0.10$0.10$0.108K
Greg (Roleplay)$0.10$0.30$0.02$0.15229K
IsometryGoogle$0.10$0.45$0.05$0.1875262K
Laguna S 2.1 Thinking$0.10$0.20$0.01$0.1251M
lfm-40b$0.10$0.20$0.125131K
LFM2.5 2.6B$0.10$0.20$0.05$0.125128K
Ling-2.6-flashInclusionAI$0.10$0.30$0.02$0.15262K
Llama 3.2 1B InstructMeta$0.10$0.201$0.10$0.1253131K
Llama 3.3 70B TurboMeta$0.10$0.32$0.155131K
llama-2-13bMeta$0.10$0.50$0.204K
llama-2-13b-chatMeta$0.10$0.50$0.204K
Llama-3.1-8B-CSMeta$0.10$0.10$0.10128K
Llama-3.2-1BMeta$0.10$0.10$0.10$0.10131K
Llama-3.2-3BMeta$0.10$0.10$0.10$0.10131K
llama-v2-70bMeta$0.10$0.10$0.104K
llama-v3-1-405b-instruct-longMeta$0.10$0.10$0.104K
llama-v3-1-70b-instruct-1bMeta$0.10$0.10$0.104K
llama-v3-1-8b-instructMeta$0.10$0.10$0.1016K
llama-v3-2-1bMeta$0.10$0.10$0.10131K
llama-v3-2-1b-instructMeta$0.10$0.10$0.1016K
llama-v3-2-3bMeta$0.10$0.10$0.10131K
llama-v3-2-3b-instructMeta$0.10$0.10$0.1016K
llama3-1-8b$0.10$0.10$0.10128K
llava-7b$0.10$0.20$0.1254K
Magibu 11B v8$0.10$0.50$0.208K
Mimo-V2-Flash$0.10$0.30$0.01$0.15256K
Ministral 3 14BMistral$0.10$0.40$0.05$0.175262K
Ministral 3 3BMistral$0.10$0.10$0.10256K
Ministral 3BMistral$0.10$0.10$0.05$0.10131K
ministral-3-3bMistral$0.10$0.10$0.01$0.10131K
Mistral Small 3.1 24B (2503)Mistral$0.10$0.30$0.05$0.15128K
Mistral Small 3.2 (Mistral AI)Mistral$0.10$0.30$0.165$0.15128K
mistral-7b-v0-3Mistral$0.10$0.15$0.112533K
mistral-small-2503-001Mistral$0.10$0.30$0.1532K
Muse Spark 1.2 Contributor (Data Used for Training)Meta$0.10$0.20$0.002$0.1251M
Muse Spark 1.3 ContributorMeta$0.10$0.20$0.002$0.1251M
nemotron-3-ultraNVIDIA$0.10$3.00$0.10$0.825262K
nemotron-nano-v2-12b-vlNVIDIA$0.10$0.10$0.104K
NovelistGoogle$0.10$0.45$0.05$0.1875262K
nvidia-nemotron-3-super-120b-a12bNVIDIA$0.10$0.50$0.15$0.20262K
OpenReasoning Nemotron 32B$0.10$0.40$0.05$0.17533K
Ornith 1.5 35B$0.10$0.40$0.05$0.175262K
Osmosis Structure 0.6B$0.10$0.50$0.204K
phi-2-3bMicrosoft$0.10$0.10$0.102K
qwen-2-1-5b-instructAlibaba$0.10$0.10$0.1033K
Qwen: Qwen2.5 7B InstructAlibaba$0.10$0.20$0.12533K
qwen2-5-0-5b-instructAlibaba$0.10$0.10$0.1033K
qwen2-5-1-5b-instructAlibaba$0.10$0.10$0.1033K
qwen2-5-coder-0-5b-instructAlibaba$0.10$0.10$0.1033K
qwen2-5-coder-1-5bAlibaba$0.10$0.10$0.1033K
qwen2-5-coder-1-5b-instructAlibaba$0.10$0.10$0.1033K
qwen2-5-coder-3bAlibaba$0.10$0.10$0.1033K
qwen2-vl-2b-instructAlibaba$0.10$0.10$0.1033K
Qwen2.5-Coder-0.5BAlibaba$0.10$0.10$0.10$0.1033K
Qwen3 1.7B BaseAlibaba$0.10$0.10$0.10$0.1033K
Qwen3 30B A3BAlibaba$0.10$0.30$0.05$0.1540K
Qwen3 32BAlibaba$0.10$0.30$0.05$0.1540K
Qwen3 32BAlibaba$0.10$0.45$0.187541K
qwen3-0-6bAlibaba$0.10$0.10$0.1041K
qwen3-1-7bAlibaba$0.10$0.10$0.10131K
qwen3-1-7b-fp8-draftAlibaba$0.10$0.10$0.10262K
qwen3-1-7b-fp8-draft-131072Alibaba$0.10$0.10$0.10131K
qwen3-1-7b-fp8-draft-40960Alibaba$0.10$0.10$0.1041K
Qwen3.5 4BAlibaba$0.10$0.20$0.05$0.125262K
Qwen3.5 Flash ThinkingAlibaba$0.10$0.40$0.05$0.175992K
Reka Edge$0.10$0.10$0.1016K
Reka Flash 3$0.10$0.20$0.12566K
Seed 2.0 Mini$0.10$0.40$0.02$0.175256K
Seed 2.0 Mini$0.10$0.40$0.175131K
stablecode-3b$0.10$0.10$0.104K
starcoder2-3b$0.10$0.10$0.1016K
Stepfun/Step-3.5 Flash$0.10$0.30$0.05$0.1564K
TheDrummer/Artemis v1.1$0.10$0.45$0.05$0.1875262K
Trendyol Asure 12B$0.10$0.50$0.025$0.2041K
Voxtral Small (latest)Mistral$0.10$0.30$0.012$0.1532K
Voxtral Small 24B 2507 (Amazon Bedrock, US)Amazon$0.10$0.30$0.15128K
Mistral NemoMistral$0.1003$0.1207$0.0502$0.105416K
MythoMax 13B$0.1003$0.1003$0.0502$0.10034K
Qwen Long 10MAlibaba$0.1003$0.408$0.0502$0.177210M
The Drummer Cydonia 24B v2$0.1003$0.1207$0.0502$0.105433K
The Drummer Magidonia 24B v4.3$0.1003$0.1207$0.0502$0.105433K
Qwen-MT TurboAlibaba$0.101$0.28$0.145816K
Qwen3 32B TEEAlibaba$0.104$0.416$0.0104$0.18241K
Qwen3-VL 30B-A3BAlibaba$0.108$0.431$0.1888131K
GPT-4.1 nano (EU)OpenAI$0.11$0.44$0.0275$0.19251M
Mistral 7B Instruct v0.3Mistral$0.11$0.11$0.1133K
doubao-seed-1-8-251215$0.114$0.286$0.157224K
E5 Multi-Lingual Large Embeddings 0.6B$0.114$0.114$0.1141K
Qwen Plus CharacterAlibaba$0.115$0.287$0.15833K
Qwen-VL PlusAlibaba$0.115$0.287$0.042$0.158131K
Mistral Small 24BMistral$0.1155$0.3465$0.173333K
Qwen: Qwen3 8BAlibaba$0.117$0.455$0.2015131K
Doubao Seed Character$0.1179$0.2947$0.0236$0.1621128K
Seed 1.6$0.1187$1.1875$0.0238$0.3859256K
Seed 1.6 Vision$0.1187$1.1875$0.0238$0.3859256K
Seed 1.8$0.1187$1.1875$0.0238$0.3859256K
Seed Character$0.1187$0.2969$0.0238$0.1633256K
Agnes 1.5 Lite$0.12$0.60$0.24256K
Brick Complexity Pro$0.12$0.46$0.205100K
Chimera XGoogle$0.12$0.38$0.06$0.185262K
Dark SoulGoogle$0.12$0.38$0.06$0.185262K
Doubao-Seed 1.6$0.12$0.29$0.023$0.1625256K
Gemma 4 26B A4BGoogle$0.12$0.38$0.06$0.185262K
Gemma 4 26B A4B MeroMeroGoogle$0.12$0.38$0.06$0.185262K
Gemma 4 26B A4B UncensoredGoogle$0.12$0.38$0.06$0.185262K
gemma 4 31B turbo TEEGoogle$0.12$0.37$0.012$0.1825131K
GLM 4.5 AirZhipu$0.12$0.80$0.06$0.29131K
Google Gemma 3 27B Instruct$0.12$0.20$0.14198K
Google Gemma 4 31B Instruct$0.12$0.36$0.09$0.18256K
hermes3-70b$0.12$0.30$0.165131K
llama3-1-70b-instruct-fp8$0.12$0.30$0.165131K
llama3-1-nemotron-70b-instruct-fp8$0.12$0.30$0.165131K
llama3-3-70b-instruct-fp8$0.12$0.30$0.165131K
Luminous MirrorGoogle$0.12$0.38$0.06$0.185262K
MiniMax M2.1 Lightning (MiniMax)MiniMax$0.12$0.48$0.03$0.21197K
Moonlight DuskGoogle$0.12$0.38$0.06$0.185262K
MusicaGoogle$0.12$0.38$0.06$0.185262K
Opus DistillGoogle$0.12$0.38$0.06$0.185262K
Qwen: Qwen3 14BAlibaba$0.12$0.24$0.15131K
Qwen: Qwen3 30B A3BAlibaba$0.12$0.50$0.215131K
Qwen3-14BAlibaba$0.12$0.24$0.1541K
Qwen3-30B-A3BAlibaba$0.12$0.50$0.21541K
Seed 1.6 Vision$0.12$1.15$0.023$0.3775256K
Seed 1.8$0.12$0.29$0.023$0.1625256K
Shadow SirenGoogle$0.12$0.38$0.06$0.185262K
The Drummer Cydonia 24B v4.3$0.12$0.15$0.06$0.127533K
voyage-4-large$0.12free$0.0932K
voyage-code-2$0.12free$0.098K
voyage-finance-2$0.12free$0.098K
voyage-law-2$0.12free$0.098K
doubao-seed-1-6-thinking-250715$0.121$1.21$0.3932256K
MiniCPM5-2B$0.124$0.7425$0.124$0.2786131K
chat-bison$0.125$0.125$0.1258K
chat-bison-001$0.125$0.125$0.1258K
Phi-4Microsoft$0.125$0.50$0.2188128K
Phi-4-reasoningMicrosoft$0.125$0.50$0.218832K
Phi-4-reasoning-plusMicrosoft$0.125$0.50$0.218832K
text-bison$0.125$0.125$0.1258K
text-bison-001$0.125$0.125$0.1258K
text-bison-safety-off$0.125$0.125$0.1258K
text-bison-safety-recitation-off$0.125$0.125$0.1258K
Doubao Seed 2.0 Lite$0.13$0.76$0.03$0.2875256K
Google Gemma 4 26B A4B Instruct$0.13$0.40$0.05$0.1975256K
hermes-4-70b$0.13$0.40$0.1975131K
llama3-2-1b-instructMeta$0.13$0.13$0.13128K
NVIDIA Nemotron 3 Nano OmniNVIDIA$0.13$0.38$0.1925262K
phi-3-5-mini-instructMicrosoft$0.13$0.52$0.2275128K
phi-3-5-vision-instructMicrosoft$0.13$0.52$0.2275128K
phi-3-mini-128k-instructMicrosoft$0.13$0.52$0.2275128K
phi-3-mini-4k-instructMicrosoft$0.13$0.52$0.22754K
Qwen 3 Coder 480BAlibaba$0.13$0.50$0.065$0.2225262K
qwen2-vl-72b-instructAlibaba$0.13$0.40$0.1975131K
Qwen3 235B A22B Thinking 2507Alibaba$0.13$0.60$0.055$0.2475262K
Doubao 1.5 Pro 32k$0.1343$0.3349$0.0672$0.1845128K
GLM 4 Air 0111Zhipu$0.1394$0.1394$0.0697$0.1394128K
MiniMax 01MiniMax$0.1394$1.122$0.0697$0.38511M
MiniMax M1MiniMax$0.1394$1.3328$0.0697$0.43771M
DeepSeek V4 Flash (Alibaba Cloud)$0.14$0.28$0.028$0.1751M
deepseek-coderDeepSeek$0.14$0.28$0.175128K
DeepSeek-V4-Flash-ELDeepSeek$0.14$0.28$0.1751M
ERNIE 4.5 VL 28B A3BBaidu$0.14$0.56$0.24530K
GPT-4o-mini-SearchOpenAI$0.14$0.54$0.075$0.24128K
Hermes 2 Pro Llama 3 8B$0.14$0.14$0.148K
inclusionAI/Ling-flash-2.0InclusionAI$0.14$0.57$0.2475131K
Meta Llama 3 8B Instruct LiteMeta$0.14$0.14$0.148K
MiMo-V2-Omni$0.14$0.28$0.0028$0.175262K
Qwen 3.8 FlashAlibaba$0.14$0.49$0.014$0.22751M
Qwen3.8 FlashAlibaba$0.14$0.42$0.016$0.21992K
tencent/Hunyuan-A13B-InstructTencent$0.14$0.57$0.2475131K
DeepSeek R1 Distill Qwen 14BDeepSeek$0.144$0.431$0.215733K
Gemma 4 31BGoogle$0.144$0.42$0.0144$0.213262K
Qwen2.5 14B InstructAlibaba$0.144$0.431$0.2157131K
Qwen2.5-Coder 7B InstructAlibaba$0.144$0.287$0.1797131K
Qwen2.5-Math 7B InstructAlibaba$0.144$0.287$0.17974K
Doubao Seed 2.0 Lite$0.1462$0.8738$0.0731$0.3281256K
Command RCohere$0.15$0.60$0.2625128K
DeepSeek: DeepSeek Flash LatestDeepSeek$0.15$0.60$0.015$0.26251M
ERNIE X1.1Baidu$0.15$0.60$0.075$0.262564K
Gemini 2.5 Flash 0520Google$0.15$0.60$0.015$0.26251M
Gemini 2.5 Flash Lite PreviewGoogle$0.15$0.60$0.015$0.26251M
Gemini 2.5 Flash Preview ThinkingGoogle$0.15$3.50$0.015$0.98751M
Gemma 3 12BGoogle$0.15$0.50$0.15$0.2375131K
Gemma 3 4B (Pretrained)Google$0.15$0.15$0.15$0.1533K
gemma-4-26b-a4b-it-maasGoogle$0.15$0.60$0.2625256K
gemma-4-31b-it-thinkingGoogle$0.15$0.40$0.2125262K
gemma-7b-itGoogle$0.15$0.15$0.158K
GLiNER2 Base$0.15$0.15$0.15$0.158K
GLiNER2 Large$0.15$0.15$0.15$0.158K
GLiNER2 Multi$0.15$0.15$0.15$0.158K
GLiNER2 Multi Large$0.15$0.15$0.15$0.158K
GLiNER2 Privacy Filter PII (Multi)$0.15$0.15$0.15$0.158K
GLM 5.3 Flash$0.15$0.50$0.03$0.23751M
GLM 5.3 Flash FP4Zhipu$0.15$0.50free$0.23751M
Google Gemma 3Google$0.15$0.30$0.1875125K
GPT OSS 120B (Databricks, EU)OpenAI$0.15$0.60$0.015$0.2625131K
GPT-4o miniOpenAI$0.15$0.60$0.075$0.2625128K
gpt-oss-120bOpenAI$0.15$0.60$0.2625128K
gpt-oss-120b-turboOpenAI$0.15$0.60$0.2625131K
hermes-3-8b-tee$0.15$0.60$0.262516K
Kat Coder Air V2.5$0.15$0.60$0.03$0.2625256K
Kimi K2 Turbo PreviewKimi$0.15$8.00$0.15$2.1125256K
Llama 4 MaverickMeta$0.15$0.60$0.075$0.26251M
llama-2-7b-chat-hfMeta$0.15$0.15$0.154K
llama4-scout-instruct-basic$0.15$0.60$0.2625131K
meta-llama-3-8b-instructMeta$0.15$0.15$0.158K
Ministral 3 8BMistral$0.15$0.15$0.15262K
Ministral 8BMistral$0.15$0.15$0.075$0.15262K
Ministral 8B InstructMistral$0.15$0.15$0.15$0.15128K
ministral-3-8bMistral$0.15$0.15$0.015$0.15262K
Mistral Small 4Mistral$0.15$0.60$0.15$0.2625256K
mistral-7b-instruct-v0-1Mistral$0.15$0.15$0.1516K
mistral-vibe-cli-fastMistral$0.15$0.60$0.015$0.2625262K
NVIDIA Nemotron 3 Super 120B A12BNVIDIA$0.15$0.65$0.275262K
NVIDIA Nemotron Cascade 2NVIDIA$0.15$0.60$0.2625262K
Nvidia Nemotron Super 49BNVIDIA$0.15$0.15$0.075$0.15128K
Open Mistral NemoMistral$0.15$0.15$0.15128K
OpenAI GPT-4o mini$0.15$0.60$0.075$0.2625128K
Perceptron Mk1$0.15$1.50$0.075$0.487533K
phi-3-small-128k-instructMicrosoft$0.15$0.60$0.2625128K
phi-3-small-8k-instructMicrosoft$0.15$0.60$0.26258K
Pokee-Isaac 28B$0.15$1.00$0.075$0.362510M
Qwen 3 Coder 30B A3B InstructAlibaba$0.15$0.60$0.2625262K
Qwen3 4B BaseAlibaba$0.15$0.15$0.15$0.1533K
Qwen3 Next 80B A3B InstructAlibaba$0.15$0.65$0.075$0.275131K
Qwen3 Next 80B A3B ThinkingAlibaba$0.15$0.65$0.075$0.275131K
qwen3-6-27b-thinkingAlibaba$0.15$0.50$0.2375262K
qwen3-6-35b-a3b-thinkingAlibaba$0.15$0.50$0.2375262K
Qwen3-Next 80B-A3B InstructAlibaba$0.15$1.20$0.4125262K
qwen3-next-80b-a3b-instruct-maasAlibaba$0.15$1.20$0.4125262K
qwen3-next-80b-a3b-thinking-maasAlibaba$0.15$1.20$0.4125262K
qwen3-vl-8bAlibaba$0.15$0.55$0.2533K
Qwen3.8 27BAlibaba$0.15$0.70$0.04$0.2875262K
Rnj-1 Instruct$0.15$0.15$0.1533K
SmolLM3 3B Base$0.15$0.15$0.15$0.1533K
Solar Pro 2$0.15$0.60$0.262566K
Solar Pro 3$0.15$0.60$0.015$0.2625131K
Solar Pro 3$0.15$0.60$0.2625131K
solar-mini$0.15$0.15$0.1533K
zephyr-7b$0.15$0.15$0.1516K
Llama 3.1 8B Instruct fp8Meta$0.152$0.287$0.185732K
DeepSeek V4 Flash (DeepSeek)$0.154$0.308$0.0308$0.19251M
mistral-7b-instruct-v0.2Mistral$0.159$0.219$0.17432K
Agnes 1.5 Pro$0.16$0.80$0.32256K
llama-3-2-11bMeta$0.16$0.16$0.16128K
phi-3-5-moe-instructMicrosoft$0.16$0.64$0.28128K
Qwen 3.32BAlibaba$0.16$0.64$0.28128K
Gemma 4 UncensoredGoogle$0.1625$0.50$0.2469256K
GPT-4o mini (EU)OpenAI$0.165$0.66$0.0825$0.2888128K
Mistral Small 4 (EU)Mistral$0.165$0.66$0.165$0.2888256K
MiMo V2.5 (NovitaAI)$0.168$0.336$0.0034$0.211M
Doubao-Seed-Code$0.17$1.12$0.03$0.4075256K
K2-Think$0.17$0.68$0.085$0.2975128K
Llama 4 Scout 17B Instruct (AWS Bedrock)Meta$0.17$0.66$0.29258K
Llama 4 Scout 17B Instruct (US)Meta$0.17$0.66$0.292510M
Minimax/Minimax-M2MiniMax$0.17$1.53$0.085$0.51200K
Nvidia Nemotron 3 Nano 30BNVIDIA$0.17$0.68$0.085$0.2975262K
Phi 4 MiniMicrosoft$0.17$0.68$0.085$0.2975128K
phi-3-medium-128k-instructMicrosoft$0.17$0.68$0.2975128K
phi-3-medium-4k-instructMicrosoft$0.17$0.68$0.29754K
LightOnOCR 2$0.1785$0.3465$0.220533K
gov-nvidia-nemotron-super-3-120b$0.18$0.78$0.33256K
gpt-oss-120b (GovCloud)Amazon$0.18$0.72$0.315128K
Qwen: Qwen3 VL 8B ThinkingAlibaba$0.18$2.10$0.66131K
Qwen/Qwen3-VL-8B-InstructAlibaba$0.18$0.68$0.305262K
voyage-3-large$0.18free$0.1358K
voyage-code-3$0.18free$0.1358K
llama3-2-3b-instructMeta$0.19$0.19$0.19128K
mamba-codestral-7b-v0-1$0.19$0.19$0.19256K
Qwen3.6 FlashAlibaba$0.19$1.16$0.02$0.4325992K
Step 3.7 Flash$0.19$1.14$0.03$0.4275262K
Llama 3.1 Instruct (8B)Meta$0.198$0.198$0.198131K
Mistral SabaMistral$0.1989$0.595$0.0994$0.297933K
ai-4-1b-8b$0.20$0.20$0.20
ai-4-1b-to-16b$0.20$0.20$0.20
ai-up-to-4b$0.20$0.20$0.20
chronos-hermes-13b$0.20$0.20$0.204K
code-llama-13b$0.20$0.20$0.2016K
code-llama-13b-instruct$0.20$0.20$0.2016K
code-llama-13b-python$0.20$0.20$0.2016K
code-llama-7b$0.20$0.20$0.2016K
code-llama-7b-instruct$0.20$0.20$0.2016K
code-llama-7b-python$0.20$0.20$0.2016K
code-qwen-1-5-7b$0.20$0.20$0.2066K
codegemma-7b$0.20$0.20$0.208K
Coding MiniMax M2.7$0.20$0.20$0.20205K
Coding MiniMax M2.7 Highspeed$0.20$0.20$0.20205K
Coding Xiaomi MiMo-V2.5-Pro$0.20$0.60$0.04$0.301M
cogito-v1-preview-llama-8b$0.20$0.20$0.20131K
cogito-v1-preview-qwen-14b$0.20$0.20$0.20131K
DeepSeek V4 Flash 0731DeepSeek$0.20$0.50$0.10$0.2751M
deepseek-coder-7b-baseDeepSeek$0.20$0.20$0.204K
deepseek-coder-7b-instructDeepSeek$0.20$0.20$0.204K
deepseek-llama3-3-70bDeepSeek$0.20$0.60$0.30131K
deepseek-r1-0528-distill-qwen3-8bDeepSeek$0.20$0.20$0.20131K
DeepSeek-V3DeepSeek$0.20$0.77$0.135$0.3425128K
DeepSeek-V3.1DeepSeek$0.20$0.70$0.10$0.325128K
dobby-mini-unhinged-plus-llama-3-1-8b$0.20$0.20$0.20131K
firellava-13b$0.20$0.20$0.204K
firesearch-ocr$0.20$0.20$0.208K
gemma-2-9bGoogle$0.20$0.20$0.208K
gemma-7bGoogle$0.20$0.20$0.208K
GLM 4 32B 0414Zhipu$0.20$0.20$0.10$0.20128K
GLM 4 9B 0414Zhipu$0.20$0.20$0.10$0.2032K
GLM 4.5 FP8Zhipu$0.20$0.80$0.35131K
GLM 5.3 Flash UncensoredZhipu$0.20$0.80$0.10$0.351M
GLM Z1 9B 0414Zhipu$0.20$0.20$0.10$0.2032K
glm-4-5-air-fp8Zhipu$0.20$1.10$0.425128K
GLM-5.3-Flash (EU)Zhipu$0.20$0.60$0.07$0.301M
GPT 5.4 NanoOpenAI$0.20$1.25$0.02$0.4625400K
GPT 5.6 Luna ProOpenAI$0.20$1.20$0.02$0.451.1M
GPT Luna LatestOpenAI$0.20$1.20$0.02$0.451.1M
GPT-4.1 nano (Fast)OpenAI$0.20$0.80$0.05$0.351M
gpt-oss-120b-ultraOpenAI$0.20$0.95$0.3875131K
granite-3-8b-instructIBM$0.20$0.20$0.208K
hermes-2-pro-mistral-7b$0.20$0.20$0.2033K
internvl3-8b$0.20$0.20$0.2016K
jamba-1-5AI21$0.20$0.40$0.25256K
jamba-1-5-miniAI21$0.20$0.40$0.25256K
jamba-1-5-mini-001AI21$0.20$0.40$0.25256K
jamba-mini-1-6AI21$0.20$0.40$0.25256K
jamba-mini-1-7AI21$0.20$0.40$0.25256K
kimi-latest-8kKimi$0.20$2.00$0.15$0.658K
llama-3-8b-chat-hfMeta$0.20$0.20$0.20
llama-v2-13bMeta$0.20$0.20$0.204K
llama-v2-13b-chatMeta$0.20$0.20$0.204K
llama-v2-7bMeta$0.20$0.20$0.204K
llama-v2-7b-chatMeta$0.20$0.20$0.204K
llama-v3-2-11b-vision-instructMeta$0.20$0.20$0.2016K
llama-v3-8bMeta$0.20$0.20$0.208K
llama-v3-8b-instruct-hfMeta$0.20$0.20$0.208K
MAI-Code-1.1-Flash$0.20$1.20$0.02$0.45256K
MiniMax Text 01 (MiniMax)MiniMax$0.20$1.10$0.4251M
Ministral 14BMistral$0.20$0.20$0.10$0.20262K
Ministral 3 14BMistral$0.20$0.20$0.20262K
ministral-3-14bMistral$0.20$0.20$0.02$0.20262K
Mistral 7B Instruct v0.3Mistral$0.20$0.20$0.20$0.2033K
Mistral Small 4$0.20$0.60$0.30262K
mistral-7bMistral$0.20$0.20$0.2032K
mistral-7b-instruct-4kMistral$0.20$0.20$0.2033K
mistral-nemo-baseMistral$0.20$0.20$0.20128K
moonshot-v1-8kKimi$0.20$2.00$0.658K
moonshot-v1-8k-visionKimi$0.20$2.00$0.658K
nemotron-content-safety-3-5NVIDIA$0.20$0.20$0.20131K
Nemotron-nano 12b v2-vlNVIDIA$0.20$0.60$0.30128K
nous-capybara-7b$0.20$0.20$0.2033K
nous-hermes-llama2-13b$0.20$0.20$0.204K
nous-hermes-llama2-7b$0.20$0.20$0.204K
NVIDIA Nemotron Nano 12B v2 VL BF16NVIDIA$0.20$0.60$0.30128K
nvidia-nemotron-nano-12b$0.20$0.20$0.20131K
Omen Alpha$0.20$0.66$0.04$0.315500K
OpenAI GPT-5.4 Nano$0.20$1.25$0.02$0.4625400K
OpenAI GPT-5.6 Luna$0.20$1.20$0.02$0.451.1M
openchat-3-5-0106-7b$0.20$0.20$0.208K
openhermes-2-5-mistral-7b$0.20$0.20$0.2033K
openhermes-2-mistral-7b$0.20$0.20$0.2033K
openorca-7b$0.20$0.20$0.2033K
phi-3-vision-128k-instructMicrosoft$0.20$0.20$0.2032K
pythia-12b$0.20$0.20$0.202K
Qwen 2.5 7B Vision InstructAlibaba$0.20$0.20$0.20125K
Qwen Omni Turbo (Alibaba Cloud)Alibaba$0.20$0.80$0.3533K
qwen-v2-5-14b-instructAlibaba$0.20$0.20$0.2033K
qwen-v2-5-7bAlibaba$0.20$0.20$0.20131K
Qwen/Qwen3-VL-32B-InstructAlibaba$0.20$0.60$0.30262K
Qwen/Qwen3-VL-32B-ThinkingAlibaba$0.20$1.50$0.525262K
qwen2-5-14bAlibaba$0.20$0.20$0.20131K
qwen2-5-coder-14bAlibaba$0.20$0.20$0.2033K
qwen2-5-coder-14b-instructAlibaba$0.20$0.20$0.2033K
qwen2-5-vl-3b-instructAlibaba$0.20$0.20$0.20128K
qwen2-7b-instructAlibaba$0.20$0.20$0.2033K
Qwen3 235B A22B FP8 (NovitaAI)Alibaba$0.20$0.80$0.3541K
Qwen3 235B A22B Instruct 2507 FP8Alibaba$0.20$0.60$0.30262K
Qwen3 30b A3b Instruct 2507Alibaba$0.20$0.50$0.10$0.275128K
Qwen3 4B InstructAlibaba$0.20$0.20$0.20$0.2033K
Qwen3 Coder 480B A35B InstructAlibaba$0.20$0.80free$0.35262K
Qwen3 Coder NextAlibaba$0.20$1.50$0.10$0.525262K
qwen3-235b-a22b-fp8-tputAlibaba$0.20$0.60$0.3040K
Qwen3.8 Flash NextAlibaba$0.20$0.50$0.05$0.275262K
Qwen3.8 Flash Next (EU)Alibaba$0.20$0.50$0.05$0.275262K
r1v4-lite$0.20$0.60$0.30262K
rolm-ocr$0.20$0.20$0.20128K
snorkel-mistral-7b-pairrm-dpo$0.20$0.20$0.2033K
starcoder-16b$0.20$0.20$0.208K
starcoder-7b$0.20$0.20$0.208K
starcoder2-15b$0.20$0.20$0.2016K
starcoder2-7b$0.20$0.20$0.2016K
toppy-m-7b$0.20$0.20$0.2033K
Venice Uncensored 1.2$0.20$0.90$0.375128K
Venice: Uncensored$0.20$0.90$0.375128K
Venice: Uncensored$0.20$0.90$0.375128K
X-Ai/Grok 4.1 Fast Non ReasoningxAI$0.20$0.50$0.05$0.2752M
X-Ai/Grok 4.1 Fast ReasoningxAI$0.20$0.50$0.05$0.27520M
x-AI/Grok-4-FastxAI$0.20$0.50$0.05$0.2752M
X-Ai/Grok-4-Fast-Non-ReasoningxAI$0.20$0.50$0.05$0.2752M
X-Ai/Grok-4-Fast-ReasoningxAI$0.20$0.50$0.05$0.2752M
x-AI/Grok-4.1-FastxAI$0.20$0.50$0.05$0.2752M
x-AI/Grok-Code-Fast 1xAI$0.20$1.50$0.02$0.525256K
yi-6b01.AI$0.20$0.20$0.204K
Z-Ai/GLM 4.7Zhipu$0.20$0.80$0.10$0.35200K
Gemma 3 4B ITGoogle$0.2006$0.2006$0.1003$0.2006128K
GLM-4 LongZhipu$0.2006$0.2006$0.1003$0.20061M
Qwen 2.5 Coder 32bAlibaba$0.2006$0.2006$0.1003$0.200632K
Sao10K Stheno 8b$0.2006$0.2006$0.1003$0.200616K
The Drummer Cydonia 24B v4$0.2006$0.2414$0.1003$0.210833K
Qwen3.6 27B ThinkingAlibaba$0.203$2.24$0.1015$0.7123260K
Doubao Seed 1.6$0.204$0.51$0.102$0.2805256K
ByteDance-Seed/Seed-OSS-36B-Instruct$0.21$0.57$0.30262K
Claude-Haiku-3Anthropic$0.21$1.10$0.021$0.4325189K
Nano-BananaGoogle$0.21$1.80$0.021$0.607566K
Step-3$0.21$0.57$0.3066K
DeepSeek V3.2DeepSeek$0.2174$0.326$0.06$0.2445128K
GPT-5.6 Luna (EU)OpenAI$0.22$1.32$0.022$0.4951.1M
Llama 3.1 8B InstructMeta$0.22$0.22$0.22128K
Llama 3.1 8B InstructMeta$0.22$0.22$0.22128K
llama4-maverick-instruct-basic$0.22$0.88$0.385131K
Qwen3 235B A22B InstructAlibaba$0.22$0.88$0.385262K
Qwen3 235B A22B Instruct 2507Alibaba$0.22$0.88$0.385262K
qwen3-coder-480b-a35b-instruct-maasAlibaba$0.22$1.80$0.615262K
Qwen3.5 122B-A10BDatabricks$0.22$2.20$0.22$0.715262K
Qwen3.5 35B A3BAlibaba$0.225$1.80$0.1125$0.6188260K
GPT OSS 120BOpenAI$0.228$0.798$2.00$0.3705131K
Mistral Small 3.2Mistral$0.228$0.456$0.10$0.285128K
Voxtral Small 24BMistral$0.228$0.513$0.01$0.299333K
Gemma 3 27B IT (Amazon Bedrock, US)Amazon$0.23$0.38$0.2675128K
Kloker$0.23$1.16$0.4625200K
Kloker Integration Architect$0.23$1.16$0.4625200K
Kloker Integration Developer$0.23$1.16$0.4625200K
Qwen VL-MAX-2025-01-25Alibaba$0.23$0.574$0.023$0.316128K
Qwen-Omni Turbo RealtimeAlibaba$0.23$0.918$0.40233K
Qwen3-Omni Flash RealtimeAlibaba$0.23$0.918$0.40266K
QwQ PlusAlibaba$0.23$0.574$0.316131K
gov-nvidia-nemotron-nano-12b-v2$0.24$0.72$0.36128K
Llama 4 Maverick 17B Instruct (US)Meta$0.24$0.97$0.42251M
llama4-maverick$0.24$0.97$0.4225128K
nemotron-nano-v2-12bNVIDIA$0.24$0.707$0.3568128K
anthropic--claude-3-haiku$0.25$1.25$0.03$0.50200K
Anthropic: Claude 3 HaikuAnthropic$0.25$1.25$0.03$0.50200K
Arcee Trinity Large Thinking (Public Preview)$0.25$0.90$0.06$0.4125128K
ByteDance Seed 2.0 Lite$0.25$2.00$0.125$0.6875262K
codestral-mambaMistral$0.25$0.25$0.25256K
Deepseek 3.2DeepSeek$0.25$0.80$0.075$0.3875164K
deepseek-v4-flash-thinkingDeepSeek$0.25$1.75$0.625200K
DeepSeek/DeepSeek-V3.1-TerminusDeepSeek$0.25$0.70$0.125$0.3625128K
Gemini 3.1 Flash LiteGoogle$0.25$1.50$0.025$0.56251M
Gemini 3.1 Flash Lite (Vertex AI, US)Google$0.25$1.50$0.025$0.56251M
GPT 5 MiniOpenAI$0.25$2.00$0.025$0.6875400K
GPT 5.1 Codex MiniOpenAI$0.25$2.00$0.025$0.6875400K
GPT-4o mini (Fast)OpenAI$0.25$1.00$0.125$0.4375128K
GPT-5.6 Luna$0.25$1.50$0.025$0.56251M
GPT-5.6 Luna Pro$0.25$1.50$0.025$0.56251M
Holo3-35B-A3B$0.25$1.80$0.125$0.637566K
llama-2-13b-chat-hfMeta$0.25$0.25$0.254K
llama-4-scout-17b-128e-instruct-maasMeta$0.25$0.70$0.362510M
llama-4-scout-17b-16e-instruct-maasMeta$0.25$0.70$0.362510M
Mercury 2$0.25$0.75$0.025$0.375128K
Mercury Coder Small$0.25$1.00$0.125$0.437533K
Mercury Edit 2$0.25$0.75$0.025$0.375128K
Mistral 7BMistral$0.25$0.25$0.258K
mistral-tinyMistral$0.25$0.25$0.2532K
Nano Banana 2 LiteGoogle$0.25$30.00$0.03$7.687566K
open-codestral-mambaMistral$0.25$0.25$0.25256K
OpenAI GPT-5 Mini$0.25$2.00$0.025$0.6875400K
Qwen 3.8 27B FableAlibaba$0.25$1.50$0.125$0.5625262K
Qwen 3.8 27B ObliteratedAlibaba$0.25$1.50$0.20$0.5625262K
Qwen 3.8 27B QueenAlibaba$0.25$1.50$0.125$0.5625262K
Qwen 3.8 27B UncensoredAlibaba$0.25$1.50$0.125$0.5625262K
Qwen3 32B$0.25$0.55$0.32533K
Qwen3 Coder 480B A35B InstructAlibaba$0.25$1.00$0.022$0.4375262K
Qwen3 Omni 30B A3B InstructAlibaba$0.25$0.97$0.4366K
Qwen3 Omni 30B A3B ThinkingAlibaba$0.25$0.97$0.4366K
qwen3-5-122b-a10b-thinkingAlibaba$0.25$1.75$0.625262K
Qwen3.8 27BAlibaba$0.25$2.09$0.04$0.71262K
Seed 1.6$0.25$2.00$0.05$0.6875256K
Seed 1.6 (250615) (ByteDance)$0.25$2.00$0.05$0.6875256K
Seed 1.6 (250915) (ByteDance)$0.25$2.00$0.05$0.6875256K
Seed 1.8 (251228) (ByteDance)$0.25$2.00$0.05$0.6875256K
Seed 2.0 Lite$0.25$2.00$0.6875131K
seed-1.8$0.25$2.00$0.05$0.6875256K
Trinity Large Thinking$0.25$0.90$0.125$0.4125262K
DeepSeek V4.1 FlashDeepSeek$0.2556$1.2778$0.0128$0.51111M
Qwen-MT PlusAlibaba$0.259$0.775$0.38816K
Qwen: Qwen3.5 Plus 2026-02-15Alibaba$0.26$1.56$0.5851M
gemma-4-31b-it-ultraGoogle$0.27$0.76$0.3925131K
MiniMax M2.5MiniMax$0.27$0.95$0.03$0.44198K
olmocr-7b-0725-fp8$0.27$1.50$0.577516K
Qwen3.5 27BAlibaba$0.27$2.16$0.135$0.7425260K
Gemma 3 12B ITGoogle$0.272$0.272$0.136$0.272131K
Gemini 3.1 Flash Lite (EU)Google$0.275$1.65$0.0275$0.61881M
GPT-5 Mini (EU)OpenAI$0.275$2.20$0.0275$0.7563200K
Kimi K2.6 NitroKimi$0.275$1.10$0.4813200K
Kimi K2.7 Code NitroKimi$0.275$1.10$0.4813200K
baidu/ERNIE-4.5-300B-A47BBaidu$0.28$1.10$0.485131K
cobuddy$0.28$1.13$0.07$0.4925131K
DeepSeek V3.2 ExpDeepSeek$0.28$0.42$0.14$0.315164K
DeepSeek V4 Flash 0731 (EU)DeepSeek$0.28$0.56$0.07$0.351M
DeepSeek/DeepSeek-V3.2-Exp-ThinkingDeepSeek$0.28$0.42$0.14$0.315128K
ERNIE 4.5 300B A47BBaidu$0.28$1.10$0.485123K
Green L$0.285$0.912$0.4417128K
Green L Raw$0.285$0.912$0.4417128K
Pixtral 12BMistral$0.285$0.285$0.15$0.285128K
Qwen3-Coder 30B-A3B InstructAlibaba$0.285$1.083$0.05$0.4845128K
Qwen3-VL 235B-A22BAlibaba$0.2867$1.1468$0.10$0.5017131K
DeepSeek R1 Distill Qwen 32BDeepSeek$0.287$0.861$0.430533K
Qwen 2.5 VL 7B InstructAlibaba$0.287$0.717$0.3945128K
Qwen Math TurboAlibaba$0.287$0.861$0.43054K
Qwen2.5 32B InstructAlibaba$0.287$0.861$0.4305131K
QwQ 32BAlibaba$0.287$0.861$0.4305131K
llava-v1-6-mistral-7b-hf$0.29$0.29$0.2932K
Qwen/Qwen3-VL-30B-A3B-InstructAlibaba$0.29$1.00$0.4675262K
Qwen3-Vl 30b A3b ThinkingAlibaba$0.29$1.00$0.4675128K
Qwen3.6 35BAlibaba$0.29$1.15$0.029$0.505131K
Qwen3.6 35B FastAlibaba$0.29$1.15$0.029$0.505131K
Llama 3.3 70B Instruct fp8 FastMeta$0.293$2.253$0.78324K
Qwen3 235B A22B Thinking 2507 TEEAlibaba$0.2989$1.1957$0.0299$0.5231262K
ai-8-1b-21b$0.30$0.30$0.30
amazon--nova-lite$0.30$2.37$0.81751M
Amoral Gemma3 27B v2$0.30$0.30$0.15$0.3033K
Codestral 2508Mistral$0.30$0.90$0.15$0.45256K
codestral-2Mistral$0.30$0.90$0.45128K
codestral-2-001Mistral$0.30$0.90$0.45128K
Codestral-22B-v0.1Mistral$0.30$0.90$0.30$0.45128K
command-lightCohere$0.30$0.60$0.3754K
command-light-textCohere$0.30$0.60$0.3754K
DeepSeek TNG R1T2 ChimeraDeepSeek$0.30$1.20$0.525130K
Gemini 2.5 FlashGoogle$0.30$2.50$0.03$0.851M
Gemini 2.5 Flash (EU)Google$0.30$2.50$0.075$0.851M
Gemini 2.5 Flash (No Thinking)Google$0.30$2.50$0.03$0.851M
Gemini 2.5 Flash ImageGoogle$0.30$30.00$0.075$7.72533K
Gemini 2.5 Flash Preview (09/2025)Google$0.30$2.50$0.03$0.851M
Gemini 2.5 Flash Preview (09/2025) – ThinkingGoogle$0.30$2.50$0.03$0.851M
Gemini 3.5 Flash LiteGoogle$0.30$2.50$0.03$0.851M
Gemini 3.5 Flash Lite (Vertex AI, US)Google$0.30$2.50$0.03$0.851M
Gemini Flash Lite LatestGoogle$0.30$2.50$0.03$0.851M
gemini-2.5-flash-nothinkGoogle$0.30$2.50$0.851M
gemini-robotics-er-1-5Google$0.30$2.50free$0.851M
GLM 4.1V Thinking FlashZhipu$0.30$0.30$0.15$0.3064K
GLM 4.1V Thinking FlashXZhipu$0.30$0.30$0.15$0.3064K
GLM 4.5Zhipu$0.30$1.30$0.15$0.55131K
GLM 4.6VZhipu$0.30$0.90$0.15$0.45128K
GLM-4.6V-FlashZhipu$0.30$0.90$0.0043$0.45131K
gov-anthropic-claude-3-haiku-20240307-v1-0$0.30$1.50$0.03$0.60200K
Grayline Qwen3 8B$0.30$0.30$0.15$0.3033K
Grok 3 MinixAI$0.30$0.50$0.075$0.35131K
Hermes 4 Large$0.30$1.20$0.15$0.525128K
Kat Coder Pro$0.30$1.20$0.06$0.525256K
Kat Coder Pro V2$0.30$1.20$0.06$0.525256K
KAT-Coder-Pro V1$0.30$1.20$0.06$0.525256K
Ling-2.6-1TInclusionAI$0.30$2.50$0.06$0.85262K
MiniMax LatestMiniMax$0.30$1.20$0.06$0.525512K
MiniMax M3 ThinkingMiniMax$0.30$1.20$0.06$0.525512K
MiniMax-M2MiniMax$0.30$1.20$0.525205K
MiniMax-M2 Her$0.30$1.20$0.52566K
minimax-m2-maasMiniMax$0.30$1.20$0.525197K
MiniMax-M2.1MiniMax$0.30$1.20$0.525205K
MiniMax-M2.5MiniMax$0.30$1.20$0.03$0.525205K
MiniMax-M2.5MiniMax$0.30$1.20$0.525197K
MiniMax-M2.5 High ThroughputMiniMax$0.30$1.20$0.525205K
MiniMax-M2.5 LightningMiniMax$0.30$2.40$0.03$0.825205K
Mistral Code LatestMistral$0.30$0.90$0.15$0.45256K
mistral-code-fimMistral$0.30$0.90$0.03$0.45128K
Moonshotai/Kimi-K2.5Alibaba$0.30$1.90$0.15$0.70256K
Nemotron 3 Nano Omni 30B A3B ReasoningNVIDIA$0.30$1.83$0.30$0.6825256K
Nemotron SuperNVIDIA$0.30$0.75$0.06$0.4125203K
NVIDIA Nemotron 3 Super 120B (Public Preview)$0.30$0.65$0.06$0.38751M
Qwen 2.5 7B Instruct TurboAlibaba$0.30$0.30$0.3033K
Qwen 3 235B A22BAlibaba$0.30$0.50$0.15$0.35128K
qwen-coderAlibaba$0.30$1.50$0.601M
Qwen: Qwen3 Coder 480B A35BAlibaba$0.30$1.00$0.10$0.475262K
Qwen3 Coder FlashAlibaba$0.30$1.50$0.15$0.60128K
Qwen3 Coder Next (EU)Alibaba$0.30$1.50$0.60262K
Qwen3 VL 235B A22B InstructAlibaba$0.30$1.20$0.15$0.525131K
Qwen3.6 27B TEEAlibaba$0.30$2.00$0.03$0.725262K
Qwen3.6 35B A3B Uncensored TEEAlibaba$0.30$1.50$0.15$0.60131K
Ring-2.6-1TInclusionAI$0.30$2.50$0.06$0.85262K
TIM-Qwen3.6 27B$0.30$3.00$0.15$0.9758K
titan-text-liteAmazon$0.30$0.40$0.32542K
Veiled Calla 12B$0.30$0.30$0.15$0.3033K
MiniMax M2-herMiniMax$0.302$1.207$0.151$0.528266K
Gemma 4 31B Claude 4.6 Opus Reasoning DistilledGoogle$0.306$0.306$0.0306$0.306262K
Gemma 4 31B Cognitive UnshackledGoogle$0.306$0.306$0.153$0.306262K
Gemma 4 31B DarkIdolGoogle$0.306$0.306$0.153$0.306262K
Gemma 4 31B Garnet V2Google$0.306$0.306$0.153$0.306262K
Gemma 4 31B QueenGoogle$0.306$0.306$0.153$0.306262K
Llama 3.1 70B Euryale$0.306$0.357$0.153$0.318720K
Qwen3.5 27B BlueStar v3 DerestrictedAlibaba$0.306$0.306$0.153$0.306262K
Qwen3.5 27B Queen DerestrictedAlibaba$0.306$0.306$0.153$0.306262K
Anubis 70B v1$0.31$0.31$0.155$0.3166K
Anubis 70B v1.1$0.31$0.31$0.155$0.3132K
MiniMax M2.7MiniMax$0.315$1.26$0.1575$0.5513205K
Qwen3.8 27B TEEAlibaba$0.32$2.50$0.032$0.865262K
Qwen 3.6 PlusAlibaba$0.325$1.95$0.0325$0.7312992K
Qwen: Qwen3.6 PlusAlibaba$0.325$1.95$0.73121M
fw-minimax-m2-5$0.33$1.32$0.033$0.57751M
fw-minimax-m3$0.33$1.32$0.066$0.5775512K
Gemini 3.5 Flash Lite (EU)Google$0.33$2.75$0.033$0.9351M
Minimax/Minimax-M2.1MiniMax$0.33$1.32$0.165$0.5775205K
nova-2-sonicAmazon$0.33$2.75$0.935
Gemma 3 27BGoogle$0.342$0.684$0.1496$0.427540K
Qwen3.6 35B-A3BAlibaba$0.342$2.052$0.056$0.7695262K
codellama-34b-instructPerplexity$0.35$1.40$0.612516K
DeepSeek V4 Flash 0731 FastDeepSeek$0.35$0.70$0.0875$0.43751M
gemini-gemma-2-27b-itGoogle$0.35$1.05$0.525
gemini-gemma-2-9b-itGoogle$0.35$1.05$0.525
GLM 4.6 OriginalZhipu$0.35$1.40$0.175$0.6125256K
GPT-OSS-120B-CSOpenAI$0.35$0.75$0.45128K
Llama 4 Maverick 17B 128E InstructMeta$0.35$1.15$0.55524K
llama-4-maverick-17b-16e-instruct-maasMeta$0.35$1.15$0.551M
llama3-2-11b-instructMeta$0.35$0.35$0.35128K
Muse Glimmer 30BMeta$0.35$1.50$0.04$0.6375131K
Qwen 3 Coder 480B TurboAlibaba$0.35$1.50$0.04$0.6375256K
Qwen 3 Next 80bAlibaba$0.35$1.90$0.7375256K
The Drummer Cydonia 24B v4.1$0.35$0.55$0.16$0.40131K
Z-AI/GLM 4.6Zhipu$0.35$1.40$0.175$0.6125200K
Gemma Sea Lion V4 27B ItGoogle$0.351$0.555$0.402128K
Nvidia Nemotron 70bNVIDIA$0.357$0.408$0.1785$0.369716K
Qwen2.5 72BAlibaba$0.357$0.408$0.1785$0.3697131K
mistralai--mistral-medium-instruct$0.36$1.22$0.575128K
Qwen3 30b A3b Thinking 2507Alibaba$0.36$1.30$0.595126K
Ministral 3 14B InstructMistral$0.37$0.50$0.4025100K
Llama 4 Maverick 17B 128E Instruct FP8Meta$0.371$1.484$0.1275$0.6492131K
llama-4-maverick-17bMeta$0.371$1.484$0.6492131K
MiniMax M2.7MiniMax$0.375$1.50$0.0688$0.6563198K
granite-ttm-1024-96-r2IBM$0.38$0.38$0.381K
granite-ttm-1536-96-r2IBM$0.38$0.38$0.381K
granite-ttm-512-96-r2IBM$0.38$0.38$0.381K
ERNIE-4.5-VL-28B-A3B-ThinkingBaidu$0.39$0.39$0.39131K
Green R$0.399$1.083$0.57131K
Green R Raw$0.399$1.083$0.57131K
Holo2 30B A3B$0.399$0.969$0.541522K
Qwen PlusAlibaba$0.3995$1.2002$0.1998$0.5997996K
babbage-002$0.40$0.40$0.4016K
Deepseek R1 CheaperDeepSeek$0.40$1.70$0.20$0.725128K
DeepSeek ReasonerDeepSeek$0.40$1.70$0.20$0.72564K
DeepSeek V3 (Turbo) DeepSeek$0.40$1.30$0.62564K
DeepSeek-R1DeepSeek$0.40$1.70$0.20$0.725128K
Devstral 2Mistral$0.40$2.00$0.40$0.80256K
Devstral 2 (Mistral AI)Mistral$0.40$2.00$0.44$0.80262K
Devstral 2 123BMistral$0.40$2.00$0.80256K
Devstral MediumMistral$0.40$2.00$0.80128K
Gemma 4 31B$0.40$1.00$0.40$0.55262K
GLM 4.6 Derestricted v5Zhipu$0.40$1.50$0.20$0.675131K
glm-4-7-fp8Zhipu$0.40$2.00$0.80203K
GPT 4.1 MiniOpenAI$0.40$1.60$0.10$0.701M
GPT 5.6 Luna (Fast)OpenAI$0.40$2.40$0.04$0.901.1M
Kimi K2 0711 FastKimi$0.40$1.80$0.20$0.75131K
Kimi K2 0711 Instruct FP4Kimi$0.40$1.80$0.20$0.75131K
Kimi K2 0905Kimi$0.40$1.80$0.20$0.75262K
Mancer: Weaver (alpha)$0.40$0.75$0.48758K
meta-llama-3-1-70b-instruct-turboMeta$0.40$0.40$0.40131K
MiMo-V2.5$0.40$2.00$0.08$0.801M
MiniMax-M3 (EU)MiniMax$0.40$2.00$0.10$0.801M
Mistral Code Agent LatestMistral$0.40$2.00$0.20$0.80262K
Mistral Medium 3Mistral$0.40$2.00$0.40$0.80128K
Mistral Medium 3Mistral$0.40$2.00$0.20$0.80131K
Mistral Medium 3.1Mistral$0.40$2.00$0.20$0.80131K
Mistral Small 4 119B ThinkingMistral$0.40$1.40$0.20$0.65262K
mistral-medium-3-001Mistral$0.40$2.00$0.80128K
Qwen3 VL InstructAlibaba$0.40$1.60$0.70131K
Qwen3 VL ThinkingAlibaba$0.40$4.00$1.30131K
Qwen3.5 397B-A17BAlibaba$0.40$2.65$0.20$0.9625262K
Qwen3.5 Plus ThinkingAlibaba$0.40$2.40$0.04$0.90984K
TheDrummer: UnslopNemo 12B$0.40$0.40$0.401M
Venice Uncensored$0.40$1.80$0.40$0.75128K
Hermes 3 70B$0.408$0.408$0.204$0.40866K
Rocinante 12b$0.408$0.595$0.204$0.454716K
ERNIE 4.5 VL 424B A47B (NovitaAI)Baidu$0.42$1.25$0.6275123K
GLM 4.6$0.43$1.75$0.08$0.76198K
DeepSeek V4 ProDeepSeek$0.435$0.87$0.04$0.54371M
Qwen3.5 122B A10B ThinkingAlibaba$0.437$3.496$0.1038$1.2018131K
DeepSeek V4 Flash 0731 TEEDeepSeek$0.44$1.32$0.044$0.661M
DeepSeek V4 Flash Vision ExpDeepSeek$0.44$1.32$0.014$0.661M
devstral-latest@euMistral$0.44$2.20$0.44$0.88256K
GPT-4.1 mini (EU)OpenAI$0.44$1.76$0.11$0.771M
Mistral Medium (latest) (EU)Mistral$0.44$2.20$0.44$0.88131K
Neural Daredevil 8B abliterated$0.44$0.44$0.22$0.448K
Xiaomi MiMo-V2.5$0.44$2.20$0.088$0.881M
Qwen3-Coder 480B-A35B InstructAlibaba$0.445$2.145$0.2225$0.87106K
DeepSeek V4 Flash 0731DeepSeek$0.4453$1.3359$0.0148$0.6681M
Seed 2.1 Turbo$0.4453$2.2265$0.0891$0.8906256K
Agnes 2.5 Pro Alpha$0.45$0.90$0.0038$0.56251M
GPT-3.5-Turbo-RawOpenAI$0.45$1.40$0.68755K
GPT-5 mini (Fast)OpenAI$0.45$3.60$0.045$1.2375400K
macaron-v1-tall$0.45$2.60$0.08$0.9875262K
Qwen3-Coder 480B-A35B InstructAlibaba$0.45$1.80$0.7875131K
Qwen3.5 397B A17B TEEAlibaba$0.45$3.00$0.045$1.0875262K
Qwen3.8 27BAlibaba$0.45$3.20$0.25$1.1375262K
Qwen: Qwen3 235B A22BAlibaba$0.455$1.82$0.7963131K
Doubao 1.5 Vision Pro 32k$0.459$1.377$0.2295$0.688532K
Apertus 70B$0.46$2.42$0.9530K
Qwen3.8 27BAlibaba$0.46$3.48$1.215262K
Qwen 3 8BAlibaba$0.47$0.47$0.235$0.4741K
DeepSeek V4 Pro (DeepSeek)$0.478$0.956$0.0043$0.59751M
Doubao Seed 2.0 Code$0.48$2.41$0.0964$0.9625256K
Doubao Seed 2.0 Pro$0.48$2.41$0.0964$0.9625256K
sap-abap-1$0.48$1.70$0.78533K
Mixtral 8x7B Instruct v0.1Mistral$0.488$0.758$0.555532K
Llama 3.05 Storybreaker Ministral 70bMeta$0.493$0.493$0.2465$0.49316K
Llama 3.1 70B Celeste v0.1$0.493$0.493$0.2465$0.49333K
Llama 3.1 70B Dracarys 2$0.493$0.493$0.2465$0.49333K
Llama 3.1 70B Hanami$0.493$0.493$0.2465$0.49333K
Llama 3.3 70B Cu Mai$0.493$0.493$0.2465$0.49333K
Llama 3.3 70B Euryale$0.493$0.493$0.2465$0.49320K
Mag Mell R1$0.493$0.493$0.2465$0.49316K
Mistral Nemo Starcannon 12b v1$0.493$0.493$0.2465$0.49316K
MN-LooseCannon-12B-v1$0.493$0.493$0.2465$0.49316K
MS3.2 24B Magnum Diamond$0.493$0.493$0.2465$0.49333K
NemoMix 12B Unleashed$0.493$0.493$0.2465$0.49333K
Nemotron Tenyxchat Storybreaker 70bMeta$0.493$0.493$0.2465$0.49316K
Steelskull Nevoria 70b$0.493$0.493$0.2465$0.49333K
Steelskull Nevoria R1 70b$0.493$0.493$0.2465$0.49333K
UnslopNemo 12b v4$0.493$0.493$0.2465$0.4938K
WizardLM-2 8x22BMicrosoft$0.493$0.493$0.2465$0.49366K
ai-moe-up-to-56b$0.50$0.50$0.50
ByteDance Seed 2.0 Code$0.50$3.00$0.25$1.125262K
ByteDance Seed 2.1 Turbo$0.50$2.50$0.25$1.00262K
chatdolphin$0.50$0.50$0.5016K
Claudinio$0.50$2.00$0.15$0.875256K
command-rCohere$0.50$1.50$0.75128K
DeepSeek V4.1 Flash (EU)DeepSeek$0.50$1.50$0.05$0.751M
deepseek-v2-lite-chatDeepSeek$0.50$0.50$0.50164K
DiffusionGemma 26B-A4B ITGoogle$0.50$0.50$0.50$0.50262K
Dola Seed 2.0 Code (preview)$0.50$3.00$1.125131K
dolphin$0.50$0.50$0.5016K
dolphin-2-6-mixtral-8x7b$0.50$0.50$0.5033K
Doubao Seed 2.1 Turbo$0.50$2.50$0.25$1.00256K
Gemini 3 Flash (Preview)Google$0.50$3.00$0.05$1.1251M
Gemini 3 Flash ThinkingGoogle$0.50$3.00$0.05$1.1251M
gemini-2-5-flash-native-audioGoogle$0.50$2.00$0.8751M
gemini-2-5-flash-native-audio-preview-09Google$0.50$2.00$0.8751M
gemini-2-5-flash-native-audio-preview-12Google$0.50$2.00$0.8751M
gemini-live-2-5-flash-native-audioGoogle$0.50$2.00$0.875131K
gemini-live-2-5-flash-preview-native-audio-09Google$0.50$2.00$0.075$0.8751M
GPT-3.5 TurboOpenAI$0.50$1.50free$0.7516K
gpt-35-turboOpenAI$0.50$1.50$0.754K
Inkling Small$0.50$1.20$0.10$0.675524K
jamba-instructAI21$0.50$0.70$0.5570K
kimi-k2-5-fp4Kimi$0.50$2.80$1.075262K
llama-2-70b-chatMeta$0.50$1.50$0.50$0.754K
Magistral SmallMistral$0.50$1.50$0.50$0.75128K
magistral-small-1-2Mistral$0.50$1.50$0.7540K
mistral-large-3:675bMistral$0.50$1.50$0.50$0.75262K
mixtral-8x7bMistral$0.50$0.50$0.5032K
mixtral-8x7b-instruct-hfMistral$0.50$0.50$0.5033K
Motif 3$0.50$2.00$0.20$0.875262K
mpt-7b-instructDatabricks$0.50free$0.50$0.3758K
Nano Banana 2Google$0.50$60.00$0.05$15.375131K
Nemotron 3 Nano OmniNVIDIA$0.50$0.90$0.06$0.6066K
Nemotron 3 Super 120BNVIDIA$0.50$1.50$0.75256K
Nemotron 3 Ultra 550B A55BNVIDIA$0.50$2.50$0.15$1.001M
Nemotron 3.5 Lightning 30B A3BNVIDIA$0.50$0.50$0.50$0.508K
nous-hermes-2-mixtral-8x7b-dpo$0.50$0.50$0.5033K
nvidia-nemotron-3-ultra$0.50$2.50$1.00262K
Omega Directive 24B Unslop v2.0$0.50$0.50$0.25$0.5033K
Qwen 3.7 PlusAlibaba$0.50$2.00$0.05$0.8751M
Qwen Plus Character (Japanese)Alibaba$0.50$1.40$0.7258K
Qwen-ImageAlibaba$0.50$2.00$0.8758K
qwen2-audio-7b-instructAlibaba$0.50$100.00$25.3754K
Qwen3 VL 235B A22B Instruct OriginalAlibaba$0.50$1.20$0.25$0.67533K
Qwen3 VL 235B A22B ThinkingAlibaba$0.50$6.00$0.25$1.875131K
Qwen3.5 122B-A10B FP8Alibaba$0.50$3.97$1.3675200K
Qwen3.6 PlusAlibaba$0.50$3.00$0.10$1.1251M
Qwerky 72B$0.50$0.50$0.25$0.5032K
Seed 2.0 Pro$0.50$3.00$0.10$1.125256K
Seed 2.0 Pro$0.50$3.00$1.125131K
Shisa V2 Llama 3.3 70B$0.50$0.50$0.25$0.50128K
Shisa V2.1 Llama 3.3 70B$0.50$0.50$0.25$0.5033K
swe-1-6$0.50$2.50$0.20$1.00
swe-1-7$0.50$2.50$0.20$1.00
titan-text-premierAmazon$0.50$1.50$0.7542K
Venice Role Play Uncensored$0.50$2.00$0.875128K
Qwen Coder Plus (Alibaba Cloud)Alibaba$0.502$1.004$0.6275131K
Amazon Nova 2 LiteAmazon$0.51$4.25$0.255$1.4451M
Llama 3 70B Instruct (NovitaAI)Meta$0.51$0.74$0.56758K
Llama 3.3 70BMeta$0.53$0.76$0.5875128K
Llama 4 Maverick 17B Instruct (SCX.ai (Turbo))Meta$0.53$1.62$0.8025131K
DeepSeek V3.2NVIDIA$0.55$1.65$0.825131K
deepseek-r1-0528-tputDeepSeek$0.55$2.19$0.96128K
deepseek-r1-basicDeepSeek$0.55$2.19$0.96128K
GLM 4.7$0.55$2.65$0.11$1.075198K
TheDrummer Skyfall 36B V2$0.55$0.80$0.25$0.612533K
amazon--nova-pro$0.56$2.13$0.9525300K
DeepSeek V3.2DeepSeek$0.56$1.68$0.056$0.84164K
Devstral 2Mistral$0.57$2.736$0.20$1.1115200K
gemma4$0.57$1.71$0.05$0.855262K
Ling-1TInclusionAI$0.57$2.29$0.11$1.00128K
Ring-1TInclusionAI$0.57$2.29$0.11$1.00128K
Moonshot Kimi K2 InstructKimi$0.574$2.294$1.004131K
Qwen Math PlusAlibaba$0.574$1.721$0.86084K
Qwen2.5-Math 72B InstructAlibaba$0.574$1.721$0.86084K
DeepSeek-V3.1DeepSeek$0.58$1.68$0.855164K
DeepSeek-V3.2-SpecialeDeepSeek$0.58$1.68$0.855128K
Kimi K2.6 TEEKimi$0.58$3.40$0.058$1.285262K
Llama 3.3 70BMeta$0.59$0.79$0.64131K
Qwen/Qwen2.5-72B-InstructAlibaba$0.59$0.59$0.5933K
Ambient Large$0.60$2.00$0.15$0.95203K
DeepSeek V3.1DeepSeek$0.60$1.70$0.06$0.875164K
flan-t5-xl-3bIBM$0.60$0.60$0.608K
fw-nemotron-3-ultra-nvfp4$0.60$2.40$0.119$1.05262K
GLM 4.5V ThinkingZhipu$0.60$1.80$0.30$0.9066K
GLM 4.6V OriginalZhipu$0.60$0.90$0.30$0.675128K
GLM 4.7 OriginalZhipu$0.60$2.20$0.11$1.00200K
glm-4-7-hZhipu$0.60$2.20$0.11$1.00205K
GLM-4.7Amazon$0.60$2.20$1.00205K
GLM-4.7Zhipu$0.60$2.20$0.06$1.00200K
GLM-5Zhipu$0.60$1.92$0.12$0.93203K
GPT-Realtime miniOpenAI$0.60$2.40$0.06$1.050
gpt-realtime-2-1-miniOpenAI$0.60$2.40$0.06$1.0532K
granite-13b-chatIBM$0.60$0.60$0.608K
granite-13b-instructIBM$0.60$0.60$0.608K
grok-3-mini-fastxAI$0.60$4.00$0.20$1.45131K
k-exaone-2-0-750b-a37b$0.60$2.40$0.12$1.05262K
Kimi K2 ThinkingKimi$0.60$2.50$0.15$1.075256K
Kimi K2 ThinkingKimi$0.60$2.50$0.06$1.075262K
Kimi K2.5Amazon$0.60$3.00$1.20262K
kimi-thinkingKimi$0.60$2.50$0.15$1.075131K
llama3-1-70b$0.60$0.60$0.60128K
MiniMax M2.7 TurboMiniMax$0.60$2.40$0.30$1.05205K
MiniMax-M2.7-highspeedMiniMax$0.60$2.40$0.06$1.05205K
MiniMax-M3$0.60$2.40$0.12$1.051M
Minimax/Minimax-M2.5 HighspeedMiniMax$0.60$2.40$0.03$1.05205K
Nemotron UltraNVIDIA$0.60$2.40$0.12$1.05203K
nemotron-3-ultra-nvfp4NVIDIA$0.60$2.40$0.12$1.05262K
NeoSmith NeoLite$0.60$2.40$0.08$1.05512K
OpenAI: GPT Audio MiniOpenAI$0.60$2.40$1.05128K
Palmyra X5 (US)Amazon$0.60$6.00$1.951M
Qwen3.5 397B A17B (Alibaba Cloud)Alibaba$0.60$3.60$1.35262K
qwen3.5:397bAlibaba$0.60$3.60$1.35262K
sonar-medium-chatPerplexity$0.60$1.80$0.9016K
Wan2.2-T2V-A14B$0.60free$0.45100
Writer: Palmyra X5$0.60$6.00$1.951M
MiniMax M1 80KMiniMax$0.6052$2.4225$0.3026$1.05951M
Kimi K2.7 Code FlexKimi$0.6175$2.60$0.0617$1.1131262K
DeepSeek V3.2DeepSeek$0.62$1.85$0.9275164K
DeepSeek V3.2 ThinkingDeepSeek$0.62$1.85$0.9275128K
fw-deepseek$0.62$1.85$0.31$0.9275164K
cohere--command-a-reasoning$0.63$5.05$1.735256K
Google: Gemma 2 27BGoogle$0.65$0.65$0.658K
l3-3-70b-euryale$0.65$0.75$0.675131K
Llama 3.3 Instruct (70B)Meta$0.65$0.65$0.65128K
llama-2-70bMeta$0.65$2.75$1.1754K
llama-3-70bMeta$0.65$2.75$1.1758K
Sao10K: Llama 3.3 Euryale 70B$0.65$0.75$0.675131K
Sao10K: Llama 3.3 Euryale 70B$0.65$0.75$0.675131K
minicpm-v-4.5$0.651$1.097$0.762532K
MM Poly 8B$0.658$1.11$0.77133K
fw-kimi-k2-5$0.66$3.30$0.11$1.32262K
gpt-4o-mini-realtimeOpenAI$0.66$2.64$0.33$1.155128K
Qwen2.5 Coder 32B InstructAlibaba$0.66$1.00$0.74533K
Bielik 11B v2.6 Instruct$0.67$0.67$0.6732K
Bielik 11B v3.0 Instruct$0.67$0.67$0.6732K
Claude-Haiku-3.5Anthropic$0.68$3.40$0.068$1.36189K
Steelskull Electra R1 70b$0.6999$0.6999$0.3499$0.699933K
AionLabs: Aion 3.0 Mini$0.70$1.40$0.18$0.875131K
codellama-70b-instructPerplexity$0.70$2.80$1.22516K
Deepseek Prover V2 671BDeepSeek$0.70$2.50$1.15160K
DeepSeek R1 (Turbo) DeepSeek$0.70$2.50$1.1564K
DeepSeek R1 Llama 70B AbliteratedDeepSeek$0.70$0.70$0.35$0.7016K
GLM Z1 AirXZhipu$0.70$0.70$0.35$0.7032K
GPT-4.1 mini (Fast)OpenAI$0.70$2.80$0.175$1.2251M
Llama 3 70B abliteratedMeta$0.70$0.70$0.35$0.708K
Llama 3.3 70B Instruct abliteratedMeta$0.70$0.70$0.35$0.7033K
Llama 3.3 70B Wayfarer$0.70$0.70$0.35$0.7033K
Mixtral 8x7BMistral$0.70$0.70$0.7032K
pplx-70b-chatPerplexity$0.70$2.80$1.2254K
Qwen 2.5 32B AbliteratedAlibaba$0.70$0.70$0.35$0.7033K
Qwen 2.5 VL 72B InstructAlibaba$0.70$0.70$0.35$0.70128K
Qwen-VL OCRAlibaba$0.717$0.717$0.71734K
Llama 3.1 70B InstructMeta$0.72$0.72$0.72128K
Llama 3.1 70B Instruct (AWS Bedrock)Meta$0.72$0.72$0.80$0.72128K
Llama 3.1 70B Instruct (US)Meta$0.72$0.72$0.72128K
Llama 3.3 70B InstructMeta$0.72$0.72$0.72128K
llama-3-2-90bMeta$0.72$0.72$0.72128K
moonshotai-kimi-k2-thinkingAmazon$0.73$3.03$1.305262K
Kat Coder Pro V2.5$0.74$2.96$0.15$1.295256K
Meta-Llama-3_3-70B-InstructMeta$0.74$0.74$0.50$0.74131K
ERNIE 5.1 ThinkingBaidu$0.75$3.00$0.75$1.3125119K
Gemini 3.1 Flash Live PreviewGoogle$0.75$4.50$1.6875131K
Gemini 3.6 FlashGoogle$0.75$3.75$0.075$1.501M
Gemini 3.6 Flash (Vertex AI, EU)Google$0.75$3.75$0.075$1.501M
Gemini 3.6 Flash (Vertex AI, US)Google$0.75$3.75$0.075$1.501M
Gemini 3.7 FlashGoogle$0.75$3.75$0.075$1.501M
Gemini 3.7 Flash (Vertex AI, US)Google$0.75$3.75$0.075$1.501M
Gemini 3.8 FlashGoogle$0.75$3.75$0.075$1.501M
Gemini 3.8 Flash (Vertex AI, US)Google$0.75$3.75$0.075$1.501M
Gemini Flash LatestGoogle$0.75$3.75$0.075$1.501M
GPT 5.4 MiniOpenAI$0.75$4.50$0.075$1.6875400K
llama2-13b-chatMeta$0.75$1.00$0.81254K
LongCat 2.0$0.75$3.00$0.015$1.31251M
mai-code-1-flash$0.75$4.50$0.075$1.6875128K
MAI-Code-1-Flash$0.75$4.50$0.075$1.6875256K
mai-code-1-flash-internal$0.75$4.50$0.075$1.6875128K
OpenAI GPT-5.4 Mini$0.75$4.50$0.075$1.6875400K
OpenAI: GPT Mini LatestOpenAI$0.75$4.50$0.075$1.6875400K
Qwen3.7 PlusAlibaba$0.768$3.072$0.08$1.3441M
Doubao Seed 2.0 Code Preview$0.782$3.893$0.391$1.5597256K
Doubao Seed 2.0 Pro$0.782$3.876$0.391$1.5555256K
mistral-saba-24bMistral$0.79$0.79$0.7933K
Qwen 2.5 Coder 32BAlibaba$0.79$0.79$0.79128K
Amazon Nova Pro 1.0Amazon$0.799$3.196$0.3995$1.3982300K
Doubao 1.5 Pro 256k$0.799$1.445$0.3995$0.9605256K
EVA-Qwen2.5-32B-v0.2$0.799$0.799$0.3995$0.79916K
EVA-Qwen2.5-72B-v0.2$0.799$0.799$0.3995$0.79916K
ReMM SLERP 13B$0.799$1.207$0.3995$0.9016K
ai-21-1b-41b$0.80$0.80$0.80
AionLabs: Aion-2.0$0.80$1.60$0.20$1.00131K
Claude 3.5 HaikuAnthropic$0.80$4.00$0.08$1.60200K
Claude 3.5 Haiku$0.80$4.00$0.08$1.60200K
claude-instantAnthropic$0.80$2.40$1.20100K
deepseek-r1-671bDeepSeek$0.80$0.80$0.80131K
GLM 5.2 NitroZhipu$0.80$2.40$1.20200K
hermes3-405b$0.80$0.80$0.80131K
Llama 3.1 8b (uncensored)$0.80$1.60$0.40$1.0033K
llama3-1-405b-instruct-fp8$0.80$0.80$0.80131K
Morph v3 Fast$0.80$1.20$0.9016K
Apertus 70B Instruct$0.82$2.92$1.34566K
Gemini 3.7 Flash (EU)Google$0.825$4.125$0.0825$1.651M
Gemini 3.8 Flash (EU)Google$0.825$4.125$0.0825$1.651M
Tencent Hy4 Preview$0.834$2.501$0.042$1.25081M
GLM-5.1 (Alibaba Cloud)$0.84$3.38$0.169$1.475200K
GLM-5.1 (Z.ai)$0.845$3.38$0.1831$1.4788200K
l3-1-70b-euryale$0.85$0.85$0.85131K
Relace: Relace Apply 3$0.85$1.25$0.95256K
router$0.85$3.40$1.4875131K
Sao10K: Llama 3.1 Euryale 70B v2.2$0.85$0.85$0.85131K
Apertus v1.5 70B$0.87$3.10$1.4275100K
Aion 3.0 Mini$0.875$1.75$0.225$1.0938128K
meta-llama-3-70b-instruct-turboMeta$0.88$0.88$0.88
community$0.89$0.89$0.8964K
GLM-5Alibaba$0.89$3.2647$0.2226$1.4837205K
Seed 2.1 Pro$0.8906$4.453$0.1781$1.7812256K
Seed Evolving$0.8906$4.453$0.1781$1.7812256K
ai-41-1b-80b$0.90$0.90$0.90
ai-above-16b$0.90$0.90$0.90
code-llama-34b$0.90$0.90$0.9016K
code-llama-34b-instruct$0.90$0.90$0.9016K
code-llama-34b-python$0.90$0.90$0.9016K
code-llama-70b$0.90$0.90$0.904K
code-llama-70b-instruct$0.90$0.90$0.904K
code-llama-70b-python$0.90$0.90$0.904K
cogito-v1-preview-llama-70b$0.90$0.90$0.90131K
deepseek-coder-33b-instructDeepSeek$0.90$0.90$0.9016K
dobby-unhinged-llama-3-3-70b-new$0.90$0.90$0.90131K
dolphin-2-9-2-qwen2-72b$0.90$0.90$0.90131K
fare-20b$0.90$0.90$0.90131K
firefunction$0.90$0.90$0.908K
internvl3-38b$0.90$0.90$0.9016K
internvl3-78b$0.90$0.90$0.9016K
kat-coder$0.90$0.90$0.90262K
kat-dev-32b$0.90$0.90$0.90131K
kat-dev-72b$0.90$0.90$0.90131K
llama-v2-70b-chatMeta$0.90$0.90$0.902K
llama-v3-1-70b-instructMeta$0.90$0.90$0.90131K
llama-v3-1-nemotron-70b-instructMeta$0.90$0.90$0.90131K
llama-v3-2-90b-vision-instructMeta$0.90$0.90$0.9016K
llama-v3-3-70b-instructMeta$0.90$0.90$0.90131K
llama-v3-70b-instructMeta$0.90$0.90$0.908K
llama-v3-70b-instruct-hfMeta$0.90$0.90$0.908K
llava-yi-34b$0.90$0.90$0.904K
mixtral-8x22b-instruct-v0-1Mistral$0.90$0.90$0.9066K
Morph v3 Large$0.90$1.90$1.1532K
Nemotron 3 UltraNVIDIA$0.90$1.70$0.10$1.10131K
nous-hermes-2-yi-34b$0.90$0.90$0.904K
nous-hermes-llama2-70b$0.90$0.90$0.904K
phind-code-llama-34b$0.90$0.90$0.9016K
phind-code-llama-34b-python$0.90$0.90$0.9016K
qwen-qwq-32bAlibaba$0.90$0.90$0.9033K
qwen1-5-72b-chat$0.90$0.90$0.9033K
qwen2-5-32bAlibaba$0.90$0.90$0.90131K
qwen2-5-72bAlibaba$0.90$0.90$0.90131K
qwen2-5-coder-32bAlibaba$0.90$0.90$0.9033K
qwen2-5-coder-32b-instruct-128kAlibaba$0.90$0.90$0.90131K
qwen2-5-coder-32b-instruct-32k-ropeAlibaba$0.90$0.90$0.9033K
qwen2-5-coder-32b-instruct-64kAlibaba$0.90$0.90$0.9066K
qwen2-72b-instructAlibaba$0.90$0.90$0.9033K
qwen3-coder-480b-instruct-bf16Alibaba$0.90$0.90$0.904K
Qwen3.5-122BAlibaba$0.90$3.60$1.575262K
yi-34b01.AI$0.90$0.90$0.904K
yi-34b-200k-capybara01.AI$0.90$0.90$0.90200K
yi-34b-chat01.AI$0.90$0.90$0.904K
Kimi K2.7 CodeKimi$0.9006$4.389$0.1881$1.7727262K
Nova Pro 1.0Amazon$0.918$3.671$1.6062300K
GPT-5.4 Mini$0.9375$5.625$0.0938$2.1094400K
GLM 5.2 FlexZhipu$0.9425$2.925$0.0943$1.43811M
GLM 5.2 Short Fast FlexZhipu$0.9425$2.925$0.0943$1.4381200K
GLM 5.2 Short FlexZhipu$0.9425$2.925$0.0943$1.4381200K
Kimi K2.6Kimi$0.95$4.00$0.16$1.7125262K
Kimi K2.6 (EU)Kimi$0.95$4.00$0.95$1.7125256K
Kimi K2.7 Code FastKimi$0.95$4.00$0.095$1.7125262K
Sakana Namazu$0.95$4.00$0.15$1.7125262K
Sakana Namazu$0.95$4.00$0.15$1.7125256K
DeepSeek: DeepSeek Pro LatestDeepSeek$0.96$2.88$0.088$1.441M
GLM 5.1 TEEZhipu$0.98$3.08$0.098$1.505203K
DeepSeek R1 Distill Llama 70BDeepSeek$0.99$0.99$0.9933K
Qwen3.5 397B-A17B FP8Alibaba$0.99$4.46free$1.8575200K
Anthropic Claude Haiku 4.5$1.00$5.00$0.10$2.00200K
ASI1 Mini$1.00$1.00$0.50$1.00128K
Claude 4.5 HaikuAnthropic$1.00$5.00$0.10$2.00200K
Claude Haiku 4.5$1.00$5.00$1.00$2.00200K
Claude Haiku 4.5 ThinkingAnthropic$1.00$5.00$0.10$2.00200K
Claude Haiku LatestAnthropic$1.00$5.00$0.10$2.00200K
Claw High$1.00$3.20$0.20$1.551M
Claw Low$1.00$3.20$0.20$1.551M
Claw Medium$1.00$3.20$0.20$1.551M
codellama-34b-instruct-hf$1.00$1.00$1.004K
codellama-70b-instruct-hf$1.00$1.00$1.004K
commandCohere$1.00$2.00$1.254K
command-nightlyCohere$1.00$2.00$1.254K
DeepSeek V3.2 TEEDeepSeek$1.00$1.00$0.10$1.00131K
deepseek-r1-0528-turboDeepSeek$1.00$3.00$1.5033K
Doubao Seed 2.1 Pro$1.00$5.00$0.50$2.00256K
Ernie 5.0 Thinking PreviewBaidu$1.00$3.50$0.50$1.625128K
fw-inkling$1.00$4.05$0.17$1.76251M
Gemini Robotics-ER 1.6 PreviewGoogle$1.00$5.00$2.00131K
GLM 4.6 TurboZhipu$1.00$3.00$0.50$1.50205K
GLM 5$1.00$3.20$0.20$1.55198K
GLM 5 Original ThinkingZhipu$1.00$3.20$0.20$1.55200K
GLM LatestZhipu$1.00$3.20$0.20$1.551M
GLM-5Amazon$1.00$3.20$1.55203K
GLM-5Zhipu$1.00$3.20$0.10$1.55203K
GLM-5.3$1.00$3.50$0.25$1.625524K
Grok Build 0.1xAI$1.00$2.00$0.20$1.25256K
grok-code-fastxAI$1.00$2.00$0.20$1.25256K
Hermes High$1.00$3.20$0.20$1.551M
Hermes Low$1.00$3.20$0.20$1.551M
Hermes Medium$1.00$3.20$0.20$1.551M
Inkling ThinkingDatabricks$1.00$4.05$0.17$1.76251M
Kimi K3 EcoKimi$1.00$4.00$0.10$1.751M
kimi-latest-32kKimi$1.00$3.00$0.15$1.5033K
llama-2-70b-chat-hfMeta$1.00$1.00$1.004K
Lumimaid v0.2$1.00$1.50$0.50$1.12516K
meta-llama-3-70b-instructMeta$1.00$1.00$1.00$1.008K
Mistral Large 3 675BMistral$1.00$3.00$0.50$1.50262K
moonshot-v1-32kKimi$1.00$3.00$1.5033K
moonshot-v1-32k-visionKimi$1.00$3.00$1.5033K
mpt-30b-instructDatabricks$1.00$1.00$1.00$1.008K
Perplexity Sonar ReasoningPerplexity$1.00$5.00$2.00127K
Qwen3 Coder PlusAlibaba$1.00$5.00$0.50$2.00128K
Relace: Relace Search$1.00$3.00$1.50256K
Sonar (Perplexity)Perplexity$1.00$1.00$0.0625$1.00130K
Qwen3 235B A22B Instruct 2507Alibaba$1.026$3.078$0.065$1.539262K
Ministral 3 3B Reasoning 2512Mistral$1.039$0.5483$0.9163262K
Qwen3.6 Max PreviewAlibaba$1.04$6.24$0.52$2.34246K
fw-kimi-k2-6$1.045$4.40$0.176$1.8838262K
fw-kimi-k2-7-code$1.05$4.40$0.21$1.8875262K
Vision Small$1.05$3.16$1.57751M
Claude Haiku 4.5 (latest) (EU)Anthropic$1.10$5.50$0.11$2.20200K
fw-glm-5$1.10$3.52$0.22$1.705200K
GLM-4.5 AirX (Z AI)Zhipu$1.10$4.50$0.22$1.95128K
GPT-5.1-InstantOpenAI$1.10$9.00$0.11$3.075128K
Hermes 3 Llama 3.1 405b$1.10$3.00$1.575128K
OpenAI o3 mini$1.10$4.40$0.55$1.925200K
OpenAI o3-miniOpenAI$1.10$4.40$0.55$1.925200K
OpenAI o3-mini (High)OpenAI$1.10$4.40$0.55$1.925200K
OpenAI o3-mini (Low)OpenAI$1.10$4.40$0.55$1.925200K
OpenAI o4-miniOpenAI$1.10$4.40$0.55$1.925200K
OpenAI o4-mini highOpenAI$1.10$4.40$0.55$1.925200K
OpenAI: o1-miniOpenAI$1.10$4.40$0.55$1.925128K
Xiaomi MiMo-V2.5-Pro$1.10$3.30$0.22$1.651M
GLM 5.3 FP4Zhipu$1.12$4.40free$1.941M
Kimi K2 Thinking TurboKimi$1.15$8.00$0.15$2.8625262K
Llama-3.3-70B-InstructNVIDIA$1.15$1.15$1.15128K
NeoSmith Basic$1.17$4.37$0.22$1.971M
GLM-5.2Zhipu$1.1875$4.1562$0.2969$1.92971M
ai-56b-to-176b$1.20$1.20$1.20
cogito-671b-v2-p1$1.20$1.20$1.20164K
dbrx-instructDatabricks$1.20$1.20$1.2033K
deepseek-coder-v2-instructDeepSeek$1.20$1.20$1.2066K
deepseek-proverDeepSeek$1.20$1.20$1.20164K
GLM 5 TurboZhipu$1.20$4.00$0.24$1.90203K
GLM 5 Turbo$1.20$4.00$0.24$1.90200K
GLM 5V Turbo ThinkingZhipu$1.20$4.00$0.24$1.90203K
glm-5-codeZhipu$1.20$5.00$0.30$2.15200K
GLM-5.2Zhipu$1.20$4.20$0.26$1.95203K
GLM-5.2 (EU)Zhipu$1.20$4.20$0.26$1.951M
GLM-5.3 (EU)Zhipu$1.20$4.20$0.26$1.951M
Inkling$1.20$5.00$0.27$2.151M
llama3-1-405b$1.20$1.20$1.20128K
Mistral Large 3 675B Instruct 2512Mistral$1.20$1.20$1.20262K
mixtral-8x22bMistral$1.20$1.20$1.2066K
mixtral-8x22b-instruct-hfMistral$1.20$1.20$1.2066K
Qwen 3 Max ThinkingAlibaba$1.20$6.00$0.24$2.40256K
Qwen: QvQ MaxAlibaba$1.20$4.80$0.60$2.10128K
qwen2-5-72b-instruct-turboAlibaba$1.20$1.20$1.20131K
Qwen3 Max (EU)Alibaba$1.20$6.00$0.24$2.40262K
Qwen3 Max PreviewAlibaba$1.2002$6.001$0.6001$2.4004256K
o4-mini (EU)OpenAI$1.21$4.84$0.3025$2.1175200K
Cogito v2.1 671B$1.25$1.25$1.25164K
Gemini 2.5 Computer Use Preview 10-2025Google$1.25$10.00$3.4375131K
Gemini 2.5 ProGoogle$1.25$10.00$0.125$3.43751M
Gemini 2.5 Pro (EU)Google$1.25$10.00$0.31$3.43751M
GLM 5.2 TEEZhipu$1.25$3.95$0.125$1.9251M
GPT 5.1 CodexOpenAI$1.25$10.00$0.125$3.4375400K
GPT 5.1 ThinkingOpenAI$1.25$10.00$0.125$3.4375400K
GPT-5 Chat (latest)OpenAI$1.25$10.00$0.125$3.4375400K
GPT-5-CodexOpenAI$1.25$10.00$0.125$3.4375400K
gpt-5-search-apiOpenAI$1.25$10.00$0.125$3.4375272K
gpt-5-thinkingOpenAI$1.25$10.00$3.4375400K
GPT-5.1 (2025-11-13)OpenAI$1.25$10.00$0.125$3.4375400K
GPT-5.1 ChatOpenAI$1.25$10.00$0.125$3.4375128K
GPT-5.1 Codex Max$1.25$10.00$0.125$3.4375400K
Grok 4.20 (Non-Reasoning)xAI$1.25$2.50$0.20$1.56251M
Grok 4.20 (Reasoning)xAI$1.25$2.50$0.20$1.56251M
Grok 4.20 Non-Reasoning (Vertex AI (OpenAI-compatible))xAI$1.25$2.50$0.20$1.56252M
Grok 4.20 Reasoning (Vertex AI (OpenAI-compatible))xAI$1.25$2.50$0.20$1.56252M
Grok 4.3xAI$1.25$2.50$0.20$1.56251M
Kimi K2.7 Code (EU)Kimi$1.25$4.50$0.31$2.0625262K
Muse Spark 1.1Meta$1.25$4.25$0.15$2.001M
Muse Spark 1.2Meta$1.25$4.25$0.15$2.001M
Muse Spark 1.3Meta$1.25$4.25$0.15$2.001M
OpenAI GPT-5$1.25$10.00$0.125$3.4375400K
OpenAI/GPT-5OpenAI$1.25$10.00$0.125$3.4375400K
GLM-5.2 CavemanZhipu$1.254$5.016$0.3135$2.19451M
GLM-5.2 Caveman LiteZhipu$1.254$5.016$0.3135$2.19451M
GLM-5.2 Caveman UltraZhipu$1.254$5.016$0.3135$2.19451M
GLM-5.2 HoneyZhipu$1.254$5.016$0.3135$2.19451M
GLM-5.2 Honey LiteZhipu$1.254$5.016$0.3135$2.19451M
GLM-5.2 Honey UltraZhipu$1.254$5.016$0.3135$2.19451M
GLM-5.2 PonytailZhipu$1.254$5.016$0.3135$2.19451M
GLM-5.2 Ponytail LiteZhipu$1.254$5.016$0.3135$2.19451M
GLM-5.2 Ponytail UltraZhipu$1.254$5.016$0.3135$2.19451M
Llama-3.3-70B-InstructMeta$1.254$1.254$0.025$1.254100K
Gemini 2.0 Pro 1206Google$1.258$4.998$0.629$2.1932.1M
Gemini 2.0 Pro ReasonerGoogle$1.292$4.998$0.323$2.2185128K
Qwen 3.6 Max PreviewAlibaba$1.30$7.80$0.13$2.925240K
titan-text-expressAmazon$1.30$1.70$1.4042K
MiMo-V2.5-Pro-UltraSpeed$1.305$2.61$0.0108$1.63131M
DeepSeek V4 Pro 0813DeepSeek$1.3359$4.0077$0.0445$2.00381M
DeepSeek-R1DeepSeek$1.35$5.40$2.3625128K
deepseek-r1-0528-maasDeepSeek$1.35$5.40$2.362565K
mai-ds-r1$1.35$5.40$2.3625128K
GPT-5 (EU)OpenAI$1.375$11.00$0.1375$3.7813400K
GPT-5.1 (EU)OpenAI$1.375$11.00$0.1375$3.7813400K
DeepSeek R1 Qwen AbliteratedDeepSeek$1.40$1.40$0.70$1.4016K
GLM 5.1Zhipu$1.40$4.40free$2.15203K
GLM 5.2$1.40$4.40$0.26$2.151M
glm-5-1-nvfp4-mtpZhipu$1.40$4.40free$2.15203K
GLM-5.1Zhipu$1.40$4.40$0.26$2.15200K
GLM-5.1 (EU)Zhipu$1.40$4.40$1.40$2.15200K
GLM-5.2Alibaba$1.40$4.40$0.26$2.151M
GLM-5.2Mistral$1.40$4.40$0.14$2.151M
GLM-5.3Zhipu$1.40$4.40$0.26$2.151M
GLM 5.2 ShortZhipu$1.45$4.50$0.145$2.2125200K
GLM 5.2 Short FastZhipu$1.45$4.50$0.145$2.2125200K
L3 70B Euryale V2.1 $1.48$1.48$1.488K
l3-70b-euryale$1.48$1.48$1.488K
L31 70B Euryale V2.2$1.48$1.48$1.488K
l31-70b-euryale$1.48$1.48$1.488K
Codex MiniOpenAI$1.50$6.00$0.375$2.625200K
command-textCohere$1.50$2.00$1.6254K
Gemini 3.5 FlashGoogle$1.50$9.00$0.15$3.3751M
Gemini 3.5 Flash (Vertex AI, US)Google$1.50$9.00$0.15$3.3751M
Gemini 3.5 Flash ThinkingGoogle$1.50$9.00$0.15$3.3751M
Gemini Omni Flash PreviewGoogle$1.50$17.50$5.50131K
gemini-omni-1-1-flashGoogle$1.50$9.00$3.375131K
GLM 5.1 Thinking TEEZhipu$1.50$5.25$0.30$2.4375203K
GLM 5V Turbo$1.50$5.00$0.30$2.375200K
GPT 5.4 Mini (Fast)OpenAI$1.50$9.00$0.15$3.375400K
GPT-3.5 Turbo InstructOpenAI$1.50$2.00$1.6254K
gpt-35-turbo-instructOpenAI$1.50$2.00$1.6254K
GPT-5.6OpenAI$1.50$12.00$0.15$4.125372K
Greg 2 Super$1.50$5.00$0.25$2.375229K
Interfaze Beta$1.50$3.50$2.001M
macaron-v1-venti$1.50$4.50$0.30$2.251M
Mistral Medium 3.5 ThinkingMistral$1.50$7.50$0.75$3.00256K
mistral-vibe-cliMistral$1.50$7.50$0.15$3.00262K
mistral-vibe-cli-with-toolsMistral$1.50$7.50$0.15$3.00262K
Xpersona Frieren 1$1.50$6.00$0.15$2.6251M
fw-glm-5-1$1.54$4.84$0.286$2.365203K
fw-glm-5-2$1.54$4.84$0.15$2.3651M
GLM 5.1$1.54$4.84$0.286$2.365200K
command-a-reasoningCohere$1.56$1.56$1.56256K
command-a-visionCohere$1.56$1.56$1.56256K
command-plusCohere$1.56$1.56$1.56128K
Qwen2.5-Max-2025-01-25Alibaba$1.5997$6.392$0.7998$2.7978128K
ftOpenAI$1.60$1.60$1.875$1.6016K
Gemini-3-ProGoogle$1.60$9.60$0.16$3.601M
gemini-deep-researchGoogle$1.60$9.60$3.601M
GPT-5.2-InstantOpenAI$1.60$13.00$0.16$4.45128K
GPT-5.3-InstantOpenAI$1.60$13.00$0.16$4.45128K
Gemini 3.5 Flash (EU)Google$1.65$9.90$0.165$3.71251M
mistral-medium-3-5@euMistral$1.65$8.25$1.65$3.30262K
Kimi K2.6 FastKimi$1.655$8.778$0.30$3.4358262K
DeepSeek-V4-Pro-ELDeepSeek$1.67$3.33$2.0851M
DeepSeek V4 Pro (Alibaba Cloud)$1.69$3.38$0.13$2.11251M
DeepSeek V4 Pro (EU)DeepSeek$1.75$3.50$0.44$2.18751M
DeepSeek V4 Pro 0813 (EU)DeepSeek$1.75$3.50$0.44$2.18751M
GLM 5.3$1.75$5.50$0.325$2.68751M
GPT 5.2 CodexOpenAI$1.75$14.00$0.175$4.8125400K
GPT 5.3 CodexOpenAI$1.75$14.00$0.175$4.8125400K
GPT-5.2 ChatOpenAI$1.75$14.00$0.175$4.8125128K
GPT-5.3 Chat (latest)OpenAI$1.75$14.00$0.175$4.8125128K
GPT-5.3 Codex XHighOpenAI$1.75$14.00$4.8125400K
Llama 3.3 70B$1.75$2.75$1.75$2.00128K
OpenAI GPT-5.2$1.75$14.00$0.175$4.8125400K
OpenAI GPT-5.3 Codex$1.75$14.00$0.175$4.8125400K
OpenAI/GPT-5.2OpenAI$1.75$14.00$0.175$4.8125400K
Qwen3-VL 235BAlibaba$1.76$2.05$1.8325218K
ai-81-1b-110b$1.80$1.80$1.80
allam-1-13b-instructIBM$1.80$1.80$1.808K
Cogito v1 Preview Qwen 32B$1.80$1.80$0.90$1.80128K
o4-mini-deep-researchOpenAI$1.80$7.20$0.45$3.15200K
NeoSmith Pro$1.81$8.39$0.30$3.4551M
inkling-256k$1.87$4.68$0.374$2.5725262K
Kimi K2.7 Code High-SpeedKimi$1.90$8.00$0.32$3.425262K
mt0-xxlIBM$1.908$1.908$1.9084K
mt0-xxl-13bIBM$1.908$1.908$1.9084K
codellama-7b-instruct-awq$1.923$1.923$1.9234K
llama-2-7b-chat-fp16Meta$1.923$1.923$1.9233K
llama-2-7b-chat-int8Meta$1.923$1.923$1.9232K
fw-deepseek-v4-pro$1.925$3.828$0.165$2.40071M
Kimi K3 FlexKimi$1.95$9.75$0.195$3.901M
llama2-70b-chatMeta$1.95$2.56$2.10254K
Gemini 2.0 Pro 0205Google$1.989$7.956$0.4973$3.48082.1M
Anthropic Claude Sonnet 5$2.00$10.00$0.20$4.001M
Celeris 1$2.00$6.00$1.00$3.008K
Claude Sonnet 5Anthropic$2.00$10.00$0.20$4.001M
Claude Sonnet 5 ThinkingAnthropic$2.00$10.00$0.20$4.001M
Claude Sonnet LatestAnthropic$2.00$10.00$0.20$4.001M
davinci-002OpenAI$2.00$2.00$2.0016K
Deep Research Max Preview (Apr-21-2026)Google$2.00$12.00$0.20$4.50131K
Deep Research Preview (Apr-21-2026)Google$2.00$12.00$0.20$4.50131K
Fugu Max$2.00$6.00$0.25$3.001M
Gemini 3 Pro ImageGoogle$2.00$12.00$0.20$4.5066K
Gemini 3.1 Pro (Preview Custom Tools)Google$2.00$12.00$0.20$4.501M
Gemini 3.1 Pro (Preview High)Google$2.00$12.00$0.20$4.501M
Gemini 3.1 Pro (Preview Low)Google$2.00$12.00$0.20$4.501M
Gemini 3.1 Pro (Preview)Google$2.00$12.00$0.20$4.501M
Gemini Pro LatestGoogle$2.00$12.00$0.20$4.501M
gemini-robotics-er-2Google$2.00$10.00$0.20$4.00131K
gemini-robotics-er-2-streamingGoogle$2.00$10.00$4.00
Gemma 4Google$2.00$5.00$0.50$2.75131K
GPT 4.1OpenAI$2.00$8.00$0.50$3.501M
GPT 5.6 Sol ProOpenAI$2.00$10.00$0.20$4.001.1M
GPT 5.6 TerraOpenAI$2.00$12.00$0.20$4.501.1M
GPT 5.6 Terra ProOpenAI$2.00$12.00$0.20$4.501.1M
GPT Chat LatestOpenAI$2.00$10.00$0.20$4.001.1M
GPT Sol LatestOpenAI$2.00$10.00$0.20$4.001.1M
GPT Terra LatestOpenAI$2.00$12.00$0.20$4.501.1M
GPT-5.6 SolOpenAI$2.00$10.00$0.20$4.001.1M
GPT-Image-1-MiniOpenAI$2.00$8.00$0.20$3.500
Grok 4.20xAI$2.00$6.00$1.00$3.002M
Grok 4.20 Beta Non-Reasoning (0309) (xAI)xAI$2.00$6.00$0.20$3.002M
Grok 4.20 Beta Reasoning (0309) (xAI)xAI$2.00$6.00$0.20$3.002M
Grok 4.20 Multi-AgentxAI$2.00$6.00$1.00$3.002M
Grok 4.5xAI$2.00$6.00$0.50$3.00500K
Grok 4.6xAI$2.00$6.00$0.50$3.00500K
Grok LatestxAI$2.00$6.00$0.50$3.00500K
grok-2xAI$2.00$10.00$4.00131K
grok-2-visionxAI$2.00$10.00$4.0033K
grok-4.1xAI$2.00$10.00$4.00200K
grok-4.2-betaxAI$2.00$6.00$0.20$3.002M
grok-buildxAI$2.00$6.00$0.30$3.00500K
jamba-1-5-largeAI21$2.00$8.00$3.50256K
jamba-1-5-large-001AI21$2.00$8.00$3.50256K
jamba-large-1-6AI21$2.00$8.00$3.50256K
jamba-large-1-7AI21$2.00$8.00$3.50256K
Kimi LatestKimi$2.00$10.00$0.20$4.001M
kimi-latest-128kKimi$2.00$5.00$0.15$2.75131K
llama3-2-90b-instructMeta$2.00$2.00$2.00128K
LucidNova RF1 100B$2.00$5.00$2.75120K
LucidQuery Nexus Coder$2.00$5.00$2.75250K
Magistral Medium (latest)Mistral$2.00$5.00$2.00$2.75128K
magistral-medium-1-2Mistral$2.00$5.00$2.7540K
mai-thinking-1$2.00$8.00$0.20$3.50256K
Mistral Large (latest)Mistral$2.00$6.00$3.00262K
Mistral Large Instruct 2411Mistral$2.00$6.00$1.00$3.00128K
mistral-large-2411-001Mistral$2.00$6.00$3.00128K
Mixtral 8x22BMistral$2.00$6.00$0.20$3.0066K
Mixtral 8x22BMistral$2.00$6.00$3.0064K
moonshot-v1-128kKimi$2.00$5.00$2.75131K
moonshot-v1-128k-visionKimi$2.00$5.00$2.75131K
moonshot-v1-autoKimi$2.00$5.00$2.75131K
Muse Glimmer 30B (TR)$2.00$5.00$0.50$2.75131K
Nano-Banana-ProGoogle$2.00$12.00$0.20$4.5066K
o4-mini (Fast)OpenAI$2.00$8.00$0.50$3.50200K
OpenAI GPT-4.1$2.00$8.00$0.50$3.501M
OpenAI GPT-5.6 Terra$2.00$12.00$0.20$4.501.1M
OpenAI o3OpenAI$2.00$8.00$1.00$3.50200K
OpenAI o3$2.00$8.00$0.50$3.50200K
OpenAI: GPT-5.6 Sol (50% off)OpenAI$2.00$10.00$0.20$4.001.1M
Pixtral Large (25.02) (EU)Mistral$2.00$6.00$3.00128K
Qwen3.8 2.4T A95BAlibaba$2.00$6.00$0.50$3.00262K
Qwen3.8 2.4T A95B (NVFP4)Alibaba$2.00$6.00$0.20$3.00262K
Qwen3.8 Max ThinkingAlibaba$2.00$6.00$0.25$3.00991K
Sonar Reasoning Pro (Perplexity)Perplexity$2.00$8.00$3.50128K
sonar-deep-researchPerplexity$2.00$8.00$3.50128K
EVA Llama 3.33 70B$2.006$2.006$1.003$2.00633K
EVA-LLaMA-3.33-70B-v0.1$2.006$2.006$1.003$2.00633K
Magnum V2 72B$2.006$2.992$1.003$2.252516K
Magnum v4 72B$2.006$2.992$1.003$2.252516K
Mistral Large 2411Mistral$2.006$6.001$0.20$3.0047128K
Llama 3.1 405BMeta$2.0265$2.0265$2.0265131K
Step 1 (32K)$2.05$9.59$0.41$3.93533K
Mistral Medium 3.5Mistral$2.052$10.26$4.104262K
fw-glm-5-2-fast$2.10$6.60$0.21$3.2251M
GLM 5.3 FastZhipu$2.10$6.60$0.21$3.2251M
glm-5-2-fast-usZhipu$2.10$6.60$0.21$3.2251M
nova-2-proAmazon$2.1875$17.50$0.5469$6.01561M
GPT-5.2$2.19$17.50$0.219$6.0175256K
GPT-5.2 Codex$2.19$17.50$0.219$6.0175256K
GPT-5.3 Codex$2.19$17.50$0.219$6.0175400K
Claude Sonnet 5 (EU)Anthropic$2.20$11.00$0.22$4.401M
GLM-4.5 X (Z AI)Zhipu$2.20$8.90$0.45$3.875128K
GLM-5.2 Turbo (SCX.ai)Zhipu$2.20$6.50$0.45$3.2751M
GPT-4.1 (EU)OpenAI$2.20$8.80$0.55$3.851M
GPT-4o-AugOpenAI$2.20$9.00$1.10$3.90128K
GPT-4o-SearchOpenAI$2.20$9.00$1.25$3.90128K
GPT-5.6 Terra (EU)OpenAI$2.20$13.20$0.22$4.951.1M
zai-glm-4-6$2.25$2.75$2.375128K
GLM-5.2$2.31$6.00$3.232596K
gov-anthropic-claude-sonnet-5$2.40$12.00$0.24$4.801M
NeoSmith Maestro$2.40$12.00$0.35$4.801M
AGI-01 Swift$2.50$15.00$5.625300K
Amazon: Nova Premier 1.0Amazon$2.50$12.50$0.625$5.001M
Cohere Command A (08/2025)Cohere$2.50$10.00$1.25$4.375256K
Command ACohere$2.50$10.00$4.375256K
Command A$2.50$10.00$4.375131K
Command A 03-2025Cohere$2.50$10.00$4.375256K
Command A PlusCohere$2.50$10.00$4.375128K
Command A TranslateCohere$2.50$10.00$4.3758K
Command A VisionCohere$2.50$10.00$4.375128K
Gemini 2.5 Pro Experimental 0325Google$2.50$10.00$0.25$4.3751M
Gemini 2.5 Pro Preview 0325Google$2.50$10.00$0.25$4.3751M
Gemini 2.5 Pro Preview 0506Google$2.50$10.00$0.25$4.3751M
Gemini 2.5 Pro Preview 0605Google$2.50$10.00$0.25$4.3751M
GPT 5.1 Codex MaxOpenAI$2.50$20.00$0.25$6.875400K
GPT 5.1 Thinking (Fast)OpenAI$2.50$20.00$0.25$6.875400K
GPT 5.4OpenAI$2.50$15.00$0.25$5.6251.1M
GPT-4o (2024-08-06)OpenAI$2.50$10.00$1.25$4.375128K
gpt-4o-audioOpenAI$2.50$10.00$4.375128K
gpt-4o-mini-audioOpenAI$2.50$10.00$4.375128K
GPT-5 (Fast)OpenAI$2.50$20.00$0.25$6.875400K
GPT-5.4 (EU)OpenAI$2.50$15.00$0.25$5.6251.1M
GPT-5.6 Sol$2.50$12.50$0.25$5.001M
GPT-5.6 Sol Pro$2.50$12.50$0.25$5.001M
GPT-5.6 Terra$2.50$15.00$0.25$5.6251M
GPT-5.6 Terra Pro$2.50$15.00$0.25$5.6251M
gpt-audio-1-5OpenAI$2.50$10.00$4.375128K
Llama-xLAM-2 70B fc-rMeta$2.50$2.50$1.25$2.50128K
Ministral 3 14B Reasoning 2512Mistral$2.50$1.70$2.30262K
nova-premier-v1Amazon$2.50$12.50$5.001M
OpenAI GPT-4o$2.50$10.00$1.25$4.375128K
OpenAI GPT-5.4$2.50$15.00$0.25$5.625400K
OpenAI: GPT AudioOpenAI$2.50$10.00$4.375128K
OpenAI: GPT-5 Image MiniOpenAI$2.50$2.00$0.25$2.375400K
Palmyra X4$2.50$10.00$4.375128K
Palmyra X4 (US)Amazon$2.50$10.00$4.375123K
Qwen 3.8 2.4TAlibaba$2.50$7.50$0.3125$3.75262K
Qwen 3.8 MaxAlibaba$2.50$7.50$0.3125$3.751M
Qwen3.8 2.4T A95B (EU)Alibaba$2.50$6.00$0.63$3.3751M
swe-1-7-lightning$2.50$12.50$1.00$5.00
Claude-Sonnet-3.5Anthropic$2.60$13.00$0.26$5.20189K
Claude-Sonnet-3.5-JuneAnthropic$2.60$13.00$0.26$5.20189K
Claude-Sonnet-3.7Anthropic$2.60$13.00$0.26$5.20197K
gov-xai-grok-4-6$2.64$7.92$0.66$3.96500K
meta-llama-3-1-70b-instructMeta$2.68$3.54$2.895128K
Qwen 3.7 MaxAlibaba$2.70$8.05$0.27$4.03751M
glm-5-1-fastZhipu$2.80$8.80$0.52$4.30203K
Cohere: Command R+Cohere$2.856$14.246$1.428$5.7035128K
roc$2.875$11.516$5.0352262K
Abliterated Model$3.00$3.00$0.30$3.00262K
AionLabs: Aion 3.0$3.00$6.00$0.75$3.75131K
Anthropic Claude 4.5 Sonnet$3.00$15.00$0.30$6.00200K
Anthropic Claude Sonnet 4.6$3.00$15.00$0.30$6.00200K
anthropic--claude-3-sonnet$3.00$15.00$0.30$6.00200K
anthropic--claude-4-sonnet$3.00$15.00$0.30$6.00200K
Anthropic: Claude 3.5 Sonnet v2Anthropic$3.00$15.00$0.30$6.00200K
Anthropic: Claude Sonnet 4Anthropic$3.00$15.00$0.30$6.001M
Claude 3.5 SonnetAnthropic$3.00$15.00$0.30$6.00200K
Claude 3.5 Sonnet$3.00$15.00$0.30$6.00200K
Claude 3.7 SonnetAnthropic$3.00$15.00$0.30$6.00200K
Claude 3.7 Sonnet$3.00$15.00$0.30$6.00200K
Claude 4 Sonnet ThinkingAnthropic$3.00$15.00$0.30$6.001M
Claude 4 Sonnet Thinking (32K)Anthropic$3.00$15.00$0.30$6.001M
Claude 4 Sonnet Thinking (64K)Anthropic$3.00$15.00$0.30$6.001M
Claude 4 Sonnet Thinking (8K)Anthropic$3.00$15.00$0.30$6.001M
Claude 4.5 SonnetAnthropic$3.00$15.00$0.30$6.00200K
Claude Sonnet 4$3.00$15.00$0.30$6.001M
Claude Sonnet 4 (latest) (EU)Anthropic$3.00$15.00$0.30$6.001M
Claude Sonnet 4.5Anthropic$3.00$15.00$0.30$6.00200K
Claude Sonnet 4.6Anthropic$3.00$15.00$0.30$6.001M
Claude Sonnet 4.6Anthropic$3.00$15.00$0.30$6.001M
Claude Sonnet 4.6 ThinkingAnthropic$3.00$15.00$0.30$6.001M
claude-3-sonnetAnthropic$3.00$15.00$0.30$6.00200K
claude-sonnet-4-1Anthropic$3.00$15.00$0.30$6.00200K
claude-sonnet-4-5-20250929-thinkingAnthropic$3.00$15.00$6.00200K
claude-sonnet-4-5-20250929-v1-0Anthropic$3.00$15.00$0.30$6.00200K
claude-sonnet-4-6-thinkingAnthropic$3.00$15.00$6.001M
Claudius$3.00$8.00$0.90$4.25256K
command-r-plusCohere$3.00$15.00$6.00128K
computer-useOpenAI$3.00$12.00$5.258K
DeepClaude$3.00$15.00$0.30$6.00128K
GLM5.2-Fast$3.00$10.25$0.50$4.81251M
gpt-35-turbo-16kOpenAI$3.00$4.00$3.2516K
GPT-5.5$3.00$18.00$0.30$6.751M
Greg 2 Ultra$3.00$10.00$0.50$4.75229K
Grok 3xAI$3.00$15.00$0.75$6.00131K
Grok 4 (xAI)xAI$3.00$15.00$0.75$6.00256K
Grok 4.2 FastxAI$3.00$9.00$4.502M
Grok 4.2 Fast Non ReasoningxAI$3.00$9.00$4.502M
j2-lightAI21$3.00$3.00$3.008K
Kimi K3Alibaba$3.00$15.00$0.30$6.001M
Kimi K3 (EU)Kimi$3.00$15.00$0.45$6.001M
Kimi K3 TEEKimi$3.00$15.00$0.30$6.001M
llama-v3-1-405b-instructMeta$3.00$3.00$3.00128K
MedGemma 4B$3.00$5.00$3.508K
OpenAI: GPT-3.5 Turbo 16kOpenAI$3.00$4.00$3.2516K
Perplexity: Sonar Pro SearchPerplexity$3.00$15.00$6.00200K
Qwen3.7 MaxAlibaba$3.00$9.00$0.50$4.501M
RouteLLM$3.00$15.00$6.00128K
Sonar Pro (Perplexity)Perplexity$3.00$15.00$6.00200K
v0-1.0-md$3.00$15.00$6.00128K
v0-1.5-md$3.00$15.00$6.00128K
yi-large01.AI$3.00$3.00$3.0033K
GPT-5.4$3.13$18.80$0.313$7.04751M
llama3-70b-instructMeta$3.18$4.20$3.4358K
Claude Sonnet 4.6Anthropic$3.196$15.94$0.32$6.3821M
Claude Sonnet 4.5 (latest) (EU)Anthropic$3.30$16.50$0.30$6.601M
Claude Sonnet 4.6 (EU)Anthropic$3.30$16.50$0.30$6.601M
fw-kimi-k3$3.30$16.50$0.33$6.601M
kimi-k3-usKimi$3.30$16.50$0.33$6.601M
Gemini 3.5 Live Translate PreviewGoogle$3.50$21.00$7.87516K
GPT 5.2 (Fast)OpenAI$3.50$28.00$0.35$9.625400K
GPT 5.3 Codex (Fast)OpenAI$3.50$28.00$0.35$9.625400K
GPT-4.1 (Fast)OpenAI$3.50$14.00$0.875$6.1251M
Llama 3.1 405B Instruct TurboMeta$3.50$3.50$3.50128K
o3 (Fast)OpenAI$3.50$14.00$0.875$6.125200K
gov-anthropic-claude-sonnet-4-5-20250929-v1-0$3.60$18.00$0.36$7.20200K
Inkling (256K)$3.74$9.36$0.748$5.145262K
Aion 3.0$3.75$7.50$0.9375$4.6875128K
daybreak-blueOpenAI$4.00$20.00$0.40$8.001.1M
GPT 5.6 Sol (Fast)OpenAI$4.00$20.00$0.40$8.001.1M
GPT 5.6 Terra (Fast)OpenAI$4.00$24.00$0.40$9.001.1M
gpt-daybreak-blueOpenAI$4.00$20.00$0.40$8.001.1M
gpt-realtimeOpenAI$4.00$16.00$0.40$7.0032K
GPT-Realtime-1.5OpenAI$4.00$16.00$0.40$7.000
gpt-realtime-2OpenAI$4.00$24.00$0.40$9.000
gpt-realtime-2.1OpenAI$4.00$24.00$0.40$9.00128K
OpenAI GPT-5.6 Sol$4.00$20.00$0.40$8.001.1M
Vision Medium$4.21$12.63$6.3151M
GPT-4o (Fast)OpenAI$4.25$17.00$2.125$7.4375128K
GPT-5.6 Sol (EU)OpenAI$4.40$22.00$0.44$8.801.1M
AGI-01 Frontier$4.50$22.00$8.875300K
ChatGPT-4o-LatestOpenAI$4.50$14.00$2.50$6.875128K
Kimi K3 FastKimi$4.50$22.50$0.45$9.001M
Kimi K3 Fast (Fireworks AI)Kimi$4.50$22.50$0.45$9.001M
DeepSeek R1 FastDeepSeek$4.998$6.987$2.499$5.4953128K
Abliterated Model Large$5.00$5.00$0.50$5.001M
Abliterated Model Large V2$5.00$5.00$0.50$5.001M
Anthropic Claude Opus 4.5$5.00$25.00$0.50$10.00200K
Anthropic Claude Opus 4.6$5.00$25.00$0.50$10.00200K
Anthropic Claude Opus 4.7$5.00$25.00$0.50$10.00200K
Anthropic Claude Opus 4.8$5.00$25.00$0.50$10.001M
Anthropic Claude Opus 5$5.00$25.00$0.50$10.001M
anthropic--claude-4.5-opus$5.00$25.00$0.50$10.00200K
anthropic--claude-4.6-opus$5.00$25.00$0.50$10.001M
anthropic--claude-4.7-opus$5.00$25.00$0.50$10.001M
anthropic--claude-4.8-opus$5.00$25.00$0.50$10.001M
Anthropic: Claude Opus 4.6Anthropic$5.00$25.00$0.50$10.001M
Anthropic: Claude Opus 4.7Anthropic$5.00$25.00$0.50$10.001M
Anthropic: Claude Opus 4.8Anthropic$5.00$25.00$0.50$10.001M
chatOpenAI$5.00$30.00$0.50$11.25272K
chatgpt-image-latestOpenAI$5.00$10.00$1.25$6.250
Claude 4.5 OpusAnthropic$5.00$25.00$0.50$10.00200K
Claude 4.5 OpusAnthropic$5.00$25.00$0.50$10.00200K
Claude 4.6 Opus ThinkingAnthropic$5.00$25.00$0.50$10.001M
Claude 4.7 OpusAnthropic$5.00$25.00$0.50$10.001M
Claude Opus 4.6Anthropic$5.00$25.00$0.50$10.001M
Claude Opus 4.6 ThinkingAnthropic$5.00$25.00$0.50$10.001M
Claude Opus 4.7Anthropic$5.00$25.00$0.50$10.001M
Claude Opus 4.7 ThinkingAnthropic$5.00$25.00$0.50$10.001M
Claude Opus 4.8Anthropic$5.00$25.00$0.50$10.001M
Claude Opus 4.8Anthropic$5.00$25.00$0.50$10.001M
Claude Opus 4.8Anthropic$5.00$25.00$0.50$10.00200K
Claude Opus 5Anthropic$5.00$25.00$0.50$10.001M
Claude Opus 5Anthropic$5.00$25.00$0.50$10.001M
Claude Opus LatestAnthropic$5.00$25.00$0.50$10.001M
claude-opus-4-7-thinkingAnthropic$5.00$25.00$10.001M
claude-opus-5-thinkingAnthropic$5.00$25.00$10.001M
Fugu Ultra$5.00$30.00$0.50$11.251M
Fugu Ultra v1.1$5.00$30.00$0.50$11.251M
Fugu Ultra v2$5.00$30.00$0.50$11.251M
Fugu Ultra v2.0 (Sakana AI)$5.00$30.00$0.50$11.251M
GPT 5.4 (Fast)OpenAI$5.00$30.00$0.50$11.251.1M
GPT 5.5OpenAI$5.00$30.00$0.50$11.251.1M
GPT Image 1$5.00$40.00$1.25$13.750
GPT Image 2.5 FlareOpenAI$5.00$30.00$1.25$11.250
GPT Image 2.5 SunburstOpenAI$5.00$30.00$1.25$11.250
GPT-5.5 (EU)OpenAI$5.00$30.00$0.50$11.251.1M
GPT-5.5 InstantOpenAI$5.00$30.00$0.50$11.25400K
GPT-Image-1OpenAI$5.00$40.00$1.25$13.75128K
gpt-image-1.5OpenAI$5.00$32.00$1.25$11.75128K
gpt-rosalind-researchOpenAI$5.00$25.00$0.50$10.00
grok-3-fastxAI$5.00$25.00$0.20$10.00131K
llama-3-1-405b-instruct-maasMeta$5.00$16.00$7.75128K
OpenAI GPT Image 1.5$5.00$10.00$1.00$6.250
OpenAI GPT-5.5$5.00$30.00$0.50$11.251M
Step 2 (16K)$5.21$16.44$1.04$8.017516K
Claude Opus 4.5 (latest)Anthropic$5.313$26.568$0.531$10.6268200K
Claude Opus 4.6Anthropic$5.313$26.561$0.531$10.6251M
llama3-1-405b-instructMeta$5.32$16.00$7.99128K
meta-llama-3-1-405b-instructMeta$5.33$16.00$5.00$7.9975128K
Claude Opus 4.7Anthropic$5.437$27.186$0.544$10.87421M
Claude Opus 4.8Anthropic$5.437$27.186$0.544$10.87421M
Claude Opus 4.5 (latest) (EU)Anthropic$5.50$27.50$0.55$11.00200K
Claude Opus 4.6 (EU)Anthropic$5.50$27.50$0.55$11.001M
Claude Opus 4.7 (EU)Anthropic$5.50$27.50$0.55$11.001M
Claude Opus 4.8 (EU)Anthropic$5.50$27.50$0.55$11.001M
Claude Opus 5 (EU)Anthropic$5.50$27.50$0.55$11.001M
gpt-4o-realtimeOpenAI$5.50$22.00$2.75$9.625128K
gpt-daybreak-blue-5-6-solOpenAI$5.50$33.00$0.55$12.3751.1M
gov-anthropic-claude-opus-4-8$6.00$30.00$0.60$12.001M
gov-anthropic-claude-opus-5$6.00$30.00$0.60$12.001M
GPT-5.5$6.25$37.50$0.625$14.06251M
Vision Large$7.37$22.11$11.0551M
Fugu Ultra v1.0$7.50$45.00$1.50$16.8751M
Web Answer$7.50$7.50$7.5033K
Qwen Deep ResearchAlibaba$7.742$23.367$11.64831M
claudeAnthropic$8.00$24.00$12.00100K
OpenAI GPT Image 2$8.00$30.00$13.500
OpenAI: GPT-5.4 Image 2OpenAI$8.00$15.00$2.00$9.75272K
o3-deep-researchOpenAI$9.00$36.00$2.20$15.75200K
GLM 4 Plus 0111Zhipu$9.996$9.996$4.998$9.996128K
Anthropic Claude Fable 5$10.00$50.00$1.00$20.001M
Anthropic Claude Fable 5.1$10.00$50.00$0.25$20.001M
Anthropic: Claude Fable 5Anthropic$10.00$50.00$1.00$20.001M
Claude Fable 5Anthropic$10.00$50.00$1.00$20.001M
Claude Fable 5Anthropic$10.00$50.00$1.00$20.001M
Claude Fable 5.1Anthropic$10.00$50.00$0.25$20.001M
Claude Fable 5.1Anthropic$10.00$50.00$0.25$20.001M
Claude Fable LatestAnthropic$10.00$50.00$0.25$20.001M
Claude Mythos 5Anthropic$10.00$50.00$1.00$20.001M
Claude Opus 4.8 (Fast)Anthropic$10.00$50.00$1.00$20.001M
Claude Opus 5Anthropic$10.00$50.00$1.00$20.001M
claude-mythos-5-1Anthropic$10.00$50.00$0.25$20.001M
Echo$10.00$50.00$20.00262K
GPT 6 AstraOpenAI$10.00$50.00$1.00$20.001.1M
GPT 6 Astra ProOpenAI$10.00$50.00$1.00$20.001.1M
GPT Astra LatestOpenAI$10.00$50.00$1.00$20.001.1M
GPT LatestOpenAI$10.00$50.00$1.00$20.001.1M
GPT-4 TurboOpenAI$10.00$30.00$15.00128K
GPT-4 Turbo VisionOpenAI$10.00$30.00$15.00128K
OpenAI GPT-6 Astra$10.00$50.00$1.00$20.001.1M
OpenAI: GPT-5 Image ($$$$)OpenAI$10.00$10.00$1.25$10.00400K
Qwen3-LiveTranslate Flash RealtimeAlibaba$10.00$10.00$10.0053K
text-unicorn$10.00$28.00$14.508K
text-unicorn-001$10.00$28.00$14.508K
Claude Fable 5 (EU)Anthropic$11.00$55.00$1.10$22.001M
Claude Fable 5.1 (EU)Anthropic$11.00$55.00$0.275$22.001M
gov-anthropic-claude-fable-5-1$12.00$60.00$0.30$24.001M
daybreak-redOpenAI$12.50$75.00$1.25$28.125400K
GPT 5.5 (Fast)OpenAI$12.50$75.00$1.25$28.1251M
gpt-5-5-cyberOpenAI$12.50$75.00$1.25$28.125
gpt-5-6-cyberOpenAI$12.50$75.00$1.25$28.125400K
GPT-6 Astra Pro$12.50$62.50$1.25$25.001.1M
gpt-daybreak-redOpenAI$12.50$75.00$1.25$28.125400K
j2-midAI21$12.50$12.50$12.508K
Anthropic Claude 4.1 Opus$15.00$75.00$1.50$30.00200K
anthropic--claude-4-opus$15.00$75.00$1.50$30.00200K
Anthropic: Claude Opus 4Anthropic$15.00$75.00$1.50$30.00200K
Claude 3 Opus$15.00$75.00$1.50$30.00200K
Claude 4 Opus ThinkingAnthropic$15.00$75.00$1.50$30.00200K
Claude 4 Opus Thinking (32K)Anthropic$15.00$75.00$1.50$30.00200K
Claude 4 Opus Thinking (8K)Anthropic$15.00$75.00$1.50$30.00200K
Claude 4.1 OpusAnthropic$15.00$75.00$1.50$30.00200K
Claude 4.1 OpusAnthropic$15.00$75.00$1.50$30.00200K
Claude 4.1 Opus Thinking (32K)Anthropic$15.00$75.00$1.50$30.00200K
Claude 4.1 Opus Thinking (8K)Anthropic$15.00$75.00$1.50$30.00200K
Claude Opus 4$15.00$75.00$1.50$30.00200K
claude-3-opusAnthropic$15.00$75.00$1.50$30.00200K
claude-opus-4-1-20250805-thinkingAnthropic$15.00$75.00$30.00200K
GPT 5 ProOpenAI$15.00$120.00$1.50$41.25400K
OpenAI o1OpenAI$15.00$60.00$7.50$26.25200K
OpenAI o1$15.00$60.00$7.50$26.25200K
v0-1.5-lg$15.00$75.00$30.00512K
j2-ultraAI21$18.80$18.80$18.808K
GPT-6 Astra (Fast)OpenAI$20.00$100.00$2.00$40.001.1M
GPT-5.2 Pro (Azure)OpenAI$21.00$168.00$57.75400K
OpenAI GPT-5.2 Pro$21.00$168.00$57.75400K
OpenAI o3-pro (2025-06-10)OpenAI$22.00$88.00$11.00$38.50200K
GPT-4-ClassicOpenAI$27.00$54.00$33.758K
GPT Pro Latest (GPT-5.5 Pro)OpenAI$30.00$180.00$67.501.1M
GPT-4 (Azure)OpenAI$30.00$60.00$37.508K
GPT-5.4 ProOpenAI$30.00$180.00$3.00$67.501.1M
GPT-5.5 ProOpenAI$30.00$180.00$3.00$67.501.1M
OpenAI GPT-5.4 Pro$30.00$180.00$67.501.1M
Universal Summarizer$30.00$30.00$30.0033K
GPT-5.4 Pro$37.50$225.00$84.3751M
GPT-5.5 Pro$37.50$225.00$84.3751M
gpt-4-32kOpenAI$60.00$120.00$75.0033K
gpt-4-5OpenAI$75.00$150.00$37.50$93.75128K
OpenAI o1 ProOpenAI$150.00$600.00$75.00$262.50200K

Common questions

How do you compare AI model prices?
Each row is one model. Input and output are US dollars per million tokens. Blended uses a 3:1 input to output mix. Cache-read is the listed prefix-cache price when a host publishes one.
What is a blended token price?
Blended is (3 × input + 1 × output) / 4. That mix matches a typical chat turn. It is a presentation choice. It is not a billed rate.
Why do two hosts list different prices for the same model?
A price belongs to a model and a host. This table shows the canonical listing. Open the model page to see every host.