Home / Pricing / Providers

LLM API pricing

Browse curated models with Exact/Approx tokenizer labels and official pricing links. Each model opens the same TokenCalculator calculator with that model preselected. Rates checked against official pages, then stamped on every model.

All providers

Same model, cheapest host

Open weight and hosted copies in this catalog, grouped when the same model is sold by more than one API. Sorted by how much the cheapest host saves on input versus the most expensive listing.

ModelHostInput / 1MOutput / 1M
DeepSeek R1DeepSeek$0.550/1M$2.19/1MCheapest input · Page · Cost
DeepSeek R1Fireworks$0.900/1M$0.900/1MPage · Cost
DeepSeek R1Together AI$3.00/1M$7.00/1MPage · Cost
DeepSeek V3DeepSeek$0.270/1M$1.10/1MCheapest input · Page · Cost
DeepSeek V3Fireworks$0.900/1M$0.900/1MPage · Cost
DeepSeek V3Together AI$1.25/1M$1.25/1MPage · Cost
Llama 3.3 70BGroq$0.590/1M$0.790/1MCheapest input · Page · Cost
Llama 3.3 70BTogether AI$0.880/1M$0.880/1MPage · Cost
Llama 3.3 70BFireworks$0.900/1M$0.900/1MPage · Cost
Mixtral 8x22BFireworks$0.900/1M$0.900/1MCheapest input · Page · Cost
Mixtral 8x22BTogether AI$1.20/1M$1.20/1MPage · Cost
Llama 3.1 8B InstantGroq$0.050/1M$0.080/1MCheapest input · Page · Cost
Llama 3.1 8B InstantTogether AI$0.180/1M$0.180/1MPage · Cost
Llama 3.1 8B InstantFireworks$0.200/1M$0.200/1MPage · Cost
Llama 4 MaverickFireworks$0.220/1M$0.880/1MCheapest input · Page · Cost
Llama 4 MaverickTogether AI$0.270/1M$0.850/1MPage · Cost
Llama 3.2 3BGroq$0.060/1M$0.060/1MCheapest input · Page · Cost
Llama 3.2 3BTogether AI$0.060/1M$0.060/1MPage · Cost
Llama 3.2 3BFireworks$0.100/1M$0.100/1MPage · Cost
Llama 3.1 70BTogether AI$0.880/1M$0.880/1MCheapest input · Page · Cost
Llama 3.1 70BFireworks$0.900/1M$0.900/1MPage · Cost

All model pricing

124 models · 10 providers · rates checked . Example column is 1000 input tokens and 500 output tokens. Official pages, not a live scrape.

Count
Gemini 1.5 Flash-8BGoogle1M$0.037/1M$0.150/1Mn/a$0.000112Approx
Command R7BCohere128K$0.037/1M$0.150/1Mn/a$0.000112Approx
Llama 3.2 1B (Groq)Groq128K$0.040/1M$0.040/1Mn/a$0.00006Approx
GPT-5 NanoOpenAI128K$0.050/1M$0.400/1M$0.005/1M$0.00025Exact
Llama 3.1 8B Instant (Groq)Groq128K$0.050/1M$0.080/1Mn/a$0.00009Approx
Mistral SmallMistral128K$0.060/1M$0.180/1Mn/a$0.00015Approx
Llama 3.2 3B (Groq)Groq128K$0.060/1M$0.060/1Mn/a$0.00009Approx
Llama 3.2 3B (Together)Together AI128K$0.060/1M$0.060/1Mn/a$0.00009Approx
Gemma 7B (Groq)Groq8K$0.070/1M$0.070/1Mn/a$0.000105Approx
Gemini 1.5 FlashGoogle1M$0.075/1M$0.300/1M$0.019/1M$0.000225Approx
Gemini 2.0 Flash-LiteGoogle1M$0.075/1M$0.300/1M$0.019/1M$0.000225Approx
GPT-4.1 NanoOpenAI1M$0.100/1M$0.400/1M$0.025/1M$0.0003Exact
Gemini 2.0 FlashGoogle1M$0.100/1M$0.400/1M$0.025/1M$0.0003Approx
Gemini 2.5 Flash-LiteGoogle1M$0.100/1M$0.400/1M$0.010/1M$0.0003Approx
Llama 3.2 3B (Fireworks)Fireworks128K$0.100/1M$0.100/1Mn/a$0.00015Approx
Llama 4 Scout (Groq)Groq128K$0.110/1M$0.340/1Mn/a$0.00028Approx
DeepSeek CoderDeepSeek128K$0.140/1M$0.280/1Mn/a$0.00028Approx
DeepSeek V4 FlashDeepSeek1M$0.140/1M$0.280/1M$0.003/1M$0.00028Approx
DeepSeek VLDeepSeek4K$0.140/1M$0.280/1Mn/a$0.00028Approx
GPT-4o miniOpenAI128K$0.150/1M$0.600/1M$0.075/1M$0.00045Exact
Ministral 8BMistral128K$0.150/1M$0.150/1Mn/a$0.000225Approx
Mistral NemoMistral128K$0.150/1M$0.150/1Mn/a$0.000225Approx
Pixtral 12BMistral128K$0.150/1M$0.150/1Mn/a$0.000225Approx
Command RCohere128K$0.150/1M$0.600/1Mn/a$0.00045Approx
Command R (08-2024)Cohere128K$0.150/1M$0.600/1Mn/a$0.00045Approx
Llama 3.2 11B Vision (Groq)Groq128K$0.180/1M$0.180/1Mn/a$0.00027Approx
Llama 3.1 8B (Together)Together AI128K$0.180/1M$0.180/1Mn/a$0.00027Approx
GPT-5.6 LunaOpenAI1.1M$0.200/1M$1.20/1M$0.020/1M$0.0008Exact
Gemma 3 27BGoogle128K$0.200/1M$0.400/1Mn/a$0.0004Approx
Grok 2 MinixAI131K$0.200/1M$0.500/1Mn/a$0.00045Approx
Grok 4 FastxAI256K$0.200/1M$0.500/1Mn/a$0.00045Approx
Mistral SabaMistral33K$0.200/1M$0.600/1Mn/a$0.0005Approx
Gemma 2 9B (Groq)Groq8K$0.200/1M$0.200/1Mn/a$0.0003Approx
Llama Guard 3 8B (Groq)Groq8K$0.200/1M$0.200/1Mn/a$0.0003Approx
Mistral 7B (Together)Together AI33K$0.200/1M$0.200/1Mn/a$0.0003Approx
Llama 3.1 8B (Fireworks)Fireworks128K$0.200/1M$0.200/1Mn/a$0.0003Approx
MythoMax L2 13B (Fireworks)Fireworks4K$0.200/1M$0.200/1Mn/a$0.0003Approx
Llama 4 Maverick (Fireworks)Fireworks1M$0.220/1M$0.880/1Mn/a$0.00066Approx
Mixtral 8x7B (Groq)Groq33K$0.240/1M$0.240/1Mn/a$0.00036Approx
GPT-5 MiniOpenAI128K$0.250/1M$2.00/1M$0.025/1M$0.00125Exact
Claude 3 HaikuAnthropic200K$0.250/1M$1.25/1M$0.030/1M$0.000875Approx
Gemini 3.1 Flash-LiteGoogle1M$0.250/1M$1.50/1M$0.025/1M$0.001Approx
Mistral TinyMistral33K$0.250/1M$0.250/1Mn/a$0.000375Approx
DeepSeek V3DeepSeek128K$0.270/1M$1.10/1M$0.070/1M$0.00082Approx
Llama 4 Maverick (Together)Together AI1M$0.270/1M$0.850/1Mn/a$0.000695Approx
DeepSeek ChatDeepSeek128K$0.280/1M$0.420/1M$0.028/1M$0.00049Approx
QwQ 32B (Groq)Groq128K$0.290/1M$0.390/1Mn/a$0.000485Approx
Qwen3 32B (Groq)Groq131K$0.290/1M$0.590/1Mn/a$0.000585Approx
Gemini 2.5 FlashGoogle1M$0.300/1M$2.50/1M$0.030/1M$0.00155Approx
DeepSeek R1 Distill Qwen 32BDeepSeek128K$0.300/1M$0.600/1Mn/a$0.0006Approx
Grok 3 MinixAI131K$0.300/1M$0.500/1M$0.075/1M$0.00055Approx
Command LightCohere4K$0.300/1M$0.600/1Mn/a$0.0006Approx
Qwen2.5 7B (Together)Together AI33K$0.300/1M$0.300/1Mn/a$0.00045Approx
GPT-4.1 MiniOpenAI1M$0.400/1M$1.60/1M$0.100/1M$0.0012Exact
Mistral Medium 3Mistral128K$0.400/1M$2.00/1Mn/a$0.0014Approx
DeepSeek V4 ProDeepSeek1M$0.435/1M$0.870/1M$0.004/1M$0.00087Approx
GPT-3.5 TurboOpenAI16K$0.500/1M$1.50/1Mn/a$0.00125Exact
Gemini 1.0 ProGoogle33K$0.500/1M$1.50/1Mn/a$0.00125Approx
Gemini 3 FlashGoogle1M$0.500/1M$3.00/1M$0.050/1M$0.002Approx
Mistral Large 3Mistral128K$0.500/1M$1.50/1Mn/a$0.00125Approx
DeepSeek R1DeepSeek128K$0.550/1M$2.19/1M$0.140/1M$0.001645Approx
DeepSeek ReasonerDeepSeek128K$0.550/1M$2.19/1M$0.140/1M$0.001645Approx
Llama 3.3 70B (Groq)Groq128K$0.590/1M$0.790/1Mn/a$0.000985Approx
Llama 3.3 70B SpecDec (Groq)Groq8K$0.590/1M$0.990/1Mn/a$0.001085Approx
Open Mixtral 8x7BMistral33K$0.700/1M$0.700/1Mn/a$0.00105Approx
DeepSeek R1 Distill Llama 70B (Groq)Groq128K$0.750/1M$0.990/1Mn/a$0.001245Approx
Claude 3.5 HaikuAnthropic200K$0.800/1M$4.00/1M$0.080/1M$0.0028Approx
Qwen2.5 Coder 32B (Together)Together AI33K$0.800/1M$0.800/1Mn/a$0.0012Approx
Llama 3.1 70B (Together)Together AI128K$0.880/1M$0.880/1Mn/a$0.00132Approx
Llama 3.3 70B (Together)Together AI128K$0.880/1M$0.880/1Mn/a$0.00132Approx
DeepSeek R1 (Fireworks)Fireworks128K$0.900/1M$0.900/1Mn/a$0.00135Approx
DeepSeek V3 (Fireworks)Fireworks128K$0.900/1M$0.900/1Mn/a$0.00135Approx
Llama 3.1 70B (Fireworks)Fireworks128K$0.900/1M$0.900/1Mn/a$0.00135Approx
Llama 3.3 70B (Fireworks)Fireworks128K$0.900/1M$0.900/1Mn/a$0.00135Approx
Mixtral 8x22B (Fireworks)Fireworks66K$0.900/1M$0.900/1Mn/a$0.00135Approx
Qwen2.5 32B (Fireworks)Fireworks33K$0.900/1M$0.900/1Mn/a$0.00135Approx
Qwen2.5 72B (Fireworks)Fireworks33K$0.900/1M$0.900/1Mn/a$0.00135Approx
Claude Haiku 4.5Anthropic200K$1.00/1M$5.00/1M$0.100/1M$0.0035Approx
CodestralMistral256K$1.00/1M$3.00/1Mn/a$0.0025Approx
Command NightlyCohere128K$1.00/1M$2.00/1Mn/a$0.002Approx
o1-miniOpenAI128K$1.10/1M$4.40/1Mn/a$0.0033Exact
o3-miniOpenAI200K$1.10/1M$4.40/1M$0.550/1M$0.0033Exact
o4-miniOpenAI200K$1.10/1M$4.40/1M$0.275/1M$0.0033Exact
Mixtral 8x22B (Together)Together AI66K$1.20/1M$1.20/1Mn/a$0.0018Approx
Qwen2.5 72B (Together)Together AI33K$1.20/1M$1.20/1Mn/a$0.0018Approx
GPT-5OpenAI400K$1.25/1M$10.00/1M$0.125/1M$0.00625Exact
Gemini 1.5 ProGoogle2M$1.25/1M$5.00/1M$0.313/1M$0.00375Approx
Gemini 2.0 Pro ExpGoogle2M$1.25/1M$5.00/1Mn/a$0.00375Approx
Gemini 2.5 ProGoogle1M$1.25/1M$10.00/1M$0.125/1M$0.00625Approx
DeepSeek V3 (Together)Together AI128K$1.25/1M$1.25/1Mn/a$0.001875Approx
GPT-4.1OpenAI1M$2.00/1M$8.00/1M$0.500/1M$0.006Exact
GPT-4.1 (2025-04-14)OpenAI1M$2.00/1M$8.00/1M$0.500/1M$0.006Exact
GPT-5.6 TerraOpenAI1.1M$2.00/1M$12.00/1M$0.200/1M$0.008Exact
o3OpenAI200K$2.00/1M$8.00/1M$0.500/1M$0.006Exact
Claude Sonnet 5Anthropic1M$2.00/1M$10.00/1M$0.200/1M$0.007Approx
Gemini 3.1 ProGoogle1M$2.00/1M$12.00/1M$0.200/1M$0.008Approx
Grok 2xAI131K$2.00/1M$10.00/1Mn/a$0.007Approx
Grok 2 VisionxAI33K$2.00/1M$10.00/1Mn/a$0.007Approx
Grok 4.6xAI500K$2.00/1M$6.00/1M$0.500/1M$0.005Approx
Mistral Large (2407)Mistral128K$2.00/1M$6.00/1Mn/a$0.005Approx
Open Mixtral 8x22BMistral66K$2.00/1M$6.00/1Mn/a$0.005Approx
GPT-4oOpenAI128K$2.50/1M$10.00/1M$1.25/1M$0.0075Exact
GPT-4o (2024-08-06)OpenAI128K$2.50/1M$10.00/1M$1.25/1M$0.0075Exact
Command ACohere256K$2.50/1M$10.00/1Mn/a$0.0075Approx
Command R+Cohere128K$2.50/1M$10.00/1Mn/a$0.0075Approx
Command R+ (08-2024)Cohere128K$2.50/1M$10.00/1Mn/a$0.0075Approx
Claude 3.5 SonnetAnthropic200K$3.00/1M$15.00/1M$0.300/1M$0.0105Approx
Claude 3 SonnetAnthropic200K$3.00/1M$15.00/1M$0.300/1M$0.0105Approx
Claude Sonnet 4.6Anthropic1M$3.00/1M$15.00/1M$0.300/1M$0.0105Approx
Grok 3xAI131K$3.00/1M$15.00/1M$0.750/1M$0.0105Approx
Grok 4xAI256K$3.00/1M$15.00/1Mn/a$0.0105Approx
DeepSeek R1 (Together)Together AI128K$3.00/1M$7.00/1Mn/a$0.0065Approx
ChatGPT-4o LatestOpenAI128K$5.00/1M$15.00/1M$2.50/1M$0.0125Exact
GPT-5.6 SolOpenAI1.1M$5.00/1M$30.00/1M$0.500/1M$0.02Exact
Claude Opus 4.6Anthropic1M$5.00/1M$25.00/1M$0.500/1M$0.0175Approx
Claude Opus 4.8Anthropic1M$5.00/1M$25.00/1M$0.500/1M$0.0175Approx
Grok BetaxAI131K$5.00/1M$15.00/1Mn/a$0.0125Approx
Grok Vision BetaxAI8K$5.00/1M$15.00/1Mn/a$0.0125Approx
Claude 2.1Anthropic200K$8.00/1M$24.00/1Mn/a$0.02Approx
GPT-4 TurboOpenAI128K$10.00/1M$30.00/1M$5.00/1M$0.025Exact
o1OpenAI200K$15.00/1M$60.00/1M$7.50/1M$0.045Exact
o1-previewOpenAI128K$15.00/1M$60.00/1Mn/a$0.045Exact
Claude 3 OpusAnthropic200K$15.00/1M$75.00/1M$1.50/1M$0.0525Approx
GPT-4OpenAI8K$30.00/1M$60.00/1Mn/a$0.06Exact

Official pricing sources