LLM API pricing

Compare per-token prices across LLM API providers.

3,516
Chat models
18
Providers
Free
Lowest input / 1M tokens
10.5M
Largest context

LLM market heatmap

3,582 models grouped by vendor — click a vendor, then a family to filter the catalog

DEAL% · listings-weighted · signed (− red / + green) · n=24/29

Models

2,720 models
ModelProvidersInput from / 1MOutput from / 1MContextCapabilities
Accounts Fireworks Models Llama V3p2 1b1$0.10/1M tokens$0.10/1M tokens131,072
Accounts Fireworks Models Llama V3p2 1b Instruct1$0.10/1M tokens$0.10/1M tokens16,384
Accounts Fireworks Models Llama V3p2 3b1$0.10/1M tokens$0.10/1M tokens131,072
Accounts Fireworks Models Llama V3p2 3b Instruct1$0.10/1M tokens$0.10/1M tokens16,384
Accounts Fireworks Models Minimax M1 80k1$0.10/1M tokens$0.10/1M tokens4,096
Accounts Fireworks Models Ministral 3 3b Instruct 25121$0.10/1M tokens$0.10/1M tokens256,000
Accounts Fireworks Models Nemotron Nano V2 12b Vl1$0.10/1M tokens$0.10/1M tokens4,096
Accounts Fireworks Models Phi 2 3b1$0.10/1M tokens$0.10/1M tokens2,048
Accounts Fireworks Models Phi 3 Mini 128k Instruct1$0.10/1M tokens$0.10/1M tokens131,072
Accounts Fireworks Models Qwen2 Vl 2b Instruct1$0.10/1M tokens$0.10/1M tokens32,768
Accounts Fireworks Models Qwen2p5 0p5b Instruct1$0.10/1M tokens$0.10/1M tokens32,768
Accounts Fireworks Models Qwen2p5 1p5b Instruct1$0.10/1M tokens$0.10/1M tokens32,768
Accounts Fireworks Models Qwen2p5 Coder 0p5b1$0.10/1M tokens$0.10/1M tokens32,768
Accounts Fireworks Models Qwen2p5 Coder 0p5b Instruct1$0.10/1M tokens$0.10/1M tokens32,768
Accounts Fireworks Models Qwen2p5 Coder 1p5b1$0.10/1M tokens$0.10/1M tokens32,768
Accounts Fireworks Models Qwen2p5 Coder 1p5b Instruct1$0.10/1M tokens$0.10/1M tokens32,768
Accounts Fireworks Models Qwen2p5 Coder 3b1$0.10/1M tokens$0.10/1M tokens32,768
Accounts Fireworks Models Qwen2p5 Coder 3b Instruct1$0.10/1M tokens$0.10/1M tokens32,768
Accounts Fireworks Models Qwen3 0p6b1$0.10/1M tokens$0.10/1M tokens40,960
Accounts Fireworks Models Qwen3 1p7b1$0.10/1M tokens$0.10/1M tokens131,072
Accounts Fireworks Models Qwen3 1p7b Fp8 Draft1$0.10/1M tokens$0.10/1M tokens262,144
Accounts Fireworks Models Qwen3 1p7b Fp8 Draft 1310721$0.10/1M tokens$0.10/1M tokens131,072
Accounts Fireworks Models Qwen3 1p7b Fp8 Draft 409601$0.10/1M tokens$0.10/1M tokens40,960
Accounts Fireworks Models Stablecode 3b1$0.10/1M tokens$0.10/1M tokens4,096
Accounts Fireworks Models Starcoder2 3b1$0.10/1M tokens$0.10/1M tokens16,384
Meta Llama 3 1 8b Instruct1$0.10/1M tokens$0.10/1M tokens8,192 FC
Llama 4 Maverick 17b 128e Instruct Fp81$0.05/1M tokens$0.10/1M tokens131,072 FC
Llama 4 Scout 17b 16e Instruct1$0.05/1M tokens$0.10/1M tokens16,384 FC
Qwen25 Coder 32b Instruct1$0.05/1M tokens$0.10/1M tokens131,072 FC
Qwen3 32b Fp81$0.05/1M tokens$0.10/1M tokens131,072 FC Reasoning
Meta Llama3 2 1b Instruct V1 01$0.10/1M tokens$0.10/1M tokens128,000 FC
Mistral Ministral 3 3b Instruct1$0.10/1M tokens$0.10/1M tokens128,000 FC
Ministral 3 3b 25121$0.10/1M tokens$0.10/1M tokens131,072Vision FC
Ministral 3b 25121$0.10/1M tokens$0.10/1M tokens131,072Vision FC
Ministral 3b Latest1$0.10/1M tokens$0.10/1M tokens131,072Vision FC
Google Gemma 3 12b It1$0.05/1M tokens$0.10/1M tokens131,072Vision
Google Gemma 3 4b It1$0.05/1M tokens$0.10/1M tokens131,072Vision
Mistralai Ministral 3b 25121$0.10/1M tokens$0.10/1M tokens131,072Vision FC
Llama 3 1 8B Instruct1$0.10/1M tokens$0.10/1M tokens131,000 FC
Mistral 7B Instruct V0 31$0.10/1M tokens$0.10/1M tokens127,000 FC
Together Ai Up To 4b1$0.10/1M tokens$0.10/1M tokens
Arize Ai Qwen 2 1 5b Instruct1$0.10/1M tokens$0.10/1M tokens32,768
Us Meta Llama3 2 1b Instruct V1 01$0.10/1M tokens$0.10/1M tokens128,000 FC
Meta Llama 3 2 1b1$0.10/1M tokens$0.10/1M tokens128,000
Mistral Ministral 8b1$0.10/1M tokens$0.10/1M tokens128,000Vision FC
JetBrains Mellum2 12B A2 5B Instruct1$0.05/1M tokens$0.10/1M tokens131,072
Qwen Qwen3 235B A22B Instruct 25071$0.10/1M tokens$0.10/1M tokens262,144
Qwen Qwen3 235B A22B Thinking 25071$0.10/1M tokens$0.10/1M tokens262,144 Reasoning
Ibm Granite Granite 4 1 8b1$0.05/1M tokens$0.10/1M tokens131,072
Ibm Granite Guardian 3 2 2b1$0.10/1M tokens$0.10/1M tokens8,192
Ibm Granite Vision 3 2 2b1$0.10/1M tokens$0.10/1M tokens8,192Vision
Meta Llama Llama 3 2 1b Instruct1$0.10/1M tokens$0.10/1M tokens128,000 FC
Glm 4 32b 0414 128k1$0.10/1M tokens$0.10/1M tokens128,000 FC
@Cf Ibm Granite Granite 4 0 H Micro1$0.02/1M tokens$0.11/1M tokens131,000 FC
Codellama 7b1$0.06/1M tokens$0.12/1M tokens16,384 FC
Deepseek Coder 6 7b1$0.06/1M tokens$0.12/1M tokens16,384 FC
Qwen2 5 Coder 7b1$0.06/1M tokens$0.12/1M tokens32,768 FC
Mistralai Mistral Nemo Instruct 24071$0.04/1M tokens$0.12/1M tokens128,000 FC
Poolside Laguna Xs 2 11$0.06/1M tokens$0.12/1M tokens262,144 FC Reasoning
Google Gemma 3n E4B It1$0.06/1M tokens$0.12/1M tokens32,768
Eu Meta Llama3 2 1b Instruct V1 01$0.13/1M tokens$0.13/1M tokens128,000 FC
Mistralai Mistral 7b Instruct1$0.13/1M tokens$0.13/1M tokens32,768
Openai Gpt Oss 20b1$0.03/1M tokens$0.13/1M tokens131,072 FC Reasoning
Qwen Qwen3 7 Flash1$0.03/1M tokens$0.13/1M tokens1,000,000Vision FC Reasoning
Mistral Nemo Instruct 24071$0.13/1M tokens$0.13/1M tokens118,000 FC
Chat Bison1$0.13/1M tokens$0.13/1M tokens8,192
Chat Bison 0011$0.13/1M tokens$0.13/1M tokens8,192
Openai Gpt Oss 20b1$0.03/1M tokens$0.13/1M tokens131,072 Reasoning
Nova Micro V11$0.04/1M tokens$0.14/1M tokens128,000 FC
Amazon Nova Micro V1 01$0.04/1M tokens$0.14/1M tokens128,000 FC
Microsoft Phi 41$0.07/1M tokens$0.14/1M tokens16,384 FC
Openai Gpt Oss 20b1$0.03/1M tokens$0.14/1M tokens131,072 FC
Qwen3 8b1$0.04/1M tokens$0.14/1M tokens32,768 FC
Nousresearch Hermes 2 Pro Llama 3 8b1$0.14/1M tokens$0.14/1M tokens8,192
Qwen Qwen3 8b Fp81$0.04/1M tokens$0.14/1M tokens128,000 Reasoning
Zai Org Autoglm Phone 9b Multilingual1$0.04/1M tokens$0.14/1M tokens65,536Vision
Us Amazon Nova Micro V1 01$0.04/1M tokens$0.14/1M tokens128,000 FC
Amazon Nova Micro1$0.04/1M tokens$0.14/1M tokens128,000 FC
HuggingFaceH4 Zephyr 7b Beta1$0.15/1M tokens$0.15/1M tokens16,384
Google Gemma 7b It1$0.15/1M tokens$0.15/1M tokens8,192
Meta Llama Llama 2 7b Chat Hf1$0.15/1M tokens$0.15/1M tokens4,096
Meta Llama Meta Llama 3 8B Instruct1$0.15/1M tokens$0.15/1M tokens8,192
Mistralai Mistral 7B Instruct V0 11$0.15/1M tokens$0.15/1M tokens16,384 FC
Mistralai Mixtral 8x7B Instruct V0 11$0.15/1M tokens$0.15/1M tokens16,384 FC
Apac Amazon Nova Micro V1 01$0.04/1M tokens$0.15/1M tokens128,000 FC
Mistral Nemo1$0.15/1M tokens$0.15/1M tokens131,072 FC
Command R7b 12 20241$0.04/1M tokens$0.15/1M tokens128,000 FC
Qwen Qwen3 5 9B1$0.10/1M tokens$0.15/1M tokens262,144Vision FC
Google Gemma 3 12b It1$0.05/1M tokens$0.15/1M tokens131,072 FC
Deepseek R1 7b Qwen1$0.08/1M tokens$0.15/1M tokens131,072 FC Reasoning
Dolphin3 8b1$0.08/1M tokens$0.15/1M tokens128,000 FC
Mistral 7b V0 31$0.10/1M tokens$0.15/1M tokens32,768 FC
Openthinker 7b1$0.08/1M tokens$0.15/1M tokens32,768 FC Reasoning
Meta Llama3 2 3b Instruct V1 01$0.15/1M tokens$0.15/1M tokens128,000 FC
Mistral Ministral 3 8b Instruct1$0.15/1M tokens$0.15/1M tokens128,000 FC
Ministral 3 8b 25121$0.15/1M tokens$0.15/1M tokens262,144Vision FC
Ministral 8b 25121$0.15/1M tokens$0.15/1M tokens262,144Vision FC
Ministral 8b Latest1$0.15/1M tokens$0.15/1M tokens262,144Vision FC
Pixtral 12b 24091$0.15/1M tokens$0.15/1M tokens128,000Vision FC
Deepseek Deepseek R1 Distill Qwen 14b1$0.15/1M tokens$0.15/1M tokens32,768 Reasoning