LLM API pricing
Compare per-token prices across LLM API providers.
LLM market heatmap
3,582 models grouped by vendor — click a vendor, then a family to filter the catalog
Models
| Model | Providers | Input from / 1M | Output from / 1M | Context | Capabilities |
|---|---|---|---|---|---|
| Amazon Titan Embed Text V2 | 1 | $0.02/1M tokens | Free | — | |
| @Cf Meta Llama 3 2 1b Instruct | 1 | $0.03/1M tokens | $0.20/1M tokens | 60,000 | |
| Gemma 4 26b | 1 | $0.03/1M tokens | $0.17/1M tokens | 131,072 | FC |
| Meta Llama Meta Llama 3 8B Instruct | 1 | $0.03/1M tokens | $0.06/1M tokens | 8,192 | FC |
| Meta Llama Meta Llama 3 1 8B Instruct | 1 | $0.03/1M tokens | $0.05/1M tokens | 131,072 | FC |
| Openai Gpt Oss 20b | 1 | $0.03/1M tokens | $0.14/1M tokens | 131,072 | FC |
| DeepSeek: DeepSeek V4 Flash 0731 | 3 | $0.03/1M tokens | $0.07/1M tokens | — | |
| Doubao Seed 2.0 Mini | 1 | $0.03/1M tokens | $0.30/1M tokens | 256,000 | |
| GLM-OCR | 1 | $0.03/1M tokens | $0.03/1M tokens | — | Vision |
| Meta Llama Llama Prompt Guard 2 22m | 1 | $0.03/1M tokens | $0.03/1M tokens | 512 | |
| Hy4 Preview | 1 | $0.03/1M tokens | $0.11/1M tokens | 1,048,576 | |
| Inference.net: Schematron V2 Turbo | 1 | $0.03/1M tokens | $0.15/1M tokens | 128,000 | |
| Hermes3 8b | 1 | $0.03/1M tokens | $0.04/1M tokens | 131,072 | FC |
| Lfm 7b | 1 | $0.03/1M tokens | $0.04/1M tokens | 131,072 | FC |
| Llama3 1 8b Instruct | 1 | $0.03/1M tokens | $0.04/1M tokens | 131,072 | FC |
| Gemma3 4b | 1 | $0.03/1M tokens | $0.08/1M tokens | 128,000 | Vision FC |
| Llama 3 1 8b | 1 | $0.03/1M tokens | $0.05/1M tokens | 131,072 | FC |
| Meta: Llama 3.2 1B Instruct | 1 | $0.03/1M tokens | $0.20/1M tokens | 60,000 | |
| Deepseek Deepseek Ocr | 1 | $0.03/1M tokens | $0.03/1M tokens | 8,192 | Vision |
| Deepseek Deepseek Ocr 2 | 1 | $0.03/1M tokens | $0.03/1M tokens | 8,192 | Vision |
| Meta Llama Llama 3 2 3b Instruct | 1 | $0.03/1M tokens | $0.05/1M tokens | 32,768 | FC |
| Qwen Qwen3 4b Fp8 | 1 | $0.03/1M tokens | $0.03/1M tokens | 128,000 | FC Reasoning |
| Deepseek Ai DeepSeek R1 Distill Llama 8B | 1 | $0.03/1M tokens | $0.03/1M tokens | — | |
| Meta Llama Llama 3 1 8B Instruct | 1 | $0.03/1M tokens | $0.03/1M tokens | — | |
| OpenAI: GPT-5 Nano (batch) | 1 | $0.03/1M tokens | $0.20/1M tokens | 400,000 | Vision FC Reasoning |
| Meta Llama Llama 3 2 1b Instruct | 1 | $0.03/1M tokens | $0.20/1M tokens | 60,000 | |
| Openai Gpt Oss 20b | 1 | $0.03/1M tokens | $0.13/1M tokens | 131,072 | FC Reasoning |
| Qwen Qwen3 7 Flash | 1 | $0.03/1M tokens | $0.13/1M tokens | 1,000,000 | Vision FC Reasoning |
| Qwen3.7 Flash | 3 | $0.03/1M tokens | $0.13/1M tokens | 1,000,000 | |
| Qwen3.5-Flash | 3 | $0.03/1M tokens | $0.26/1M tokens | 1,000,000 | Vision FC |
| Qwen3 5 Flash 2026 02 23 | 1 | $0.03/1M tokens | $0.30/1M tokens | — | |
| Qwen3 7 Flash | 2 | $0.03/1M tokens | $0.12/1M tokens | — | |
| Qwen3 7 Flash 2026 07 15 | 1 | $0.03/1M tokens | $0.12/1M tokens | — | |
| Ibm Granite Granite 3 3 8b Instruct | 1 | $0.03/1M tokens | $0.25/1M tokens | — | FC |
| Openai Gpt Oss 120b | 1 | $0.03/1M tokens | $0.17/1M tokens | 131,072 | Reasoning |
| Openai Gpt Oss 20b | 1 | $0.03/1M tokens | $0.13/1M tokens | 131,072 | Reasoning |
| DeepSeek: DeepSeek V4 Flash Latest | 2 | $0.03/1M tokens | $0.07/1M tokens | — | |
| Nova Micro V1 | 1 | $0.04/1M tokens | $0.14/1M tokens | 128,000 | FC |
| Amazon Nova Micro V1 0 | 1 | $0.04/1M tokens | $0.14/1M tokens | 128,000 | FC |
| Amazon: Nova Micro 1.0 | 2 | $0.04/1M tokens | $0.14/1M tokens | — | |
| Apac Amazon Nova Micro V1 0 | 1 | $0.04/1M tokens | $0.15/1M tokens | 128,000 | FC |
| Ministral 3b | 1 | $0.04/1M tokens | $0.04/1M tokens | 128,000 | FC |
| Us Gov West 1 Amazon Nova Micro V1 0 | 1 | $0.04/1M tokens | $0.17/1M tokens | 128,000 | FC |
| Google Gemma 4 E2b | 1 | $0.04/1M tokens | $0.08/1M tokens | 128,000 | Vision FC Reasoning |
| Cohere: Command R7B (12-2024) | 1 | $0.04/1M tokens | $0.15/1M tokens | 128,000 | |
| Command R7b 12 2024 | 1 | $0.04/1M tokens | $0.15/1M tokens | 128,000 | FC |
| Qwen Qwen2 5 7B Instruct | 1 | $0.04/1M tokens | $0.10/1M tokens | 32,768 | |
| Sao10K L3 8B Lunaris V1 Turbo | 1 | $0.04/1M tokens | $0.05/1M tokens | 8,192 | |
| Nvidia NVIDIA Nemotron Nano 9B V2 | 1 | $0.04/1M tokens | $0.16/1M tokens | 131,072 | FC |
| Openai Gpt Oss 120b | 1 | $0.04/1M tokens | $0.17/1M tokens | 131,072 | FC |
| GLM-4.6V-FlashX | 1 | $0.04/1M tokens | $0.40/1M tokens | — | Vision |
| Google: Gemma 4 26B A4B | 3 | $0.04/1M tokens | $0.22/1M tokens | — | |
| Gpt Oss 120b | 1 | $0.04/1M tokens | $0.20/1M tokens | 128,000 | |
| Gpt Oss 20b | 1 | $0.04/1M tokens | $0.15/1M tokens | 128,000 | |
| Meta Llama Llama Prompt Guard 2 86m | 1 | $0.04/1M tokens | $0.04/1M tokens | 512 | |
| Inception: Mercury 2.5 | 2 | $0.04/1M tokens | $0.15/1M tokens | 260,000 | FC Reasoning |
| Llama 3 2 3b | 1 | $0.04/1M tokens | $0.08/1M tokens | 131,072 | FC |
| Qwen3 8b | 1 | $0.04/1M tokens | $0.14/1M tokens | 32,768 | FC |
| Mistral Voxtral Mini 3b 2507 | 1 | $0.04/1M tokens | $0.04/1M tokens | 128,000 | |
| Mistralai Mistral Nemo Instruct 2407 | 1 | $0.04/1M tokens | $0.12/1M tokens | 128,000 | FC |
| Meta Llama Llama 3 8b Instruct | 1 | $0.04/1M tokens | $0.04/1M tokens | 8,192 | |
| Mistralai Mistral Nemo | 1 | $0.04/1M tokens | $0.17/1M tokens | 60,288 | |
| Openai Gpt Oss 20b | 1 | $0.04/1M tokens | $0.15/1M tokens | 131,072 | Reasoning |
| Qwen Qwen3 8b Fp8 | 1 | $0.04/1M tokens | $0.14/1M tokens | 128,000 | Reasoning |
| Zai Org Autoglm Phone 9b Multilingual | 1 | $0.04/1M tokens | $0.14/1M tokens | 65,536 | Vision |
| Openai Gpt Oss 120b | 1 | $0.04/1M tokens | $0.17/1M tokens | 131,072 | FC Reasoning |
| Gpt Oss 20b | 1 | $0.04/1M tokens | $0.15/1M tokens | 131,000 | Reasoning |
| Meta Llama 3 2 1B Instruct | 1 | $0.04/1M tokens | $0.08/1M tokens | 16,384 | |
| Sao10K: Llama 3 8B Lunaris | 1 | $0.04/1M tokens | $0.05/1M tokens | 8,192 | |
| Tencent: Hy-MT2-1.8B | 1 | $0.04/1M tokens | $0.18/1M tokens | 8,192 | |
| Us Amazon Nova Micro V1 0 | 1 | $0.04/1M tokens | $0.14/1M tokens | 128,000 | FC |
| Amazon Nova Micro | 1 | $0.04/1M tokens | $0.14/1M tokens | 128,000 | FC |
| Mistral Ministral 3b | 1 | $0.04/1M tokens | $0.04/1M tokens | 128,000 | FC |
| Gpt 5 Nano | 1 | $0.05/1M tokens | $0.40/1M tokens | 272,000 | Vision FC Reasoning |
| Gpt 5 Nano 2025 08 07 | 1 | $0.05/1M tokens | $0.40/1M tokens | 272,000 | Vision FC Reasoning |
| Us Gov West 1 Google Gemma 4 E2b | 1 | $0.05/1M tokens | $0.10/1M tokens | 128,000 | Vision FC Reasoning |
| @Cf Meta Llama 3 2 11b Vision Instruct | 1 | $0.05/1M tokens | $0.68/1M tokens | 128,000 | Vision |
| @Cf Meta Llama 3 2 3b Instruct | 1 | $0.05/1M tokens | $0.34/1M tokens | 80,000 | |
| @Cf Qwen Qwen3 30b A3b Fp8 | 1 | $0.05/1M tokens | $0.34/1M tokens | 32,768 | FC Reasoning |
| Qwen Turbo | 1 | $0.05/1M tokens | $0.20/1M tokens | 129,024 | FC Reasoning |
| Qwen Turbo 2024 11 01 | 1 | $0.05/1M tokens | $0.20/1M tokens | 1,000,000 | FC Reasoning |
| Qwen Turbo 2025 04 28 | 1 | $0.05/1M tokens | $0.20/1M tokens | 1,000,000 | FC Reasoning |
| Qwen Turbo Latest | 1 | $0.05/1M tokens | $0.20/1M tokens | 1,000,000 | FC Reasoning |
| Databricks Gpt 5 Nano | 1 | $0.05/1M tokens | $0.40/1M tokens | 272,000 | FC |
| Google Gemma 3 12b It | 1 | $0.05/1M tokens | $0.15/1M tokens | 131,072 | FC |
| Google Gemma 3 4b It | 1 | $0.05/1M tokens | $0.10/1M tokens | 131,072 | FC |
| Meta Llama Llama 3 2 11B Vision Instruct | 1 | $0.05/1M tokens | $0.05/1M tokens | 131,072 | |
| Mistralai Mistral Small 24B Instruct 2501 | 1 | $0.05/1M tokens | $0.08/1M tokens | 32,768 | FC |
| Nvidia Nemotron 3 Nano 30B A3B | 1 | $0.05/1M tokens | $0.20/1M tokens | 262,144 | FC Reasoning |
| DeepSeek: DeepSeek V4 Flash 0423 | 4 | $0.05/1M tokens | $0.12/1M tokens | — | |
| Eu Amazon Nova Micro V1 0 | 1 | $0.05/1M tokens | $0.18/1M tokens | 128,000 | FC |
| Accounts Fireworks Models Nemotron Lightning 3p5 30b A3b | 1 | $0.05/1M tokens | $0.20/1M tokens | 262,144 | FC Reasoning |
| Nemotron Lightning 3p5 30b A3b | 1 | $0.05/1M tokens | $0.20/1M tokens | 262,144 | FC Reasoning |
| Google: Gemini 2.5 Flash Lite (batch) | 1 | $0.05/1M tokens | $0.20/1M tokens | 1,048,576 | Vision FC Reasoning |
| GPT-5 Nano | 2 | $0.05/1M tokens | $0.40/1M tokens | 400,000 | |
| Gpt 5 Nano 2025 08 07 | 1 | $0.05/1M tokens | $0.40/1M tokens | 272,000 | Vision FC Reasoning |
| Gemma 7b It | 1 | $0.05/1M tokens | $0.08/1M tokens | 8,192 | FC |
| Llama 3 1 8b Instant | 1 | $0.05/1M tokens | $0.08/1M tokens | 131,072 | FC |
| Inference.net: Schematron V2 Small | 1 | $0.05/1M tokens | $0.23/1M tokens | 128,000 | |
| Llama 4 Maverick 17b 128e Instruct Fp8 | 1 | $0.05/1M tokens | $0.10/1M tokens | 131,072 | FC |