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 |
|---|---|---|---|---|---|
| NVIDIA: Nemotron 3 Super | 1 | $0.09/1M tokens | $0.40/1M tokens | 262,144 | FC Reasoning |
| OpenAI: GPT-4.1 Nano | 1 | $0.10/1M tokens | $0.40/1M tokens | 1,047,576 | Vision FC |
| OpenAI: GPT-5 Nano | 1 | $0.05/1M tokens | $0.40/1M tokens | 400,000 | Vision FC Reasoning |
| Qwen2.5 72B Instruct | 1 | $0.36/1M tokens | $0.40/1M tokens | 32,768 | FC |
| TheDrummer: UnslopNemo 12B | 1 | $0.40/1M tokens | $0.40/1M tokens | 1,024,000 | FC |
| Z.ai: GLM 4.7 Flash | 1 | $0.06/1M tokens | $0.40/1M tokens | 200,000 | FC Reasoning |
| DeepSeek: DeepSeek V3.2 Exp | 1 | $0.27/1M tokens | $0.41/1M tokens | 163,840 | FC Reasoning |
| Qwen: Qwen3 VL 32B Instruct | 1 | $0.10/1M tokens | $0.42/1M tokens | 131,072 | Vision FC |
| Google: Gemma 3 27B | 1 | $0.08/1M tokens | $0.45/1M tokens | 131,072 | Vision FC |
| Mistral: Codestral 2508 (batch) | 1 | $0.15/1M tokens | $0.45/1M tokens | 256,000 | FC |
| Qwen: Qwen3 8B | 1 | $0.12/1M tokens | $0.46/1M tokens | 131,072 | FC Reasoning |
| Qwen: Qwen3 VL 8B Instruct | 1 | $0.12/1M tokens | $0.46/1M tokens | 262,144 | Vision FC |
| Qwen: Qwen3.8 Flash | 1 | $0.15/1M tokens | $0.47/1M tokens | 1,000,000 | Vision FC Reasoning |
| Qwen: Qwen3 30B A3B | 1 | $0.12/1M tokens | $0.50/1M tokens | 131,072 | FC Reasoning |
| TheDrummer: Cydonia 24B V4.1 | 1 | $0.30/1M tokens | $0.50/1M tokens | 131,072 | |
| Z.ai: GLM 5.3 Flash | 1 | $0.15/1M tokens | $0.50/1M tokens | 1,310,720 | Vision FC Reasoning |
| Tencent: Hy3 | 1 | $0.13/1M tokens | $0.53/1M tokens | 262,144 | FC Reasoning |
| Mistral: Mistral Small 3.1 24B | 1 | $0.35/1M tokens | $0.56/1M tokens | 128,000 | Vision |
| Tencent: Hunyuan A13B Instruct | 1 | $0.14/1M tokens | $0.57/1M tokens | 131,072 | Reasoning |
| Cohere: Command R (08-2024) | 1 | $0.15/1M tokens | $0.60/1M tokens | 128,000 | FC |
| DeepSeek: DeepSeek V4.1 Flash | 1 | $0.15/1M tokens | $0.60/1M tokens | 1,048,576 | Vision FC Reasoning |
| Mistral: Saba | 1 | $0.20/1M tokens | $0.60/1M tokens | 32,768 | FC |
| Mistral: Mistral Small 4 | 1 | $0.15/1M tokens | $0.60/1M tokens | 262,144 | Vision FC Reasoning |
| OpenAI: GPT-4o-mini | 1 | $0.15/1M tokens | $0.60/1M tokens | 128,000 | Vision FC |
| OpenAI: GPT-4o-mini (2024-07-18) | 1 | $0.15/1M tokens | $0.60/1M tokens | 128,000 | Vision FC |
| OpenAI: GPT-5.6 Luna Pro (batch) | 1 | $0.10/1M tokens | $0.60/1M tokens | 1,050,000 | Vision FC Reasoning |
| OpenAI: GPT-5.6 Luna (batch) | 1 | $0.10/1M tokens | $0.60/1M tokens | 1,050,000 | Vision FC Reasoning |
| OpenAI: gpt-oss-120b (batch) | 1 | $0.15/1M tokens | $0.60/1M tokens | 131,072 | FC Reasoning |
| Qwen: Qwen3 VL 30B A3B Instruct | 1 | $0.15/1M tokens | $0.60/1M tokens | 262,144 | Vision FC |
| Tencent: Hy3 preview | 1 | $0.18/1M tokens | $0.60/1M tokens | 262,144 | FC Reasoning |
| Upstage: Solar Pro 3 | 1 | $0.15/1M tokens | $0.60/1M tokens | 131,072 | FC Reasoning |
| WizardLM-2 8x22B | 1 | $0.62/1M tokens | $0.62/1M tokens | 65,535 | |
| OpenAI: GPT-5.4 Nano (batch) | 1 | $0.10/1M tokens | $0.63/1M tokens | 400,000 | Vision FC Reasoning |
| Google: Gemma 2 27B | 1 | $0.65/1M tokens | $0.65/1M tokens | 8,192 | |
| ReMM SLERP 13B | 1 | $0.35/1M tokens | $0.65/1M tokens | 6,144 | |
| DeepSeek: DeepSeek V4 Flash Vision Exp | 1 | $0.22/1M tokens | $0.66/1M tokens | 1,048,576 | Vision FC Reasoning |
| Meta: Llama 4 Maverick | 1 | $0.20/1M tokens | $0.70/1M tokens | 1,048,576 | Vision FC |
| Nous: Hermes 3 70B Instruct | 1 | $0.70/1M tokens | $0.70/1M tokens | 131,072 | |
| Google: Gemini 3.1 Flash Lite (batch) | 1 | $0.13/1M tokens | $0.75/1M tokens | 1,048,576 | Vision FC Reasoning |
| Inception: Mercury 2 | 1 | $0.25/1M tokens | $0.75/1M tokens | 128,000 | FC Reasoning |
| Mancer: Weaver (alpha) | 1 | $0.40/1M tokens | $0.75/1M tokens | 8,000 | |
| Meta: Muse Glimmer 30B (batch) | 1 | $0.18/1M tokens | $0.75/1M tokens | 131,072 | Vision FC Reasoning |
| Mistral: Mistral Large 3 2512 (batch) | 1 | $0.25/1M tokens | $0.75/1M tokens | 262,144 | Vision FC |
| OpenAI: GPT-3.5 Turbo (batch) | 1 | $0.25/1M tokens | $0.75/1M tokens | 16,385 | FC |
| Sao10K: Llama 3.3 Euryale 70B | 1 | $0.65/1M tokens | $0.75/1M tokens | 131,072 | |
| Qwen: Qwen-Plus | 1 | $0.26/1M tokens | $0.78/1M tokens | 1,000,000 | FC |
| Qwen: Qwen Plus 0728 | 1 | $0.26/1M tokens | $0.78/1M tokens | 1,000,000 | FC |
| Arcee AI: Trinity Large Thinking | 1 | $0.25/1M tokens | $0.80/1M tokens | 262,144 | FC Reasoning |
| DeepSeek: R1 Distill Llama 70B | 1 | $0.80/1M tokens | $0.80/1M tokens | 8,192 | Reasoning |
| OpenAI: GPT-4.1 Mini (batch) | 1 | $0.20/1M tokens | $0.80/1M tokens | 1,047,576 | Vision FC |
| Qwen: Qwen3 Coder Next | 1 | $0.12/1M tokens | $0.80/1M tokens | 262,144 | FC |
| TheDrummer: Skyfall 36B V2 | 1 | $0.55/1M tokens | $0.80/1M tokens | 32,768 | |
| Sao10K: Llama 3.1 Euryale 70B v2.2 | 1 | $0.85/1M tokens | $0.85/1M tokens | 131,072 | FC |
| Z.ai: GLM 4.5 Air | 1 | $0.13/1M tokens | $0.85/1M tokens | 131,072 | FC Reasoning |
| Xiaomi: MiMo-V2.5-Pro | 1 | $0.44/1M tokens | $0.87/1M tokens | 1,050,000 | FC Reasoning |
| Venice: Uncensored | 1 | $0.20/1M tokens | $0.90/1M tokens | 128,000 | |
| Mistral: Codestral 2508 | 1 | $0.30/1M tokens | $0.90/1M tokens | 256,000 | FC |
| Qwen: Qwen3.6 35B A3B | 1 | $0.10/1M tokens | $0.90/1M tokens | 262,144 | Vision FC Reasoning |
| Z.ai: GLM 4.6V | 1 | $0.30/1M tokens | $0.90/1M tokens | 131,072 | Vision FC Reasoning |
| Qwen: Qwen3 14B | 1 | $0.23/1M tokens | $0.91/1M tokens | 131,072 | FC Reasoning |
| DeepSeek: DeepSeek V3.1 | 1 | $0.25/1M tokens | $0.95/1M tokens | 163,840 | FC Reasoning |
| Google: Gemma 4 31B (batch) | 1 | $0.39/1M tokens | $0.97/1M tokens | 262,144 | Vision FC Reasoning |
| Qwen: Qwen3 Coder Flash | 1 | $0.20/1M tokens | $0.98/1M tokens | 1,000,000 | FC |
| DeepSeek: DeepSeek V3 0324 | 1 | $0.25/1M tokens | $1.00/1M tokens | 163,840 | FC |
| DeepSeek: DeepSeek V3.1 Terminus | 1 | $0.27/1M tokens | $1.00/1M tokens | 163,840 | FC Reasoning |
| Mistral: Mistral Medium 3.1 (batch) | 1 | $0.20/1M tokens | $1.00/1M tokens | 131,072 | Vision FC |
| Nous: Hermes 3 405B Instruct | 1 | $1.00/1M tokens | $1.00/1M tokens | 131,072 | |
| OpenAI: GPT-5 Mini (batch) | 1 | $0.13/1M tokens | $1.00/1M tokens | 400,000 | Vision FC Reasoning |
| Perplexity: Sonar | 1 | $1.00/1M tokens | $1.00/1M tokens | 127,072 | Vision |
| Qwen2.5 Coder 32B Instruct | 1 | $0.66/1M tokens | $1.00/1M tokens | 32,768 | |
| Qwen: Qwen2.5 VL 72B Instruct | 1 | $0.80/1M tokens | $1.00/1M tokens | 128,000 | Vision |
| Qwen: Qwen3 Coder 480B A35B | 1 | $0.30/1M tokens | $1.00/1M tokens | 262,144 | FC |
| MiniMax: MiniMax M2 | 1 | $0.26/1M tokens | $1.02/1M tokens | 204,800 | FC Reasoning |
| DeepSeek: DeepSeek V3 | 1 | $0.26/1M tokens | $1.03/1M tokens | 163,840 | FC |
| MiniMax: MiniMax M2.5 | 1 | $0.27/1M tokens | $1.08/1M tokens | 204,800 | FC Reasoning |
| Meta: Muse Glimmer 30B | 1 | $0.30/1M tokens | $1.10/1M tokens | 131,072 | Vision FC Reasoning |
| MiniMax: MiniMax-01 | 1 | $0.20/1M tokens | $1.10/1M tokens | 1,000,192 | Vision |
| Qwen: Qwen3 Next 80B A3B Instruct | 1 | $0.09/1M tokens | $1.10/1M tokens | 262,144 | FC |
| Qwen: Qwen3.6 Flash | 1 | $0.19/1M tokens | $1.13/1M tokens | 1,000,000 | Vision FC Reasoning |
| StepFun: Step 3.7 Flash | 1 | $0.20/1M tokens | $1.15/1M tokens | 262,144 | Vision FC Reasoning |
| Kwaipilot: KAT-Coder-Pro V2 | 1 | $0.30/1M tokens | $1.20/1M tokens | 262,144 | FC |
| Meituan: LongCat 2.0 | 1 | $0.30/1M tokens | $1.20/1M tokens | 1,048,756 | FC Reasoning |
| MiniMax: MiniMax M2-her | 1 | $0.30/1M tokens | $1.20/1M tokens | 65,536 | |
| MiniMax: MiniMax M2.1 | 1 | $0.30/1M tokens | $1.20/1M tokens | 204,800 | FC Reasoning |
| MiniMax: MiniMax M2.7 | 1 | $0.30/1M tokens | $1.20/1M tokens | 204,800 | FC Reasoning |
| MiniMax: MiniMax M3 | 1 | $0.30/1M tokens | $1.20/1M tokens | 1,048,576 | Vision FC Reasoning |
| MiniMax: MiniMax M3 (batch) | 1 | $0.30/1M tokens | $1.20/1M tokens | 524,288 | Vision FC Reasoning |
| Morph: Morph V3 Fast | 1 | $0.80/1M tokens | $1.20/1M tokens | 81,920 | |
| OpenAI: GPT-5.6 Luna | 1 | $0.20/1M tokens | $1.20/1M tokens | 1,050,000 | Vision FC Reasoning |
| OpenAI: GPT-5.6 Luna Pro | 1 | $0.20/1M tokens | $1.20/1M tokens | 1,050,000 | Vision FC Reasoning |
| Qwen: Qwen3 Next 80B A3B Thinking | 1 | $0.15/1M tokens | $1.20/1M tokens | 262,144 | FC Reasoning |
| Thinking Machines: Inkling Small | 1 | $0.45/1M tokens | $1.20/1M tokens | 1,048,576 | Vision FC Reasoning |
| Thinking Machines: Inkling Small (batch) | 1 | $0.50/1M tokens | $1.20/1M tokens | 524,288 | Vision FC Reasoning |
| OpenAI GPT Luna Latest | 1 | $0.20/1M tokens | $1.20/1M tokens | 1,050,000 | Vision FC Reasoning |
| Anthropic: Claude 3 Haiku | 1 | $0.25/1M tokens | $1.25/1M tokens | 200,000 | Vision FC |
| Baidu: ERNIE 4.5 VL 424B A47B | 1 | $0.42/1M tokens | $1.25/1M tokens | 123,000 | Vision Reasoning |
| Google: Gemini 2.5 Flash (batch) | 1 | $0.15/1M tokens | $1.25/1M tokens | 1,048,576 | Vision FC Reasoning |
| Google: Gemini 3.5 Flash Lite (batch) | 1 | $0.15/1M tokens | $1.25/1M tokens | 1,048,576 | Vision FC Reasoning |
| OpenAI: GPT-5.4 Nano | 1 | $0.20/1M tokens | $1.25/1M tokens | 400,000 | Vision FC Reasoning |
| Qwen: Qwen3.5-35B-A3B | 1 | $0.31/1M tokens | $1.25/1M tokens | 262,144 | Vision FC Reasoning |