Offerings
Every active offering: a model as served by one host, with its current canonical price. Sort by clicking a column header; filter with the row below. Prices are USD per 1M tokens unless the unit toggle is set to per 1M characters (an approximation using a measured, blended tokens-per-character ratio).
Showing tier-tagged and vendor-direct models. Show all offerings, including the long tail
More columns: + Vendor - Region - Cache - Batch - Tokenizer - Last change + Source All columns Default columns
| Model | Host | Variant | Region | Input | Output | Blended ↑? | Cache read | Cache write | Batch in | Batch out | Context | Tokenizer | Last change | Confidence? |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| GPT-5 mini | Perplexity | – | – | 0.250 | 2.00 | 0.688 | 0.0250 | – | – | – | 400,000 | o200k | – | aggregator |
| Qwen3-Coder-480B-A35B 2 sources | DeepInfra | – | – | 0.400 | 1.60 | 0.700 | 0.100 | – | – | – | 262,144 | qwen2 | 2026-08-27 ↕ | aggregator |
| GLM-4.6 | DeepInfra | flex+fp4 | – | 0.400 | 1.60 | 0.700 | 0.0800 | – | – | – | 200,000 | – | – | api |
| Llama 3.3 70B Instruct | OpenRouter | – | – | 0.710 | 0.710 | 0.710 | 0.710 | – | – | – | 128,000 | llama3 | – | api |
| Llama 3.3 70B Instruct | CoreWeave | – | – | 0.710 | 0.710 | 0.710 | 0.710 | – | – | – | 128,000 | llama3 | – | api |
| Llama 3.3 70B Instruct 2 sources | Azure AI Foundry | – | – | 0.710 | 0.710 | 0.710 | – | – | – | – | 128,000 | llama3 | – | aggregator |
| Llama 3.3 70B Instruct | Google Vertex AI | – | us-central1 | 0.720 | 0.720 | 0.720 | – | – | – | – | 128,000 | llama3 | – | api |
| Llama 3.3 70B Instruct 3 sources | Google Vertex AI | – | – | 0.720 | 0.720 | 0.720 | – | – | 0.360 | 0.360 | 128,000 | llama3 | – | api |
| Llama 3.3 70B Instruct 2 sources | AWS Bedrock | – | – | 0.720 | 0.720 | 0.720 | – | – | 0.360 | 0.360 | 128,000 | llama3 | – | aggregator |
| Llama 3.3 70B Instruct | AWS Bedrock | – | us | 0.720 | 0.720 | 0.720 | – | – | 0.360 | 0.360 | 128,000 | llama3 | – | aggregator |
| Mistral Large 3 (25.12) | OpenRouter | – | – | 0.500 | 1.50 | 0.750 | 0.0500 | – | – | – | 262,144 | mistral | – | api |
| Mistral Large 3 (25.12) | Mistral AI | zdr | – | 0.500 | 1.50 | 0.750 | 0.0500 | – | – | – | 262,144 | mistral | – | api |
| Llama 3.3 70B Instruct 2 sources | SambaNova | – | – | 0.600 | 1.20 | 0.750 | – | – | – | – | 128,000 | llama3 | – | api |
| Mistral Large 3 (25.12) | Azure AI Foundry | – | – | 0.500 | 1.50 | 0.750 | – | – | – | – | 262,144 | mistral | – | aggregator |
| Mistral Large 3 (25.12) 2 sources | AWS Bedrock | – | – | 0.500 | 1.50 | 0.750 | – | – | 0.250 | 0.750 | 262,144 | mistral | – | aggregator |
| Mistral Large 3 (25.12) 2 sources | Mistral AI | – | – | 0.500 | 1.50 | 0.750 | 0.0500 | – | – | – | 262,144 | mistral | 2026-03-02 ↓ | aggregator |
| GPT-5 mini | Azure AI Foundry | – | swedencentral | 0.275 | 2.20 | 0.756 | 0.0330 | – | – | – | 400,000 | o200k | – | api |
| GPT-5 mini | Azure AI Foundry | – | eu | 0.275 | 2.20 | 0.756 | 0.0275 | – | 0.138 | 1.10 | 400,000 | o200k | – | aggregator |
| GPT-5 mini | Azure AI Foundry | – | us | 0.275 | 2.20 | 0.756 | 0.0275 | – | 0.138 | 1.10 | 400,000 | o200k | – | aggregator |
| GLM-4.6 | Venice | fp4 | – | 0.430 | 1.75 | 0.760 | 0.0800 | – | – | – | 200,000 | – | – | api |
| Mistral Large 3 (25.12) | AWS Bedrock | – | ap-southeast-2 | 0.515 | 1.55 | 0.773 | – | – | – | – | 262,144 | mistral | – | aggregator |
| Llama 3.3 70B Instruct | Cloudflare Workers AI | fp8 | – | 0.293 | 2.25 | 0.783 | – | – | – | – | 128,000 | llama3 | – | api |
| Qwen3-Coder-480B-A35B 2 sources | AWS Bedrock | – | – | 0.450 | 1.80 | 0.788 | – | – | – | – | 262,144 | qwen2 | 2026-09-06 ↑ | aggregator |
| Qwen3-Coder-480B-A35B | Fireworks AI | – | – | 0.450 | 1.80 | 0.788 | – | – | – | – | 262,144 | qwen2 | – | aggregator |
| Qwen3-235B-A22B 2 sources | Alibaba Cloud | – | – | 0.455 | 1.82 | 0.796 | – | – | – | – | 131,072 | qwen2 | – | api |
| Mistral Medium 3.1 | Mistral AI | – | – | 0.400 | 2.00 | 0.800 | – | – | – | – | 131,072 | mistral | – | aggregator |
| Qwen3-Coder-480B-A35B | AWS Bedrock | – | ap-southeast-2 | 0.464 | 1.85 | 0.811 | – | – | – | – | 262,144 | qwen2 | – | aggregator |
| Qwen3-Coder-480B-A35B | AWS Bedrock | – | ap-southeast-3 | 0.470 | 1.87 | 0.820 | – | – | – | – | 262,144 | qwen2 | – | aggregator |
| Mistral Large 3 (25.12) | Mistral AI | – | eu | 0.550 | 1.65 | 0.825 | 0.0550 | – | – | – | 262,144 | mistral | – | api |
| Gemini 2.5 Flash | OpenRouter | – | – | 0.300 | 2.50 | 0.850 | 0.0300 | 0.0833 | – | – | 1,048,576 | gemini | – | api |
| MiniMax-M1 | MiniMax | – | – | 0.400 | 2.20 | 0.850 | – | – | – | – | 1,000,000 | – | – | api |
| Gemini 2.5 Flash 4 sources | – | – | 0.300 | 2.50 | 0.850 | 0.0300 | 0.0833 | 0.150 | 1.25 | 1,048,576 | gemini | – | official | |
| Gemini 2.5 Flash 3 sources | Google Vertex AI | – | – | 0.300 | 2.50 | 0.850 | 0.0300 | 0.0833 | 0.150 | 1.25 | 1,048,576 | gemini | – | api |
| Gemini 2.5 Flash 2 sources | DeepInfra | – | – | 0.300 | 2.50 | 0.850 | – | – | – | – | 1,048,576 | gemini | 2025-10-04 ↑ | official |
| GLM-4.6 | OpenRouter | – | – | 0.500 | 2.00 | 0.875 | 0.100 | – | – | – | 200,000 | – | – | api |
| GLM-4.6 | DeepInfra | fp4 | – | 0.500 | 2.00 | 0.875 | 0.100 | – | – | – | 200,000 | – | – | api |
| Kimi K2 | DeepInfra | – | – | 0.500 | 2.00 | 0.875 | – | – | – | – | 131,072 | – | – | aggregator |
| GLM-4.6 3 sources | DeepInfra | – | – | 0.500 | 2.00 | 0.875 | 0.100 | – | – | – | 200,000 | – | – | official |
| DeepSeek V3.2 (chat) | Together AI | – | – | 0.600 | 1.70 | 0.875 | – | – | – | – | 128,000 | deepseek | – | aggregator |
| Mistral Large 3 (25.12) | AWS Bedrock | – | ap-south-1 | 0.590 | 1.76 | 0.883 | – | – | – | – | 262,144 | mistral | – | aggregator |
| Mistral Large 3 (25.12) | AWS Bedrock | – | ap-northeast-1 | 0.610 | 1.82 | 0.913 | – | – | – | – | 262,144 | mistral | – | aggregator |
| Mistral Large 3 (25.12) | AWS Bedrock | – | sa-east-1 | 0.610 | 1.82 | 0.913 | – | – | – | – | 262,144 | mistral | – | aggregator |
| Llama 4 Maverick | SambaNova | – | – | 0.630 | 1.80 | 0.923 | – | – | – | – | 1,000,000 | llama3 | – | aggregator |
| Qwen3-Coder-480B-A35B | AWS Bedrock | – | ap-south-1 | 0.530 | 2.12 | 0.928 | – | – | – | – | 262,144 | qwen2 | – | aggregator |
| Qwen3-Coder-480B-A35B | AWS Bedrock | – | sa-east-1 | 0.540 | 2.16 | 0.945 | – | – | – | – | 262,144 | qwen2 | – | aggregator |
| Qwen3-Coder-480B-A35B | AWS Bedrock | – | ap-northeast-1 | 0.540 | 2.18 | 0.950 | – | – | – | – | 262,144 | qwen2 | – | aggregator |
| GLM-4.6 3 sources | Novita AI | – | – | 0.550 | 2.20 | 0.963 | 0.110 | – | – | – | 200,000 | – | 2026-01-13 ↓ | api |
| MiniMax-M1 3 sources | Novita AI | – | – | 0.550 | 2.20 | 0.963 | – | – | – | – | 1,000,000 | – | 2026-01-13 ↓ | api |
| DeepSeek V4 Pro | DeepSeek | off-peak | – | 0.660 | 1.98 | 0.990 | 0.0220 | – | – | – | 1,048,576 | deepseek | – | official |
| GLM-4.6 | Zhipu AI (Z.ai) | fp4 | – | 0.600 | 2.20 | 1.00 | 0.110 | – | – | – | 200,000 | – | – | api |
Confidence: official = vendor pricing page · api = OpenRouter per-host · aggregator = community list, may lag · unreviewed = automatic extraction awaiting review. When sources disagree the most authoritative wins. Details: /methodology#confidence