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 | Last change | Confidence? |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Llama 3.3 70B Instruct 2 sources | DeepInfra | – | – | 0.230 | 0.400 | 0.273 | – | – | – | – | 128,000 | 2026-08-27 ↓ | aggregator |
| Grok 4 Fast | Azure AI Foundry | – | – | 0.200 | 0.500 | 0.275 | – | – | – | – | 2,000,000 | 2026-01-14 ↓ | aggregator |
| Llama 3.3 70B Instruct | AkashML | fp8 | – | 0.200 | 0.520 | 0.280 | 0.100 | – | – | – | 128,000 | – | api |
| Llama 4 Scout 3 sources | Novita AI | – | – | 0.180 | 0.590 | 0.283 | – | – | – | – | 10,000,000 | 2026-01-13 ↓ | api |
| Llama 4 Scout | Together AI | – | – | 0.180 | 0.590 | 0.283 | – | – | – | – | 10,000,000 | – | aggregator |
| Mistral Small 4 | Mistral AI | – | eu | 0.165 | 0.660 | 0.289 | 0.0165 | – | – | – | 262,144 | – | api |
| Mistral Small 4 | Mistral AI | – | us | 0.165 | 0.660 | 0.289 | 0.0165 | – | – | – | 262,144 | – | api |
| Llama 3.3 70B Instruct | Parasail | fp8 | – | 0.220 | 0.500 | 0.290 | 0.110 | – | – | – | 128,000 | – | api |
| DeepSeek V4 Flash | Azure AI Foundry | – | us | 0.210 | 0.560 | 0.298 | 0.0310 | – | – | – | 1,048,576 | – | api |
| Qwen3-235B-A22B 2 sources | Nebius AI Studio | – | – | 0.200 | 0.600 | 0.300 | 0.200 | – | – | – | 131,072 | – | aggregator |
| Codestral 25.01 | Google Vertex AI | – | – | 0.200 | 0.600 | 0.300 | – | – | – | – | 262,144 | – | aggregator |
| Llama 4 Maverick | DigitalOcean | – | – | 0.188 | 0.653 | 0.304 | 0.0500 | – | – | – | 1,000,000 | – | api |
| Gemini 2.5 Flash-Lite | priority | – | 0.180 | 0.720 | 0.315 | 0.0180 | 0.150 | – | – | 1,048,576 | – | api | |
| DeepSeek V3.2 (chat) | DeepSeek | – | – | 0.280 | 0.420 | 0.315 | 0.0280 | – | – | – | 128,000 | 2026-01-13 ↓ | aggregator |
| DeepSeek V3.2 (reasoner) | DeepSeek | – | – | 0.280 | 0.420 | 0.315 | 0.0280 | – | – | – | 128,000 | 2026-01-13 ↓ | aggregator |
| GPT-5 mini | OpenAI | flex | – | 0.125 | 1.00 | 0.344 | 0.0125 | – | – | – | 400,000 | – | api |
| Llama 4 Scout 2 sources | Azure AI Foundry | – | – | 0.200 | 0.780 | 0.345 | – | – | – | – | 10,000,000 | – | aggregator |
| Llama 4 Maverick 2 sources | DeepInfra | – | – | 0.200 | 0.800 | 0.350 | – | – | – | – | 1,000,000 | 2026-08-27 ↑ | aggregator |
| Qwen3-235B-A22B 2 sources | Novita AI | – | – | 0.200 | 0.800 | 0.350 | – | – | – | – | 131,072 | 2026-01-13 ↓ | aggregator |
| Llama 4 Scout | Google Vertex AI | – | us-east5 | 0.250 | 0.700 | 0.363 | – | – | – | – | 10,000,000 | – | api |
| Llama 4 Scout 2 sources | Google Vertex AI | – | – | 0.250 | 0.700 | 0.363 | – | – | 0.125 | 0.350 | 10,000,000 | – | aggregator |
| DeepSeek V3.2 (chat) | DeepInfra | flex+fp4 | – | 0.256 | 0.712 | 0.370 | – | – | – | – | 128,000 | – | api |
| Qwen3-235B-A22B | Fireworks AI | – | – | 0.220 | 0.880 | 0.385 | – | – | – | – | 131,072 | – | aggregator |
| GPT-6 Luna 2 sources | OpenAI | fast | – | 0.200 | 1.00 | 0.400 | 0.0200 | 0.250 | – | – | 1,050,000 | – | official |
| DeepSeek V3.2 (reasoner) | Hyperbolic | – | – | 0.400 | 0.400 | 0.400 | – | – | – | – | 128,000 | – | aggregator |
| Llama 4 Maverick 2 sources | Novita AI | – | – | 0.270 | 0.850 | 0.415 | – | – | – | – | 1,000,000 | 2026-01-13 ↓ | aggregator |
| Gemini 2.5 Flash | flex | – | 0.150 | 1.25 | 0.425 | 0.0150 | 0.0417 | – | – | 1,048,576 | – | api | |
| DeepSeek V3.2 (chat) 2 sources | DeepInfra | – | – | 0.250 | 0.950 | 0.425 | 0.130 | – | – | – | 128,000 | 2026-08-27 ↓ | aggregator |
| Llama 4 Maverick 2 sources | Azure AI Foundry | – | – | 0.250 | 1.00 | 0.438 | – | – | – | – | 1,000,000 | 2026-09-17 ↕ | aggregator |
| Codestral 25.01 2 sources | Azure AI Foundry | – | – | 0.300 | 0.900 | 0.450 | – | – | – | – | 262,144 | – | aggregator |
| Codestral 25.01 | Mistral AI | – | – | 0.300 | 0.900 | 0.450 | 0.0300 | – | – | – | 262,144 | 2026-08-21 ↓ | aggregator |
| DeepSeek V3.2 (chat) | OpenRouter | – | – | 0.257 | 1.03 | 0.450 | – | – | – | – | 128,000 | – | api |
| DeepSeek V3.2 (chat) | DeepInfra | fp4 | – | 0.320 | 0.890 | 0.463 | – | – | – | – | 128,000 | – | api |
| DeepSeek V4 Flash | Wafer | mxfp4 | – | 0.600 | 0.170 | 0.493 | 0.200 | – | – | – | 1,048,576 | 2026-10-27 ↓ | api |
| DeepSeek V3.2 (chat) | StreamLake promo −10% | – | – | 0.286 | 1.14 | 0.500 | – | – | – | – | 128,000 | – | api |
| Grok 3 mini | Azure AI Foundry | – | – | 0.250 | 1.27 | 0.505 | – | – | – | – | 131,072 | 2026-01-14 ↓ | aggregator |
| Llama 4 Maverick | OpenRouter | – | – | 0.350 | 1.00 | 0.513 | 0.170 | – | – | – | 1,000,000 | – | api |
| Llama 4 Maverick | Parasail | fp8 | – | 0.350 | 1.00 | 0.513 | 0.170 | – | – | – | 1,000,000 | – | api |
| Llama 4 Maverick | Google Vertex AI | – | us-east5 | 0.350 | 1.15 | 0.550 | – | – | – | – | 1,000,000 | – | api |
| Llama 4 Maverick 2 sources | Google Vertex AI | – | – | 0.350 | 1.15 | 0.550 | – | – | 0.175 | 0.575 | 1,000,000 | – | aggregator |
| Qwen3-Coder-480B-A35B | Google Vertex AI | – | – | 0.220 | 1.80 | 0.615 | 0.0220 | – | 0.110 | 0.900 | 262,144 | 2026-08-21 ↓ | aggregator |
| Inkling Small | OpenRouter | – | – | 0.450 | 1.20 | 0.638 | 0.100 | – | – | – | 524,288 | – | api |
| Inkling Small | DeepInfra | fp8 | – | 0.450 | 1.20 | 0.638 | 0.100 | – | – | – | 524,288 | – | api |
| Inkling Small 2 sources | DeepInfra | – | – | 0.450 | 1.20 | 0.638 | 0.100 | – | – | – | 524,288 | – | aggregator |
| Inkling Small | DeepInfra | fp4 | – | 0.450 | 1.20 | 0.638 | 0.100 | – | – | – | 524,288 | – | api |
| Llama 3.3 70B Instruct 2 sources | Groq | – | – | 0.590 | 0.790 | 0.640 | 0.295 | – | – | – | 128,000 | – | api |
| Qwen3-Coder-480B-A35B 2 sources | Novita AI | – | – | 0.380 | 1.55 | 0.673 | – | – | – | – | 262,144 | 2026-08-27 ↑ | aggregator |
| GPT-5 mini | OpenRouter | – | – | 0.250 | 2.00 | 0.688 | 0.0250 | – | – | – | 400,000 | – | api |
| GPT-5 mini 3 sources | Azure AI Foundry | – | – | 0.250 | 2.00 | 0.688 | 0.0300 | – | 0.125 | 1.00 | 400,000 | – | api |
| GPT-5 mini 3 sources | OpenAI | – | – | 0.250 | 2.00 | 0.688 | 0.0250 | – | 0.125 | 1.00 | 400,000 | – | 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