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 every active offering, including the long tail. Show curated models only
More columns: + Vendor + Region + Cache - Batch - Tokenizer - Last change + Source All columns Default columns
| Model | Host | Variant | Region | Input | Output | Blended ↑? | Batch in | Batch out | Context | Tokenizer | Last change | Confidence? |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| GPT-5 nano | OpenRouter | – | – | 0.0500 | 0.400 | 0.138 | – | – | 400,000 | o200k | – | api |
| Qwen3.5-9B | Parasail | – | – | 0.100 | 0.250 | 0.138 | – | – | 262,144 | qwen2 | – | api |
| GPT-5 nano 3 sources | Azure AI Foundry | – | – | 0.0500 | 0.400 | 0.138 | 0.0250 | 0.200 | 400,000 | o200k | – | api |
| GPT-5 nano 3 sources | OpenAI | – | – | 0.0500 | 0.400 | 0.138 | 0.0250 | 0.200 | 400,000 | o200k | – | api |
| Gemma 4 26B A4B 3 sources | DeepInfra | – | – | 0.0700 | 0.340 | 0.138 | – | – | 262,144 | gemma | – | official |
| Gemma 4 26B A4B | Makora | – | – | 0.0900 | 0.280 | 0.138 | – | – | 262,144 | gemma | 2026-11-13 ↑ | api |
| GPT-5 nano | Perplexity | – | – | 0.0500 | 0.400 | 0.138 | – | – | 400,000 | o200k | – | aggregator |
| Gemma 3 27B 3 sources | Novita AI | – | – | 0.119 | 0.200 | 0.139 | – | – | 131,072 | gemini | 2026-01-13 ↓ | api |
| Phi 4 Multimodal | Azure AI Foundry | – | – | 0.0800 | 0.320 | 0.140 | – | – | 131,072 | – | 2025-04-14 ↓ | aggregator |
| Gemma 3 12B 2 sources | AWS Bedrock | – | – | 0.0900 | 0.290 | 0.140 | 0.0500 | 0.150 | 131,072 | gemini | – | aggregator |
| Hermes 2 Pro Llama 3 8B 2 sources | Novita AI | – | – | 0.140 | 0.140 | 0.140 | – | – | 8,192 | – | 2026-01-13 ↓ | aggregator |
| Phi-4-multimodal | Azure AI Foundry | – | – | 0.0800 | 0.320 | 0.140 | – | – | 128,000 | – | – | aggregator |
| Gemma 4 26B A4B | NextBit promo −15% | – | – | 0.0900 | 0.300 | 0.143 | – | – | 262,144 | gemma | – | api |
| Qwen3 30B A3B Instruct 2507 | DekaLLM | – | – | 0.0900 | 0.300 | 0.143 | – | – | 262,144 | qwen2 | – | api |
| Qwen3 30B A3B Instruct 2507 | SiliconFlow | fp8 | – | 0.0900 | 0.300 | 0.143 | – | – | 262,144 | qwen2 | – | api |
| Mistral Small 3.2 24B | Parasail | – | – | 0.0900 | 0.300 | 0.143 | – | – | 256,000 | mistral | – | api |
| Llama Guard 4 12B | DeepInfra | flex | – | 0.144 | 0.144 | 0.144 | – | – | 163,840 | – | – | api |
| Gemma 3 12B | AWS Bedrock | – | ap-southeast-2 | 0.0927 | 0.299 | 0.144 | – | – | 131,072 | gemini | – | aggregator |
| Hy3 | Tencent Cloud | fp8+off-peak | – | 0.0825 | 0.330 | 0.144 | – | – | 262,144 | – | – | api |
| Hy3 | OpenRouter | off-peak | – | 0.0825 | 0.330 | 0.144 | – | – | 262,144 | – | – | api |
| MiMo-V2.6-Flash | io.net | fp8 | – | 0.100 | 0.280 | 0.145 | – | – | 1,050,000 | – | 2026-10-23 ↓ | api |
| MiMo-V2.6-Flash | Darkbloom | fp4 | – | 0.100 | 0.280 | 0.145 | – | – | 1,050,000 | – | 2026-10-06 ↓ | api |
| GLM 4.7 Flash 2 sources | DeepInfra | – | – | 0.0600 | 0.400 | 0.145 | – | – | 200,000 | – | – | aggregator |
| gpt-oss-120b | SAIL Research | fp4 | – | 0.0600 | 0.400 | 0.145 | – | – | 131,072 | o200k | – | api |
| GLM 4.7 Flash | OpenRouter | – | – | 0.0605 | 0.400 | 0.145 | – | – | 200,000 | – | – | api |
| GLM 4.7 Flash | Cloudflare Workers AI | – | – | 0.0605 | 0.400 | 0.145 | – | – | 200,000 | – | – | api |
| DeepSeek V4.1 Flash 1017 | ambient | fp4 | – | 0.0980 | 0.294 | 0.147 | – | – | 1,048,576 | deepseek | – | api |
| Gemma 3 27B | NextBit | fp8 | – | 0.0800 | 0.350 | 0.148 | – | – | 131,072 | gemini | – | api |
| gpt-oss-20b | AWS Bedrock | – | ap-south-1 | 0.0800 | 0.350 | 0.148 | – | – | 131,072 | o200k | – | aggregator |
| MiMo-V2.5 | OpenRouter | – | – | 0.119 | 0.238 | 0.149 | – | – | 1,000,000 | – | – | api |
| DeepSeek V4 Flash 0731 | DigitalOcean | – | – | 0.119 | 0.238 | 0.149 | – | – | 1,048,576 | deepseek | – | api |
| Ministral 3 8B 2512 | OpenRouter | – | – | 0.150 | 0.150 | 0.150 | – | – | 262,144 | mistral | – | api |
| Voxtral Small 24B 2507 | OpenRouter | – | – | 0.100 | 0.300 | 0.150 | – | – | 32,768 | mistral | – | api |
| Qwen3 30B A3B Instruct 2507 | OpenRouter | – | – | 0.100 | 0.300 | 0.150 | – | – | 262,144 | qwen2 | – | api |
| Qwen3 14B | OpenRouter | – | – | 0.120 | 0.240 | 0.150 | – | – | 40,960 | qwen2 | – | api |
| Llama 4 Scout | OpenRouter | – | – | 0.100 | 0.300 | 0.150 | – | – | 10,000,000 | llama3 | – | api |
| DeepSeek V4 Flash | Relace | fp4 | – | 0.0500 | 0.450 | 0.150 | – | – | 1,048,576 | deepseek | 2026-11-11 ↑ | api |
| Step 3.5 Flash | SiliconFlow | fp8 | – | 0.100 | 0.300 | 0.150 | – | – | 262,144 | – | – | api |
| Ministral 3 8B 2512 | Mistral AI | zdr | – | 0.150 | 0.150 | 0.150 | – | – | 262,144 | mistral | – | api |
| Ministral 3 8B 2512 3 sources | Mistral AI | – | – | 0.150 | 0.150 | 0.150 | – | – | 262,144 | mistral | – | api |
| Voxtral Small 24B 2507 | Mistral AI | zdr | – | 0.100 | 0.300 | 0.150 | – | – | 32,768 | mistral | – | api |
| Voxtral Small 24B 2507 | Mistral AI | – | – | 0.100 | 0.300 | 0.150 | – | – | 32,768 | mistral | – | api |
| gpt-oss-120b | DigitalOcean | – | – | 0.0600 | 0.420 | 0.150 | – | – | 131,072 | o200k | – | api |
| Qwen3 30B A3B Instruct 2507 | Nebius AI Studio | fp8 | – | 0.100 | 0.300 | 0.150 | – | – | 262,144 | qwen2 | – | api |
| Mistral Small 3.2 24B | Mistral AI | – | eu | 0.100 | 0.300 | 0.150 | – | – | 256,000 | mistral | – | api |
| Qwen3 14B | DeepInfra | fp8 | – | 0.120 | 0.240 | 0.150 | – | – | 40,960 | qwen2 | – | api |
| Llama 4 Scout | DeepInfra | fp8 | – | 0.100 | 0.300 | 0.150 | – | – | 10,000,000 | llama3 | – | api |
| Gemma 3 27B | Nebius AI Studio | fp8 | – | 0.100 | 0.300 | 0.150 | – | – | 131,072 | gemini | – | api |
| Mistral Nemo | Mistral AI | – | eu | 0.150 | 0.150 | 0.150 | – | – | 131,072 | mistral | – | api |
| Mistral Nemo | Azure AI Foundry | – | – | 0.150 | 0.150 | 0.150 | – | – | 131,072 | mistral | – | aggregator |
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