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 ↑? | Cache read | Cache write | Context | Last change | Confidence? |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Command R7B | Cohere | – | – | 0.0375 | 0.150 | 0.0656 | – | – | – | – | official |
| Gemma 4 26B A4B | Darkbloom | – | – | 0.0400 | 0.150 | 0.0675 | 0.0100 | – | 262,144 | 2026-11-03 ↓ | api |
| gpt-oss-120b | DekaLLM | – | – | 0.0300 | 0.180 | 0.0675 | 0.0300 | – | 131,072 | – | api |
| gpt-oss-20b 2 sources | Novita AI | – | – | 0.0400 | 0.150 | 0.0675 | – | – | 131,072 | 2026-01-13 ↓ | aggregator |
| DeepSeek R1 0528 Qwen3 8B 2 sources | Novita AI | – | – | 0.0600 | 0.0900 | 0.0675 | – | – | 128,000 | 2026-01-13 ↓ | aggregator |
| Ling 3.1 Flash | OpenRouter | – | – | 0.0450 | 0.135 | 0.0675 | 0.009000 | – | 1,000,000 | – | api |
| GPT-5 nano | OpenAI | flex | – | 0.0250 | 0.200 | 0.0688 | 0.002500 | – | 400,000 | – | api |
| gemini-31-flash-lite-image | Together AI | – | – | – | 0.0690 | 0.0690 | – | – | – | – | official |
| gpt-oss-120b | AkashML | fp4 | – | 0.0300 | 0.187 | 0.0693 | 0.0300 | – | 131,072 | – | api |
| nvidia/NVIDIA-Nemotron-Nano-9B-v2 | DeepInfra | – | – | 0.0400 | 0.160 | 0.0700 | – | – | 131,072 | – | aggregator |
| Baichuan M2 32B 2 sources | Novita AI | – | – | 0.0700 | 0.0700 | 0.0700 | – | – | 131,072 | 2026-01-13 ↓ | aggregator |
| Qwen2.5 7B Instruct 2 sources | Novita AI | – | – | 0.0700 | 0.0700 | 0.0700 | – | – | 32,768 | 2026-01-13 ↓ | aggregator |
| flux-2-max | Together AI | – | – | 0.0700 | – | 0.0700 | – | – | – | – | official |
| Phi-4 | DeepInfra | flex | – | 0.0560 | 0.112 | 0.0700 | – | – | 16,384 | – | api |
| gpt-oss-120b 3 sources | DeepInfra | – | – | 0.0370 | 0.170 | 0.0703 | 0.0185 | – | 131,072 | 2026-08-27 ↓ | api |
| Llama 3.2 1B Instruct | OpenRouter | – | – | 0.0270 | 0.201 | 0.0705 | – | – | 60,000 | – | api |
| Llama 3.2 1B Instruct | Cloudflare Workers AI | – | – | 0.0270 | 0.201 | 0.0705 | – | – | 60,000 | – | api |
| arcee-ai/trinity-mini | Together AI | – | – | 0.0450 | 0.150 | 0.0713 | – | – | 128,000 | – | aggregator |
| DeepSeek-V4-Flash-0731 | DeepInfra | flex+fp8 | – | 0.0480 | 0.144 | 0.0720 | 0.0120 | – | 1,048,576 | – | api |
| Mistral Nemo 2 sources | Novita AI | – | – | 0.0400 | 0.170 | 0.0725 | – | – | 131,072 | 2026-01-13 ↓ | aggregator |
| Amazon Nova Micro | AWS Bedrock | – | us-gov-west-1 | 0.0420 | 0.168 | 0.0735 | 0.0105 | – | 128,000 | – | aggregator |
| Gemma 3 12B | OpenRouter | – | – | 0.0500 | 0.150 | 0.0750 | – | – | 131,072 | – | api |
| gpt-oss-20b | SiliconFlow | fp8 | – | 0.0400 | 0.180 | 0.0750 | – | – | 131,072 | – | api |
| Gemma 3 12B 4 sources | DeepInfra | – | – | 0.0500 | 0.150 | 0.0750 | – | – | 131,072 | 2026-08-27 ↑ | official |
| text-embedding-ada-002 | Azure AI Foundry | – | – | 0.100 | free | 0.0750 | – | – | 8,192 | – | aggregator |
| Embed v3 Multilingual | Azure AI Foundry | – | – | 0.100 | free | 0.0750 | – | – | 512 | – | aggregator |
| Embed v3 English | Azure AI Foundry | – | – | 0.100 | free | 0.0750 | – | – | 512 | – | aggregator |
| Mistral Embed | Mistral AI | – | – | 0.100 | free | 0.0750 | – | – | 8,000 | – | aggregator |
| text-embedding-ada-002 | OpenAI | – | – | 0.100 | free | 0.0750 | – | – | 8,192 | – | aggregator |
| qwen-image-20-pro | Together AI | – | – | – | 0.0750 | 0.0750 | – | – | – | 2026-11-11 ↓ | official |
| Gemma 3 4B | AWS Bedrock | – | eu-west-2 | 0.0600 | 0.120 | 0.0750 | – | – | 131,072 | – | aggregator |
| Hy-MT2-1.8B | OpenRouter | – | – | 0.0440 | 0.177 | 0.0773 | – | – | 8,192 | – | api |
| Hy-MT2-1.8B | Tencent Cloud | fp8 | – | 0.0440 | 0.177 | 0.0773 | – | – | 8,192 | – | api |
| GLM 5.3 Flash | Wafer | nvfp4 | us | 0.0420 | 0.184 | 0.0775 | 0.0410 | – | 1,048,576 | 2026-11-11 ↑ | api |
| DeepSeek V4.1 Flash 1017 | SAIL Research | fp4 | us | 0.0700 | 0.100 | 0.0775 | 0.007000 | – | 1,048,576 | 2026-11-16 ↓ | api |
| Embed 5 Fast | Cohere | – | – | 0.0800 | – | 0.0800 | – | – | – | – | official |
| flux-1-kontext-max | Together AI | – | – | 0.0800 | – | 0.0800 | – | – | – | – | official |
| Gemma 3 27B | DeepInfra | flex+fp8 | – | 0.0640 | 0.128 | 0.0800 | – | – | 131,072 | – | api |
| Amazon Nova Micro | AWS Bedrock | – | eu | 0.0460 | 0.184 | 0.0805 | 0.0115 | – | 128,000 | – | aggregator |
| Granite 4.2 8B | OpenRouter | – | – | 0.0600 | 0.150 | 0.0825 | 0.0150 | – | 131,072 | – | api |
| Granite 4.2 8B | CoreWeave | – | – | 0.0600 | 0.150 | 0.0825 | 0.0150 | – | 131,072 | 2026-11-02 ↓ | api |
| NVIDIA-Nemotron-3.5-Lightning 2 sources | DeepInfra | – | – | 0.0600 | 0.160 | 0.0850 | 0.0300 | – | 262,144 | 2026-11-12 ↓ | official |
| DeepSeek V4.1 Flash 1017 | particle-ai | flex | us | 0.0300 | 0.250 | 0.0850 | 0.005000 | – | 1,048,576 | – | api |
| Mistral Small 3.2 24B | DeepInfra | flex+fp8 | – | 0.0600 | 0.160 | 0.0850 | – | – | 256,000 | – | api |
| Particle-1 | particle-ai | flex | us | 0.0300 | 0.250 | 0.0850 | 0.001500 | – | 1,048,576 | – | api |
| Solar Mini 4 | OpenRouter | – | – | 0.0500 | 0.200 | 0.0875 | 0.005000 | – | 524,288 | – | api |
| Phi-4 | OpenRouter | – | – | 0.0700 | 0.140 | 0.0875 | – | – | 16,384 | – | api |
| MythoMax 13B | OpenRouter | – | – | 0.0800 | 0.110 | 0.0875 | – | – | 8,192 | – | api |
| DeepSeek V4 Flash 0731 | Relace | fp4 | – | 0.0700 | 0.140 | 0.0875 | 0.0140 | – | 1,048,576 | 2026-11-03 ↕ | api |
| Nemotron 3 Nano 30B A3B | Novita AI | fp4 | – | 0.0500 | 0.200 | 0.0875 | – | – | 262,144 | – | 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