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 | Batch in | Batch out | Context | Tokenizer | Confidence? |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Gemini 2.5 Flash-Lite | flex | – | 0.0500 | 0.200 | 0.0875 | 0.005000 | 0.0417 | – | – | 1,048,576 | gemini | api | |
| Phi-4 3 sources | DeepInfra | – | – | 0.0700 | 0.140 | 0.0875 | – | – | – | – | 16,384 | – | official |
| MythoMax 13B | Parasail | – | – | 0.0800 | 0.110 | 0.0875 | – | – | – | – | 8,192 | – | api |
| Qwen Turbo 2 sources | Alibaba Cloud | – | – | 0.0500 | 0.200 | 0.0875 | – | – | – | – | 129,024 | – | aggregator |
| qwen-turbo-latest | Alibaba Cloud | – | – | 0.0500 | 0.200 | 0.0875 | – | – | – | – | 1,000,000 | – | aggregator |
| Nemotron 3.5 Lightning 30B A3B 2 sources | Fireworks AI | – | – | 0.0500 | 0.200 | 0.0875 | 0.0100 | – | – | – | 262,144 | – | aggregator |
| Nemotron 3 Nano 30B A3B 2 sources | Novita AI | – | – | 0.0500 | 0.200 | 0.0875 | – | – | – | – | 262,144 | – | aggregator |
| Nemotron 3 Nano 30B A3B 2 sources | DeepInfra | – | – | 0.0500 | 0.200 | 0.0875 | 0.0250 | – | – | – | 262,144 | – | aggregator |
| gpt-oss-20b | Together AI | – | – | 0.0500 | 0.200 | 0.0875 | – | – | – | – | 131,072 | o200k | aggregator |
| MiniMax M3.1 Flash | Tenstorrent | fp8 | – | 0.0500 | 0.200 | 0.0875 | 0.005000 | – | – | – | 1,048,576 | – | api |
| Ling 3.0 Flash VL | DeepInfra | – | – | 0.0600 | 0.180 | 0.0900 | 0.0120 | – | – | – | 131,072 | – | api |
| Ling 3.0 Flash Fin | DeepInfra | fp4 | – | 0.0600 | 0.180 | 0.0900 | 0.0120 | – | – | – | 262,144 | – | api |
| Ling 3.0 Flash 3 sources | Novita AI promo −65% | – | – | 0.0600 | 0.180 | 0.0900 | 0.0120 | – | – | – | 262,144 | – | api |
| Ling 3.0 Flash 2 sources | DeepInfra | – | – | 0.0600 | 0.180 | 0.0900 | 0.0120 | – | – | – | 262,144 | – | api |
| gpt-oss-20b 2 sources | AWS Bedrock | – | eu-west-1 | 0.0700 | 0.150 | 0.0900 | – | – | – | – | 131,072 | o200k | api |
| gpt-oss-20b 3 sources | AWS Bedrock | – | – | 0.0700 | 0.150 | 0.0900 | – | – | 0.0350 | 0.150 | 131,072 | o200k | api |
| MythoMax 13B 2 sources | Novita AI | – | – | 0.0900 | 0.0900 | 0.0900 | – | – | – | – | 8,192 | – | aggregator |
| inclusionai/ling-3.0-flash-fast | Novita AI | – | – | 0.0600 | 0.180 | 0.0900 | 0.0120 | – | – | – | 262,144 | – | aggregator |
| Embed v4 | Azure AI Foundry | – | – | 0.120 | free | 0.0900 | – | – | – | – | 128,000 | – | aggregator |
| DeepSeek-V4-Flash-0731 | DeepInfra | – | – | 0.0600 | 0.180 | 0.0900 | 0.0150 | – | – | – | 1,048,576 | – | official |
| DeepSeek-V4-Flash-0731 | DeepInfra | fp8 | – | 0.0600 | 0.180 | 0.0900 | 0.0150 | – | – | – | 1,048,576 | – | api |
| Ling 3.0 Flash VL | DeepInfra | fp4 | – | 0.0600 | 0.180 | 0.0900 | 0.0120 | – | – | – | 131,072 | – | api |
| Qwen3.5-9B | DeepInfra | flex | – | 0.0800 | 0.120 | 0.0900 | – | – | – | – | 262,144 | qwen2 | api |
| Ling 3.0 Flash | DeepInfra | fp4 | – | 0.0600 | 0.180 | 0.0900 | 0.0120 | – | – | – | 262,144 | – | api |
| DeepSeek V4 Flash | DeepInfra | flex+fp8 | – | 0.0720 | 0.144 | 0.0900 | 0.0144 | – | – | – | 1,048,576 | deepseek | api |
| Qwen3.5-9B | Darkbloom | fp4 | – | 0.0800 | 0.130 | 0.0925 | 0.0400 | – | – | – | 262,144 | qwen2 | api |
| Ternary Bonsai 2 9B | Darkbloom | int4 | – | 0.0800 | 0.130 | 0.0925 | 0.0400 | – | – | – | 262,144 | qwen2 | api |
| Ternary Bonsai 2 9B | OpenRouter | – | – | 0.0800 | 0.130 | 0.0925 | 0.0400 | – | – | – | 262,144 | qwen2 | api |
| Gemma 3 12B | NextBit | int4 | – | 0.0750 | 0.150 | 0.0938 | 0.0500 | – | – | – | 131,072 | gemini | api |
| GLM 5.3 Flash | Darkbloom | fp4 | – | 0.0650 | 0.180 | 0.0938 | 0.0120 | – | – | – | 1,048,576 | – | api |
| Gemma 3 4B | DeepInfra | priority | – | 0.0750 | 0.150 | 0.0938 | – | – | – | – | 131,072 | gemini | api |
| Schematron V2 Small | OpenRouter | – | – | 0.0500 | 0.230 | 0.0950 | 0.0500 | – | – | – | 128,000 | – | api |
| Schematron V2 Small | Inference.net | – | – | 0.0500 | 0.230 | 0.0950 | 0.0500 | – | – | – | 128,000 | – | api |
| Qwen2.5 32B Instruct | Nebius AI Studio | – | – | 0.0600 | 0.200 | 0.0950 | – | – | – | – | 128,000 | – | aggregator |
| Schematron V2 Small | Inference.net | – | us | 0.0500 | 0.230 | 0.0950 | 0.0500 | – | – | – | 128,000 | – | api |
| text-embedding-3-large | Azure AI Foundry | – | – | 0.130 | free | 0.0975 | – | – | – | – | 8,191 | – | aggregator |
| text-embedding-3-large | OpenAI | – | – | 0.130 | free | 0.0975 | – | – | – | – | 8,191 | – | aggregator |
| Reka Edge | OpenRouter | – | – | 0.100 | 0.100 | 0.100 | – | – | – | – | 16,384 | – | api |
| Ministral 3 3B 2512 | OpenRouter | – | – | 0.100 | 0.100 | 0.100 | 0.0100 | – | – | – | 131,072 | mistral | api |
| GPT-6 Luna Pro | OpenAI | flex | – | 0.0500 | 0.250 | 0.100 | 0.005000 | 0.0625 | – | – | 1,050,000 | o200k | api |
| GPT-6 Luna 2 sources | OpenAI | flex | – | 0.0500 | 0.250 | 0.100 | 0.005000 | 0.0625 | – | – | 1,050,000 | o200k | official |
| Reka Edge | Reka AI | – | – | 0.100 | 0.100 | 0.100 | – | – | – | – | 16,384 | – | api |
| Ministral 3 3B 2512 | Mistral AI | zdr | – | 0.100 | 0.100 | 0.100 | 0.0100 | – | – | – | 131,072 | mistral | api |
| Ministral 3 3B 2512 3 sources | Mistral AI | – | – | 0.100 | 0.100 | 0.100 | 0.0100 | – | – | – | 131,072 | mistral | api |
| gpt-oss-120b | Crusoe | – | – | 0.0500 | 0.250 | 0.100 | 0.0500 | – | – | – | 131,072 | o200k | api |
| Gemma 3 27B | DeepInfra | fp8 | – | 0.0800 | 0.160 | 0.100 | – | – | – | – | 131,072 | gemini | api |
| FW-Nemotron-Lightning-3.5-30B-A3B | Azure AI Foundry | – | – | 0.0600 | 0.220 | 0.100 | 0.0100 | – | – | – | 262,144 | – | aggregator |
| llama3.1-8b | Cerebras | – | – | 0.100 | 0.100 | 0.100 | – | – | – | – | 128,000 | – | aggregator |
| Gemma 3 27B 3 sources | DeepInfra | – | – | 0.0800 | 0.160 | 0.100 | – | – | – | – | 131,072 | gemini | official |
| eu.meta.llama3-2-1b-instruct-v1:0 | AWS Bedrock | – | – | 0.100 | 0.100 | 0.100 | – | – | – | – | 128,000 | – | 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