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 | Last change | Confidence? |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Reka Flash 3 | OpenRouter | – | – | 0.100 | 0.200 | 0.125 | – | – | – | – | 65,536 | – | – | api |
| Muse Spark 1.3 Contributor 3 sources | Meta | – | – | 0.100 | 0.200 | 0.125 | 0.002000 | – | – | – | 1,048,576 | – | – | api |
| Muse Spark 1.2 Contributor 3 sources | Meta | – | – | 0.100 | 0.200 | 0.125 | 0.002000 | – | – | – | 1,048,576 | – | – | api |
| Laguna S 2.1 | Poolside promo −10% | fp4 | – | 0.100 | 0.200 | 0.125 | 0.0100 | – | – | – | 1,048,576 | – | – | api |
| Laguna XS 2.1 | Poolside promo −40% | fp8 | – | 0.100 | 0.200 | 0.125 | 0.0500 | – | – | – | 262,144 | – | – | api |
| UI-TARS 7B | Parasail | – | – | 0.100 | 0.200 | 0.125 | 0.100 | – | – | – | 128,000 | – | – | api |
| Reka Flash 3 | Reka AI | – | – | 0.100 | 0.200 | 0.125 | – | – | – | – | 65,536 | – | – | api |
| Qwen2.5 7B Instruct | Phala | – | – | 0.100 | 0.200 | 0.125 | – | – | – | – | 32,768 | qwen2 | – | api |
| nvidia.nemotron-nano-3-30b | AWS Bedrock | – | ap-northeast-1 | 0.0700 | 0.290 | 0.125 | – | – | – | – | 256,000 | – | – | aggregator |
| nvidia.nemotron-nano-3-30b | AWS Bedrock | – | sa-east-1 | 0.0700 | 0.290 | 0.125 | – | – | – | – | 256,000 | – | – | aggregator |
| Amazon Nova Lite | AWS Bedrock | – | us-gov-west-1 | 0.0720 | 0.288 | 0.126 | 0.0180 | – | 0.0360 | 0.144 | 300,000 | – | – | aggregator |
| nvidia.nemotron-nano-3-30b | AWS Bedrock | – | us-gov-east-1 | 0.0720 | 0.288 | 0.126 | – | – | 0.0360 | 0.144 | 256,000 | – | – | aggregator |
| nvidia.nemotron-nano-3-30b | AWS Bedrock | – | us-gov-west-1 | 0.0720 | 0.288 | 0.126 | – | – | 0.0360 | 0.144 | 256,000 | – | – | aggregator |
| nvidia.nemotron-nano-3-30b | AWS Bedrock | – | us-gov | 0.0720 | 0.288 | 0.126 | – | – | – | – | 256,000 | – | – | aggregator |
| nvidia.nemotron-nano-3-30b | AWS Bedrock | – | ap-southeast-3 | 0.0720 | 0.288 | 0.126 | – | – | – | – | 256,000 | – | – | aggregator |
| nvidia.nemotron-nano-3-30b | AWS Bedrock | – | eu-central-1 | 0.0720 | 0.288 | 0.126 | – | – | – | – | 256,000 | – | – | aggregator |
| nvidia.nemotron-nano-3-30b | AWS Bedrock | – | eu-north-1 | 0.0720 | 0.288 | 0.126 | – | – | – | – | 256,000 | – | – | aggregator |
| gpt-oss-20b | Fireworks AI | – | – | 0.0700 | 0.300 | 0.128 | 0.0350 | – | – | – | 131,072 | o200k | 2026-06-18 ↑ | aggregator |
| openai.gpt-oss-20b-1:0 | AWS Bedrock | – | – | 0.0700 | 0.300 | 0.128 | – | – | 0.0350 | 0.150 | 128,000 | – | – | aggregator |
| Hy-MT2-30B-A3B | OpenRouter | – | – | 0.0740 | 0.295 | 0.129 | – | – | – | – | 8,192 | – | – | api |
| Hy-MT2-7B | OpenRouter | – | – | 0.0740 | 0.295 | 0.129 | – | – | – | – | 8,192 | – | – | api |
| Hy-MT2-30B-A3B | Tencent Cloud | fp8 | – | 0.0740 | 0.295 | 0.129 | – | – | – | – | 8,192 | – | – | api |
| Hy-MT2-7B | Tencent Cloud | fp8 | – | 0.0740 | 0.295 | 0.129 | – | – | – | – | 8,192 | – | – | api |
| Qwen3 32B | OpenRouter | – | – | 0.0800 | 0.280 | 0.130 | – | – | – | – | 131,072 | qwen2 | – | api |
| Qwen3 14B | NextBit | int4 | – | 0.100 | 0.220 | 0.130 | – | – | – | – | 40,960 | qwen2 | – | api |
| Qwen3 32B | DeepInfra | fp8 | – | 0.0800 | 0.280 | 0.130 | – | – | – | – | 131,072 | qwen2 | – | api |
| Qwen3 32B 3 sources | DeepInfra | – | – | 0.0800 | 0.280 | 0.130 | – | – | – | – | 131,072 | qwen2 | 2026-08-27 ↓ | official |
| GLM-4.6V-FlashX | Zhipu AI (Z.ai) | – | – | 0.0400 | 0.400 | 0.130 | 0.004000 | – | – | – | – | – | – | official |
| eu.meta.llama3-2-1b-instruct-v1:0 | AWS Bedrock | – | eu | 0.130 | 0.130 | 0.130 | – | – | – | – | 128,000 | – | – | aggregator |
| eu.meta.llama3-2-1b-instruct-v1:0 | AWS Bedrock | – | eu-central-1 | 0.130 | 0.130 | 0.130 | – | – | – | – | 128,000 | – | – | aggregator |
| eu.meta.llama3-2-1b-instruct-v1:0 | AWS Bedrock | – | eu-west-3 | 0.130 | 0.130 | 0.130 | – | – | – | – | 128,000 | – | – | aggregator |
| gpt-oss-20b | AWS Bedrock | – | ap-southeast-3 | 0.0700 | 0.310 | 0.130 | – | – | – | – | 131,072 | o200k | – | aggregator |
| gpt-oss-safeguard-20b | OpenRouter | – | – | 0.0750 | 0.300 | 0.131 | 0.0375 | – | – | – | 131,072 | o200k | – | api |
| Seed 1.6 Flash | ByteDance Seed | fp8 | – | 0.0750 | 0.300 | 0.131 | – | – | – | – | 262,144 | – | – | api |
| gpt-oss-safeguard-20b 3 sources | Groq | – | – | 0.0750 | 0.300 | 0.131 | 0.0375 | – | – | – | 131,072 | o200k | – | api |
| gpt-oss-20b 3 sources | Groq | – | – | 0.0750 | 0.300 | 0.131 | 0.0375 | – | – | – | 131,072 | o200k | 2026-01-21 ↓ | api |
| Phi-4-Mini | Azure AI Foundry | – | – | 0.0750 | 0.300 | 0.131 | – | – | – | – | 131,072 | – | – | aggregator |
| Phi-4-mini-reasoning 2 sources | Azure AI Foundry | – | – | 0.0750 | 0.300 | 0.131 | – | – | – | – | 131,072 | – | 2026-09-17 ↓ | aggregator |
| DeepSeek V4 Flash 2 sources | Fireworks AI | – | – | 0.105 | 0.210 | 0.131 | 0.0210 | – | – | – | 1,048,576 | deepseek | – | api |
| gemini-2.0-flash-lite | Google Vertex AI | – | – | 0.0750 | 0.300 | 0.131 | – | – | 0.0375 | 0.150 | – | – | – | aggregator |
| Phi-4-mini | Azure AI Foundry | – | – | 0.0750 | 0.300 | 0.131 | – | – | – | – | 128,000 | – | – | aggregator |
| accounts/fireworks/routers/spot-deepseek-v4-flash | Fireworks AI | – | – | 0.105 | 0.210 | 0.131 | 0.0210 | – | – | – | 1,048,576 | – | – | aggregator |
| MiniMax M3.1 Flash | MiniMax | off-peak | – | 0.0750 | 0.300 | 0.131 | 0.007500 | – | – | – | 1,048,576 | – | – | api |
| MiniMax M3.1 Flash | OpenRouter | off-peak | – | 0.0750 | 0.300 | 0.131 | 0.007500 | – | – | – | 1,048,576 | – | – | api |
| gpt-oss-20b | AWS Bedrock | – | ap-southeast-2 | 0.0721 | 0.309 | 0.131 | – | – | – | – | 131,072 | o200k | – | aggregator |
| Nemotron 3.5 Super VL | Darkbloom | nvfp4 | – | 0.0600 | 0.350 | 0.133 | 0.0100 | – | – | – | 1,048,576 | – | – | api |
| Mistral Small 3.2 24B | Venice | fp8 | – | 0.0938 | 0.250 | 0.133 | – | – | – | – | 256,000 | mistral | – | api |
| nano-banana-pro | Together AI | – | – | – | 0.134 | 0.134 | – | – | – | – | – | – | – | official |
| DeepSeek-V4-Flash-0731 | DeepInfra | fp8+priority | – | 0.0900 | 0.270 | 0.135 | 0.0225 | – | – | – | 1,048,576 | – | – | api |
| Amazon Nova Lite | AWS Bedrock | – | eu | 0.0780 | 0.312 | 0.137 | 0.0195 | – | – | – | 300,000 | – | – | 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