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 | Context | Confidence? |
|---|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 5.5 | Perplexity | – | – | 4.00 | 20.00 | 8.00 | 0.200 | – | 1,000,000 | aggregator |
| Claude Opus 5.5 | AWS Bedrock | – | global | 4.00 | 20.00 | 8.00 | 0.200 | 5.00 | 1,000,000 | aggregator |
| Claude Opus 5.5 | DeepInfra | – | – | 4.00 | 20.00 | 8.00 | 0.200 | – | 1,000,000 | official |
| Nano Banana 2.1 | Google Vertex AI | – | – | 1.50 | 30.00 | 8.63 | 0.150 | – | 65,536 | aggregator |
| Claude Opus 5.5 | AWS Bedrock | – | eu-west-1 | 4.40 | 22.00 | 8.80 | 0.220 | 5.50 | 1,000,000 | api |
| Claude Opus 5.5 | AWS Bedrock | – | us-east-1 | 4.40 | 22.00 | 8.80 | 0.220 | 5.50 | 1,000,000 | api |
| Claude Opus 5.5 | Azure AI Foundry | – | us | 4.40 | 22.00 | 8.80 | 0.220 | 5.50 | 1,000,000 | api |
| Claude Opus 5.5 | Google Vertex AI | – | us | 4.40 | 22.00 | 8.80 | 0.220 | 5.50 | 1,000,000 | api |
| Claude Opus 5.5 | Google Vertex AI | – | europe | 4.40 | 22.00 | 8.80 | 0.220 | 5.50 | 1,000,000 | api |
| Claude Opus 5.5 | AWS Bedrock | – | apac | 4.40 | 22.00 | 8.80 | 0.220 | 5.50 | 1,000,000 | aggregator |
| Claude Opus 5.5 | AWS Bedrock | – | au | 4.40 | 22.00 | 8.80 | 0.220 | 5.50 | 1,000,000 | aggregator |
| Claude Opus 5.5 | AWS Bedrock | – | eu | 4.40 | 22.00 | 8.80 | 0.220 | 5.50 | 1,000,000 | aggregator |
| Claude Opus 5.5 | AWS Bedrock | – | jp | 4.40 | 22.00 | 8.80 | 0.220 | 5.50 | 1,000,000 | aggregator |
| Claude Opus 5.5 | AWS Bedrock | – | us | 4.40 | 22.00 | 8.80 | 0.220 | 5.50 | 1,000,000 | aggregator |
| Claude Opus 5.5 | AWS Bedrock | – | us-gov-east-1 | 4.80 | 24.00 | 9.60 | 0.240 | 6.00 | 1,000,000 | aggregator |
| Claude Opus 5.5 | AWS Bedrock | – | us-gov-west-1 | 4.80 | 24.00 | 9.60 | 0.240 | 6.00 | 1,000,000 | aggregator |
| Claude Opus 5.5 | AWS Bedrock | – | us-gov | 4.80 | 24.00 | 9.60 | 0.240 | 6.00 | 1,000,000 | aggregator |
| Claude Opus 4.5 | OpenRouter | – | – | 5.00 | 25.00 | 10.00 | 0.500 | 6.25 | 200,000 | api |
| GPT-6 Astra 2 sources | OpenAI | flex | – | 5.00 | 25.00 | 10.00 | 0.500 | 6.25 | 1,050,000 | official |
| Claude Opus 4.5 | Claude on AWS | – | – | 5.00 | 25.00 | 10.00 | 0.500 | 6.25 | 200,000 | api |
| Claude Opus 4.5 | Azure AI Foundry | – | global | 5.00 | 25.00 | 10.00 | 0.500 | 6.25 | 200,000 | api |
| Claude Opus 4.5 | Google Vertex AI | – | global | 5.00 | 25.00 | 10.00 | 0.500 | 6.25 | 200,000 | api |
| Claude Opus 4.5 3 sources | AWS Bedrock | – | – | 5.00 | 25.00 | 10.00 | 0.500 | 6.25 | 200,000 | api |
| Claude Opus 4.5 4 sources | Anthropic | – | – | 5.00 | 25.00 | 10.00 | 0.500 | 6.25 | 200,000 | official |
| Claude Opus 4.5 2 sources | Azure AI Foundry | – | – | 5.00 | 25.00 | 10.00 | 0.500 | 6.25 | 200,000 | aggregator |
| Claude Opus 4.5 | Perplexity | – | – | 5.00 | 25.00 | 10.00 | 0.500 | – | 200,000 | aggregator |
| Claude Opus 4.5 2 sources | Google Vertex AI | – | – | 5.00 | 25.00 | 10.00 | 0.500 | 6.25 | 200,000 | aggregator |
| GPT-Rosalind Research 2 sources | OpenAI | – | – | 5.00 | 25.00 | 10.00 | 0.500 | – | – | official |
| GPT-6 Astra | OpenAI | batch | – | 5.00 | 25.00 | 10.00 | 0.500 | 6.25 | 1,050,000 | official |
| Claude Opus 4.5 | AWS Bedrock | – | global | 5.00 | 25.00 | 10.00 | 0.500 | 6.25 | 200,000 | aggregator |
| GPT-Rosalind Discovery 2 sources | OpenAI | – | – | 5.00 | 25.00 | 10.00 | 0.500 | – | – | official |
| Claude Opus 4.5 | AWS Bedrock | – | eu-west-1 | 5.50 | 27.50 | 11.00 | 0.550 | 6.88 | 200,000 | api |
| Claude Opus 4.5 | AWS Bedrock | – | eu | 5.50 | 27.50 | 11.00 | 0.550 | 6.88 | 200,000 | aggregator |
| Claude Opus 4.5 | AWS Bedrock | – | us | 5.50 | 27.50 | 11.00 | 0.550 | 6.88 | 200,000 | aggregator |
| Claude Opus 5.5 | Anthropic | fast | – | 8.00 | 40.00 | 16.00 | 0.400 | 10.00 | 1,000,000 | api |
| GPT-6 Astra | OpenRouter | – | – | 10.00 | 50.00 | 20.00 | 1.00 | 12.50 | 1,050,000 | api |
| Claude Fable 5.1 | OpenRouter | – | – | 10.00 | 50.00 | 20.00 | 0.250 | 12.50 | 1,000,000 | api |
| GPT-6 Astra 3 sources | Azure AI Foundry | – | – | 10.00 | 50.00 | 20.00 | 1.00 | 12.50 | 1,050,000 | api |
| GPT-6 Astra 4 sources | OpenAI | – | – | 10.00 | 50.00 | 20.00 | 1.00 | 12.50 | 1,050,000 | official |
| Claude Fable 5.1 3 sources | Azure AI Foundry | – | – | 10.00 | 50.00 | 20.00 | 0.250 | 12.50 | 1,000,000 | api |
| Claude Fable 5.1 4 sources | Anthropic | – | – | 10.00 | 50.00 | 20.00 | 0.250 | 12.50 | 1,000,000 | official |
| Claude Fable 5.1 3 sources | AWS Bedrock | – | – | 10.00 | 50.00 | 20.00 | 0.250 | 12.50 | 1,000,000 | api |
| Claude Fable 5.1 | Google Vertex AI | – | global | 10.00 | 50.00 | 20.00 | 0.250 | 12.50 | 1,000,000 | api |
| Claude Fable 5.1 2 sources | Google Vertex AI | – | – | 10.00 | 50.00 | 20.00 | 0.250 | 12.50 | 1,000,000 | aggregator |
| Claude Fable 5.1 | Perplexity | – | – | 10.00 | 50.00 | 20.00 | 0.250 | – | 1,000,000 | aggregator |
| GPT-6 Astra 2 sources | AWS Bedrock | – | global | 10.00 | 50.00 | 20.00 | 1.00 | 12.50 | 1,050,000 | api |
| Claude Fable 5.1 | AWS Bedrock | – | global | 10.00 | 50.00 | 20.00 | 0.250 | 12.50 | 1,000,000 | aggregator |
| GPT-6 Astra | Perplexity | – | – | 10.00 | 50.00 | 20.00 | 1.00 | 12.50 | 1,050,000 | aggregator |
| GPT-6 Astra | AWS Bedrock | – | us-west-2 | 11.00 | 55.00 | 22.00 | 1.10 | 13.75 | 1,050,000 | api |
| GPT-6 Astra 2 sources | Azure AI Foundry | – | us | 11.00 | 55.00 | 22.00 | 1.10 | 13.75 | 1,050,000 | 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