Flagship Claude model for deep reasoning, coding, and long-horizon agentsClaude Opus 4.1 by anthropic is offered by 11 providers on this page. No official API price is listed for it; the prices below come from third-party channels. The lowest paid channel is Jiekou.AI at $13.50 / $67.50 per 1M. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.
The context window is 200,000 tokens, with an output limit of 32,000 tokens. It supports reasoning, tool use, and structured output. Accepted input modalities are Text, Image, and PDF. Its training knowledge cuts off at 2025-03-31.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Jiekou.AI | Gateway | $13.50 | $67.50 | — | — | 200,000 | 32,000 | deprecated |
| 302.AI | Gateway | $15.00 | $75.00 | $1.50 | $18.75 | 200,000 | 32,000 | |
| 302.AI claude-opus-4-1-20250805-thinking | Gateway | $15.00 | $75.00 | — | — | 200,000 | 32,000 | |
| Vertex (Anthropic) claude-opus-4-1@20250805 | Cloud | $15.00 | $75.00 | $1.50 | $18.75 | 200,000 | 32,000 | deprecated |
| Amazon Bedrock anthropic.claude-opus-4-1-20250805-v1:0 | Cloud | $15.00 | $75.00 | $1.50 | $18.75 | 200,000 | 32,000 | deprecated |
| Amazon Bedrock us.anthropic.claude-opus-4-1-20250805-v1:0 | Cloud | $15.00 | $75.00 | $1.50 | $18.75 | 200,000 | 32,000 | deprecated |
| Vertex claude-opus-4-1@20250805 | Cloud | $15.00 | $75.00 | $1.50 | $18.75 | 200,000 | 32,000 | deprecated |
| Merge Gateway | Gateway | $15.00 | $75.00 | $1.50 | $18.75 | 200,000 | 32,000 | |
| FastRouter anthropic/claude-opus-4.1 | Gateway | $15.00 | $75.00 | $1.50 | $18.75 | 200,000 | 32,000 | |
| Helicone | Gateway | $15.00 | $75.00 | $1.50 | $18.75 | 200,000 | 32,000 | |
| Abacus | Gateway | $15.00 | $75.00 | — | — | 200,000 | 32,000 | deprecated |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
2 / 11 providers expose no reasoning control (reasoning_options: []).