- Input $/1M
- $5.00
- Output $/1M
- $25.00
- Context
- 1M
- Max output
- 128K
- Reasoning
- Yes
- Included in
- 6 plans
API model id
claude-opus-4-6Input
$5.00
Output
$25.00
Cache read
$0.50
- Cache writes · 1 hour
- $10.00 / 1M tokens
- Cache writes · 5 minutes
- $6.25 / 1M tokens
- Reasoning tokens
- Billed at the output token rate
Published rate checked 2026-09-29. Sources below.
Current published base rates. Context tiers, cache-write duration and other conditions may change the rate for a request. These are not a reconstructed historical invoice.
- Context window
- 1,000,000
- Maximum output
- 128,000
- Input
- text · image
- Output
- text
- Knowledge cutoff
- May 2025
- Reasoning
- Supported
- Thinking
- Adaptive (extended deprecated) · default effort high
- API availability
- Active (legacy)
- Released
- February 5, 2026
- Retirement commitment
- Not sooner than February 5, 2027
- Extended output
- Maximum output is 300K tokens on the Batch API (beta). The standard maximum output limit remains 128K tokens.
- Prompt caching
- Five-minute cache writes cost $6.25 per MTok, one-hour cache writes cost $10 per MTok and cache reads cost $0.50 per MTok.
- Platforms
- Claude API, Amazon Bedrock (InvokeModel), Google Cloud, Microsoft Foundry and Claude Platform on AWS.
Pricing, assumptions & evidence
cache-write-1h
Input $5.00 · Output $25.00 · Cache read $0.50 · Cache write $10.00
cache-write-5m
Input $5.00 · Output $25.00 · Cache read $0.50 · Cache write $6.25
Published base rate
Input $5.00 · Output $25.00 · Cache read $0.50 · Cache write See duration-specific rates below
Missing token-category prices are not zero. Workload pricing applies exact recorded categories and admitted routes. No benchmark score or quality ranking is inferred from prices.
Aliases, routes and identity
Catalog ID claude-opus-4-6
Model release (kind: release)
Developer: Anthropic
anthropic/claude-opus-4.6harness_alias