Anthropic
Claude Opus 4.8 Fast
Claude Opus 4.8 low-latency variant. Skips extended thinking for faster response at higher per-token cost.
claude-opus-4-8-fastPricing
~46%- Input
- $5.37664 / 1,000,000 tokens
- Output
- $26.8832 / 1,000,000 tokens
- Cache read
- $0.537664 / 1,000,000 tokens
- Cache write
- $6.7208 / 1,000,000 tokens
Discount history
Model details
- Input
- text
- Output
- text
- Context window
- 1,000,000 tokens
- Maximum output
- 128,000 tokens
- Availability
- $8Uncapped capacity
- Updated
- 11/8/2026, 3:58:06 AM UTC
Capacity is reserved when your request is accepted.
Capabilities
ChatStreamingTool callingVisionJSON mode
Supported parameters
frequency_penaltymax_completion_tokensmax_tokensparallel_tool_callspresence_penaltyresponse_formatseedstopstreamstream_optionstemperaturetool_choicetoolstop_puserverbosity