15% off all models 🎉 Every model at 85% of OpenRouter list price.Browse models →
Maker: Anthropic
Claude Opus 4.8
Anthropic's most capable generally available Opus model for demanding professional and agentic work.
- Interface model ID
- claude-opus-4.8
- Context
- 1M context
- Max output
- Not published
- API provider
- 3 API providers
- Fast mode
- 0 fast routes
ApiFlux uptimeStatus unknown
Model transit availability
ApiFlux pricing by access route
USD per 1M tokens
- Input
- $4.2500
- Output
- $21.2500
Anthropic
Not published
Cache pricing includes read, standard write, and one-hour write rates.
Input $4.2500Output $21.2500Cache read $0.4250Cache write $5.31251-hour cache write $8.50001M Context · Not published max outputProvider statusOfficial statusAmazon Bedrock
Not published
Cache pricing includes read, standard write, and one-hour write rates.
Input $4.2500Output $21.2500Cache read $0.4250Cache write $5.31251-hour cache write $8.50001M Context · Not published max outputProvider statusOfficial statusVertex AI
Not published
Cache pricing includes read, standard write, and one-hour write rates.
Input $4.2500Output $21.2500Cache read $0.4250Cache write $5.31251-hour cache write $8.50001M Context · Not published max outputProvider statusOfficial status
Pricing last updated: July 25, 2026
Long-context pricing applies only after the threshold shown. Cache and token prices are listed per 1M tokens.
Suitable for
- Text and chat requests that fit the published context window.
- Workloads that benefit from a unified OpenAI-compatible ApiFlux endpoint.
Unsuitable for
- Native image, audio, or video generation priced with non-token units.
- Workloads that require an unpublished cache or output-limit guarantee.