All Claude models on OneInfer
Routing is data-driven from the OneInfer catalog. Prices match Anthropic direct except where regional multipliers apply (Google Vertex +10%).
| Model | Input $/1M | Output $/1M | Context | Family role |
|---|---|---|---|---|
| Claude Haiku 4.5 | $1.00 | $5.00 | 200K | Lightweight, fastest |
| Claude Sonnet 5 | $2.00 | $10.00 | 1M | Value tier |
| Claude Opus 5 | $5.00 | $25.00 | 1M | Cheaper Anthropic tier |
| Claude Fable 5 | $10.00 | $50.00 | 1M | Predecessor flagship |
| Claude Fable 5.1 | $10.00 | $50.00 | 1M | Current flagship |
| Claude Mythos 5 | $10.00 | $50.00 | 1M | Access-gated, vetted orgs |
| Claude Mythos 5.1 | $10.00 | $50.00 | 1M | Access-gated, vetted orgs |
How to choose
Which Claude model you should use depends on cache hit rate and effort level more than on the model name. The family runs from $1 to $10 per 1M input tokens. Start with Sonnet 5 or Opus 5 unless the workload is genuinely agentic, in which case Fable 5.1 wins on published agent benchmarks.
Ready to test the workflow?
Create account & add creditsFrequently asked questions
Which Claude model should you use?
Which Claude model you should use depends on cache hit rate and effort level more than on the model name: the family runs from $1 to $10 per 1M input tokens. Start with Sonnet 5 or Opus 5 unless the workload is genuinely agentic, in which case Fable 5.1 wins on published agent benchmarks.
Put Claude Fable 5.1 to work
Fund a controlled evaluation, start with a prepared prompt, and measure quality and cost on your own workload.