Family · Claude · verified 2 September 2026

Claude models on OneInfer

OneInfer routes the full Claude family at the same rates as Anthropic direct. Claude Fable 5.1, released 1 September 2026, is the current flagship and leads every benchmark Anthropic published at launch.

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%).

ModelInput $/1MOutput $/1MContextFamily role
Claude Haiku 4.5$1.00$5.00200KLightweight, fastest
Claude Sonnet 5$2.00$10.001MValue tier
Claude Opus 5$5.00$25.001MCheaper Anthropic tier
Claude Fable 5$10.00$50.001MPredecessor flagship
Claude Fable 5.1$10.00$50.001MCurrent flagship
Claude Mythos 5$10.00$50.001MAccess-gated, vetted orgs
Claude Mythos 5.1$10.00$50.001MAccess-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 credits

Frequently 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.