ModelRefs / Claude Haiku 4.5 by Anthropic — Benchmarks, Pricing & Revie…

Claude Haiku 4.5 by Anthropic — Benchmarks, Pricing & Revie…

Claude Haiku 4.5 (Anthropic): Claude Haiku 4.5 by Anthropic.. 200K context. Pricing: from $0.00100/1K in. Specs, benchmarks and code examples.

What this reference supports

Claude Haiku 4.5 is the small, fast tier of Anthropic's Claude 4 generation, positioned to deliver a large share of Sonnet-tier capability at materially lower cost and latency. Implementation decisions center on volume routing: which workload segments can move to Haiku without breaching measured quality floors.

Claude Haiku 4.5 is attributed to Anthropic in ModelRefs' canonical registry. Tracked modalities: Text input and output, Image input. Primary use cases considered on ModelRefs: High-volume assistants, extraction, and summarization with tight latency budgets; Sub-agent and tool-execution roles inside larger agentic systems.

This ModelRefs profile is Provisional and pending review — decision-support material, not a final or universal ranking. Confirm current behavior, access, pricing, limits, licensing, and lifecycle in Anthropic's own documentation, and evaluate Claude Haiku 4.5 on representative workloads before implementation.

Benchmark & Evaluation

ModelRefs does not yet hold qualifying sourced benchmark evidence for Claude Haiku 4.5, so its benchmark coverage is incomplete. Treat any benchmark discussion as provisional and confirm results on representative workloads before selecting it.

  • No benchmark score is imported into this editorial record. Provider-reported evaluations support scoped notes only; canonical score records are governed separately with their own provenance.
  • Anthropic's release notes report provider-run coding and agentic evaluations for Haiku 4.5; canonical score records remain separately governed.

Implementation considerations

  • Evaluate Haiku directly against Sonnet-tier models on your own tasks; provider-reported near-parity claims are workload-dependent.
  • Verify extended-thinking and feature availability for the exact API tier; small-tier feature matrices differ by platform.
  • Hosted through the Anthropic API and eligible cloud partners (per Anthropic's current documentation).
  • Feature flags, rate limits, and data-retention controls differ by platform and account; check the models overview for the current matrix.

Risks and limitations

  • Hosted-model behavior, quotas, pricing, and data controls can change without a client-side version pin unless a dated snapshot is used.
  • Provider-reported capabilities require task-specific evaluation before production reliance.

Source coverage

This reference is Provisional. Model behavior, access, pricing, limits, and lifecycle can change; verify the linked provider documentation and run task-specific evaluations before implementation.

Known coverage gaps:

  • Independent reproduction of provider-reported evaluations is not attached.
  • Cost-quality routing evidence versus Sonnet 4.5 is incomplete.

Sources

Continue your research

Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Claude Haiku 4.5 by Anthropic — Benchmarks, Pricing & Revie….