Fast Claude lane for lightweight agents, office tasks, and responsive chat
Claude Haiku 4.5 (latest) by anthropic is offered by 26 providers on this page. Public prices are shown for 23 of them. Its official list price is $1.00 per 1M input tokens and $5.00 per 1M output tokens. The lowest paid channel is Xpersona at $0.60 / $3.70 per 1M, about 1.8× below the list price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.
The context window is 200,000 tokens, with an output limit of 64,000 tokens. It supports reasoning, tool use, and structured output. Accepted input modalities are Text, Image, and PDF. Its training knowledge cuts off at 2025-02-28.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Xpersona | Gateway | $0.60 | $3.70 | $0.06 | — | 200,000 | 128,000 | |
| Cortecs | Gateway | $1.00 | $4.98 | $0.099 | $1.19 | 200,000 | 64,000 | |
| AnthropicOfficial | First-party | $1.00 | $5.00 | $0.10 | $1.25 | 200,000 | 64,000 | |
| NEAR AI Cloud | Gateway | $1.00 | $5.00 | $0.10 | $1.25 | 200,000 | 64,000 | |
| Databricks databricks-claude-haiku-4-5 | Cloud | $1.00 | $5.00 | $0.10 | $1.25 | 200,000 | 64,000 | |
| Kilo Gateway anthropic/claude-haiku-4.5 | Gateway | $1.00 | $5.00 | $0.10 | $1.25 | 200,000 | 64,000 | |
| OpenRouter anthropic/claude-haiku-4.5 | Gateway | $1.00 | $5.00 | $0.10 | $1.25 | 200,000 | 64,000 | |
| Impossibl | Gateway | $1.00 | $5.00 | $0.10 | $1.25 | 200,000 | 64,000 | |
| Cloudflare AI Gateway anthropic/claude-haiku-4.5 | Cloud | $1.00 | $5.00 | $0.10 | $1.25 | 200,000 | 64,000 | |
| OrcaRouter anthropic/claude-haiku-4.5 | Gateway | $1.00 | $5.00 | $0.10 | $1.25 | 200,000 | 64,000 | |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Interleaved thinking (reasoning between tool calls) is declared by 4 of 26 providers.
2 / 26 providers expose no reasoning control (reasoning_options: []).
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| SWE-Bench Pro | dataset: public | 39.45 | resolve rate | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.