Fast Claude lane for lightweight agents, office tasks, and responsive chatClaude Haiku 4.5 (latest) by anthropic is offered by 49 providers on this page. Public prices are shown for 46 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 Teapot Router at $0.35 / $1.75 per 1M, about 2.9× below the list price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.
Artificial Analysis rates it 7.4 on the Intelligence Index, with 19.4 for Finance & Accounting, its strongest domain. Against its lowest blended price of $0.70 per 1M, that is roughly 11 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 101 tokens per second, with 21.58s to the first token. Running one task of the Artificial Analysis suite costs about $0.5318, which reflects how many tokens its reasoning consumes rather than the unit price alone.
The context window is 200,000 tokens at the reference host, but hosts report different limits, from 192,000 to 200,000, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text, Image, and PDF. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2025-02-28.
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Teapot Router | Gateway | $0.35 | $1.75 | — | — | 200,000 | 64,000 | |
| xxapi | Gateway | $0.38 | $1.92 | $0.038 | $0.48 | 200,000 | 64,000 | |
| Outer Labs | Gateway | $0.60 | $3.00 | $0.06 | $0.75 | 200,000 | 64,000 | |
| KoRouter | Gateway | $0.65 | $3.25 | $0.065 | $0.81 | 200,000 | 64,000 | |
| Xpersona | Gateway | $0.60 | $3.70 | $0.06 | — | 200,000 | 128,000 | |
| Kunavo | Gateway | $0.70 | $3.50 | $0.07 | $0.88 | 200,000 | 64,000 | |
| Poe anthropic/claude-haiku-4.5 | Gateway | $0.86 | $4.29 | $0.086 | $1.07 | 192,000 ⚠ | 64,000 | |
| AnthropicOfficial | First-party | $1.00 | $5.00 | $0.10 | $1.25 | 200,000 | 64,000 | |
| Perplexity Agent | Gateway | $1.00 | $5.00 | $0.10 | $1.25 | 200,000 | 64,000 | |
| CrossModel | 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 6 of 49 providers.
6 / 49 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.