Fast Claude model for responsive assistance, classification, and lightweight agents
Claude Haiku 4.5 by anthropic is offered by 28 providers on this page. Public prices are shown for 27 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 QiHang at $0.14 / $0.71 per 1M, about 8.6× 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 16.9 on the Intelligence Index, with 43.9 for coding and 8 for agentic tasks. Against its lowest blended price of $0.282 per 1M, that is roughly 60 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 102 tokens per second, with 18.34s to the first token. Running one task of the Artificial Analysis suite costs about $0.2768, 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 20,000 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 |
|---|---|---|---|---|---|---|---|---|
| QiHang | Gateway | $0.14 | $0.71 | — | — | 200,000 | 64,000 | |
| Poe anthropic/claude-haiku-4.5 | Gateway | $0.85 | $4.30 | $0.085 | $1.10 | 192,000 ⚠ | 64,000 | |
| Jiekou.AI | Gateway | $0.90 | $4.50 | — | — | 20,000 ⚠ | — | |
| Perplexity Agent anthropic/claude-haiku-4-5 | Gateway | $1.00 | $5.00 | $0.10 | — | 200,000 | 64,000 | |
| NanoGPT anthropic/claude-haiku-4.5 | Gateway | $1.00 | $5.00 | $0.10 | — | 200,000 | 64,000 | |
| AnthropicOfficial | First-party | $1.00 | $5.00 | $0.10 | $1.25 | 200,000 | 64,000 | |
| Abacus | Gateway | $1.00 | $5.00 | — | — | 200,000 | 64,000 | |
| 302.AI claude-haiku-4-5 | Gateway | $1.00 | $5.00 | — | — | 200,000 | 64,000 | |
| Azure claude-haiku-4-5 | Cloud | $1.00 | $5.00 | $0.10 | $1.25 | 200,000 | 64,000 | |
| FreeModel | 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 1 of 28 providers.
4 / 28 providers expose no reasoning control (reasoning_options: []).
Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and harness, so rows are not comparable with one another. The Intelligence Index above draws on a different, newer set of evaluations.