Balanced Claude model for coding, analysis, agent workflows, and cost control
Claude Sonnet 4.5 by anthropic is offered by 26 providers on this page. Public prices are shown for 25 of them. Its official list price is $3.00 per 1M input tokens and $15.00 per 1M output tokens. The lowest paid channel is QiHang at $0.43 / $2.14 per 1M, about 8.7× 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 1,000,000 tokens at the reference host, but hosts report different limits, from 198,000 to 1,000,000, 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 2025-07-31.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| QiHang | Gateway | $0.43 | $2.14 | — | — | 200,000 ⚠ | 64,000 | |
| Poe anthropic/claude-sonnet-4.5 | Gateway | $2.60 | $13.00 | $0.26 | $3.20 | 983,040 ⚠ | 32,768 | |
| Jiekou.AI | Gateway | $2.70 | $13.50 | — | — | 200,000 ⚠ | 64,000 | |
| Perplexity Agent anthropic/claude-sonnet-4-5 | Gateway | $3.00 | $15.00 | $0.30 | — | 200,000 ⚠ | 64,000 | |
| NanoGPT anthropic/claude-sonnet-4.5 | Gateway | $3.00 | $15.00 | $0.30 | — | 200,000 ⚠ | 64,000 | |
| AnthropicOfficial | First-party | $3.00 | $15.00 | $0.30 | $3.75 | 1,000,000 | 64,000 | |
| Databricks databricks-claude-sonnet-4 | Cloud | $3.00 | $15.00 | $0.30 | $3.75 | 200,000 ⚠ | 64,000 | |
| Abacus | Gateway | $3.00 | $15.00 | — | — | 200,000 ⚠ | 64,000 | |
| Azure claude-sonnet-4-5 | Cloud | $3.00 | $15.00 | $0.30 | $3.75 | 200,000 ⚠ | 64,000 | |
| Azure Cognitive Services claude-sonnet-4-5 | Cloud | $3.00 | $15.00 | $0.30 | $3.75 | 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 26 providers.
4 / 26 providers expose no reasoning control (reasoning_options: []).