Balanced Claude model for coding, analysis, agent workflows, and cost control
Claude Sonnet 3.7 by anthropic is offered by 7 providers on this page. Public prices are shown for 6 of them. Its reference price is $3.00 per 1M input tokens and $15.00 per 1M output tokens. The lowest paid channel is Poe at $2.60 / $13.00 per 1M, about 1.2× below the reference price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.
Artificial Analysis rates it 17.7 on the Intelligence Index, with 36.4 for coding. Against its lowest blended price of $5.20 per 1M, that is roughly 3 index points per dollar, which is the value ratio the leaderboards rank on.
The context window is 1,000,000 tokens at the reference host, but hosts report different limits, from 196,608 to 1,000,000, so the usable window depends on the provider you pick. It supports reasoning and tool use. Accepted input modalities are Text, Image, and PDF. Its training knowledge cuts off at 2024-10-31.
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 |
|---|---|---|---|---|---|---|---|---|
| Poe anthropic/claude-sonnet-3.7 | Gateway | $2.60 | $13.00 | $0.26 | $3.20 | 196,608 ⚠ | 128,000 | |
| ZenMux anthropic/claude-3.7-sonnet | Gateway | $3.00 | $15.00 | $0.30 | $3.75 | 200,000 ⚠ | 64,000 | deprecated |
| Merge Gateway | Gateway | $3.00 | $15.00 | $0.30 | $3.75 | 200,000 ⚠ | 64,000 | |
| DigitalOcean anthropic-claude-3.7-sonnet | Cloud | $3.00 | $15.00 | $0.30 | $3.75 | 200,000 ⚠ | 64,000 | deprecated |
| Abacus | Gateway | $3.00 | $15.00 | — | — | 200,000 ⚠ | 64,000 | |
| Pioneer claude-3-7-sonnet-latest | Gateway | $3.00 | $15.00 | $0.30 | $3.75 | 1,000,000 | 128,000 | |
| Qiniu claude-3.7-sonnet | Gateway | — | — | — | — | 200,000 ⚠ | 128,000 | hostTable.undisclosed |
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 7 providers.
3 / 7 providers expose no reasoning control (reasoning_options: []).
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| Aider Polyglot | — | 64.9 | percent correct | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.
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.