Everyday Claude agent model for coding, planning, browsing, and general workClaude Sonnet 5 by anthropic is offered by 67 providers on this page. Public prices are shown for 65 of them. Its official list price is $2.00 per 1M input tokens and $10.00 per 1M output tokens. The lowest paid channel is Teapot Router at $0.70 / $3.50 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. It also has 1 free ($0) channel; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.
Median output speed is 65 tokens per second, with 1.39s to the first token.
The context window is 1,000,000 tokens, with an output limit of 128,000 tokens. 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 2026-01-31.
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 |
|---|---|---|---|---|---|---|---|---|
| GitLab Duo duo-chat-sonnet-5 | Cloud | Free | $0 | $0 | 1,000,000 | 64,000 | ||
| Teapot Router | Gateway | $0.70 | $3.50 | — | — | 1,000,000 | 128,000 | |
| xxapi | Gateway | $0.77 | $3.85 | $0.077 | $0.96 | 1,000,000 | 128,000 | |
| JZSTOKEN | Gateway | $0.78 | $3.89 | $0.078 | $0.97 | 1,000,000 | 128,000 | |
| Outer Labs | Gateway | $1.20 | $6.00 | $0.12 | $1.50 | 1,000,000 | 128,000 | |
| KoRouter | Gateway | $1.30 | $6.50 | $0.13 | $1.63 | 1,000,000 | 128,000 | |
| Kunavo | Gateway | $1.40 | $7.00 | $0.14 | $1.75 | 1,000,000 | 128,000 | |
| Kenari | Gateway | $1.43 | $7.14 | $0.57 | $1.71 | 1,000,000 | 128,000 | |
| UnoRouter | Gateway | $1.44 | $7.20 | — | — | 1,000,000 | 128,000 | |
| AnthropicOfficial | First-party | $2.00 | $10.00 | $0.20 | $2.50 | 1,000,000 | 128,000 |
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 67 providers.
6 / 67 providers expose no reasoning control (reasoning_options: []).
1 more channels offer $0 (GitLab Duo); free tiers usually have rate limits and no SLA, excluded from ranking.
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| SWE-Bench Verified | — | 85.2 | resolved | Source ↗ |
| SWE-Bench Pro | — | 63.2 | resolve rate | Source ↗ |
| SWE-Bench Multilingual | — | 78.3 | resolve rate | Source ↗ |
| Terminal-Bench | harness: Terminus-2 · v2.1 | 80.4 | success rate | Source ↗ |
| OSWorld-Verified | — | 81.2 | success rate | Source ↗ |
| BrowseComp | variant: single agent | 84.7 | accuracy | Source ↗ |
| FrontierCode | vv1 | 38.8 | pass rate | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.