Strongest Claude Opus model for coding, agents, and professional workClaude Opus 5 by anthropic is offered by 67 providers on this page. Public prices are shown for 65 of them. Its official list price is $5.00 per 1M input tokens and $25.00 per 1M output tokens. The lowest paid channel is JZSTOKEN at $1.17 / $5.84 per 1M, about 4.3× 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.
Artificial Analysis rates it 44.2 on the Intelligence Index, with 53.7 for Strategy & Ops, its strongest domain. Against its lowest blended price of $2.34 per 1M, that is roughly 19 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 51 tokens per second, with 69.09s to the first token. Running one task of the Artificial Analysis suite costs about $11.8215, which reflects how many tokens its reasoning consumes rather than the unit price alone.
The context window is 1,000,000 tokens at the reference host, but hosts report different limits, from 262,144 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 2026-05.
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-opus-5 | Cloud | Free | $0 | $0 | 1,000,000 | 128,000 | ||
| JZSTOKEN | Gateway | $1.17 | $5.84 | $0.12 | $1.46 | 1,000,000 | 128,000 | |
| Teapot Router | Gateway | $1.75 | $8.75 | — | — | 1,000,000 | 128,000 | |
| xxapi | Gateway | $1.92 | $9.62 | $0.19 | $2.40 | 1,000,000 | 128,000 | |
| Outer Labs | Gateway | $3.00 | $15.00 | $0.30 | $3.75 | 1,000,000 | 128,000 | |
| KoRouter | Gateway | $3.25 | $16.25 | $0.33 | $4.06 | 1,000,000 | 128,000 | |
| Kunavo | Gateway | $3.50 | $17.50 | $0.35 | $4.38 | 1,000,000 | 128,000 | |
| AnthropicOfficial | First-party | $5.00 | $25.00 | $0.50 | $6.25 | 1,000,000 | 128,000 | |
| Perplexity Agent | Gateway | $5.00 | $25.00 | $0.50 | $6.25 | 1,000,000 | 128,000 | |
| CrossModel | Gateway | $5.00 | $25.00 | $0.50 | $6.25 | 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: []).
| Mode | Provider | Input | Output | Cache read | Cache write |
|---|---|---|---|---|---|
| fast | Anthropic | $10.00 | $50.00 | $1.00 | $12.50 |
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 | — | 96 | resolved | Source ↗ |
| SWE-Bench Pro | — | 79.2 | resolve rate | Source ↗ |
| SWE-Bench Multilingual | — | 89.5 | resolve rate | Source ↗ |
| SWE-Bench Multimodal | — | 59.4 | resolve rate | Source ↗ |
| DeepSWE | v1.1 | 68.8 | resolve rate | Source ↗ |
| FrontierCode | variant: medium effort · dataset: Main · v1.1 | 53.4 | mean@5 | Source ↗ |
| Frontier-Bench | harness: mini-SWE-agent · variant: max effort · vv0.1 | 43.3 | mean reward | Source ↗ |
| BrowseComp | variant: single agent | 90.8 | accuracy | Source ↗ |
| Humanity's Last Exam | variant: no tools | 56.3 | accuracy | Source ↗ |
| Humanity's Last Exam | variant: with tools | 64.7 | accuracy | Source ↗ |
| DeepSearchQA | variant: max effort | 95 | F1 | Source ↗ |
| OSWorld | v2.0 | 70.6 | success rate | Source ↗ |
| GDPval-AA | variant: max effort · vv2 | 1861 | Elo | Source ↗ |
| AA-Briefcase | variant: max effort | 1720 | Elo | Source ↗ |
| AutomationBench | variant: max effort | 26 | success rate | Source ↗ |
| ARC-AGI-1 | variant: max effort | 97.5 | accuracy | Source ↗ |
| ARC-AGI-2 | variant: max effort | 90.4 | accuracy | Source ↗ |
| ARC-AGI-3 | variant: high effort | 30.2 | RHAE | Source ↗ |
| HealthBench Professional | variant: max effort | 59.8 | score | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.