Claude model for long-running agentic coding and knowledge workClaude Opus 5.5 by anthropic is offered by 72 providers on this page. Public prices are shown for 70 of them. Its official list price is $4.00 per 1M input tokens and $20.00 per 1M output tokens. The lowest paid channel is APIKO at $0.90 / $4.50 per 1M, about 4.4× 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 59.1 on the Intelligence Index, with 65.3 for Engineering, its strongest domain. Against its lowest blended price of $1.80 per 1M, that is roughly 33 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 95 tokens per second, with 768.92s to the first token. Running one task of the Artificial Analysis suite costs about $10.0364, which reflects how many tokens its reasoning consumes rather than the unit price alone.
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 2026-06.
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-5-5 | Cloud | Free | $0 | $0 | 1,000,000 | 128,000 | ||
| APIKO | Gateway | $0.90 | $4.50 | $0.045 | — | 1,000,000 | 32,000 | |
| JZSTOKEN claude-opus-5.5 | Gateway | $1.17 | $5.84 | $0.12 | $1.46 | 1,000,000 | 128,000 | |
| Teapot Router | Gateway | $1.40 | $7.00 | — | — | 1,000,000 | 128,000 | |
| xxapi | Gateway | $1.54 | $7.69 | $0.077 | $1.92 | 1,000,000 | 128,000 | |
| AIGROW claude-opus-5.5 | Gateway | $1.60 | $8.00 | $0.20 | $3.20 | 1,000,000 | 128,000 | |
| Infer by Flow7 infer/claude-opus-5-5:low-cost | Gateway | $1.97 | $9.81 | $0.10 | $2.46 | 1,000,000 | 128,000 | |
| IteraCompute | Gateway | $2.00 | $10.00 | $0.10 | $2.50 | 1,000,000 | 128,000 | |
| Outer Labs | Gateway | $2.40 | $12.00 | $0.12 | $3.00 | 1,000,000 | 128,000 | |
| KoRouter | Gateway | $2.60 | $13.00 | $0.13 | $3.25 | 1,000,000 | 128,000 | |
| AnthropicOfficial | First-party | $4.00 | $20.00 | $0.20 | $5.00 | 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 3 of 72 providers.
2 / 72 providers expose no reasoning control (reasoning_options: []).
| Mode | Provider | Input | Output | Cache read | Cache write |
|---|---|---|---|---|---|
| fast | Anthropic | $8.00 | $40.00 | $0.40 | $10.00 |
1 more channels offer $0 (GitLab Duo); free tiers usually have rate limits and no SLA, excluded from ranking.
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| Terminal-Bench | variant: xhigh effort; production safeguards with fallback · v4.0 | 66.4 | score | Source ↗ |
| FrontierCode | variant: max effort; production safeguards with fallback · dataset: Main · v1.1 | 54.4 | score | Source ↗ |
| CursorBench | variant: max effort; production safeguards with fallback · v4.0 | 57.8 | score | Source ↗ |
| GDPval-AA | variant: max effort; production safeguards with fallback · v2.1 | 1846 | Elo | Source ↗ |
| AutomationBench | variant: max effort; production safeguards; no fallback | 40 | pass rate | Source ↗ |
| Humanity's Last Exam | variant: max effort; with tools; production safeguards with fallback | 67.7 | score | Source ↗ |
| Terminal-Bench-Science | variant: max effort; production safeguards with fallback · v0.1 | 58.7 | score | Source ↗ |
| OSWorld | variant: max effort; production safeguards with fallback · v2.0 | 81.8 | partial score | Source ↗ |
| Chartography | variant: max effort; with tools; production safeguards with fallback | 89 | score | 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 scale (percent correct, points or an index), so rows are not comparable with one another.