Anthropic: Claude Opus 5 (Fast)
Flagship Claude model for deep reasoning, coding, and long-horizon agents
Sources
Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| models.devcheapestanthropic/claude-opus-5-fast | Vercel AI Gateway | $10 | $50 | $1 | 1M |
| models.devclaude-opus-5-fast | Pioneer | $10 | $50 | $1 | 1M |
| models.devclaude-opus-5-fast | Venice AI | $10 | $50 | $1 | 1M |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Attachments
- In: text
- In: image
- In: pdf
- Out: text
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Hover or tap the i next to any score for its source. Full boards on /benchmarks.
- Terminal-Bench Science 0.130i
- AA intelligence50.8i
- AA coding78i
- AA agentic56.5i
- DeepSWE v1.173.7i
- Agents' Last Exam55.5i
- AutomationBench (Public)26.9i
- ARC-AGI-330.2i
- FrontierMath Tier 4 (v2)73.2i
- BenchCAD82.1i
- GPQA Diamond93.7i
- HealthBench Professional54.5i
- ExploitBench70i
- ARC-AGI-290.4i
Arena rows are community-vote Elo from Arena AI, Artificial Analysis indices arrive via OpenRouter, and launch-eval figures are collected from vendor announcements, analyst writeups, and community benchmarks. Full boards and credits on /benchmarks.
See what this model costs you
The app reads the sessions your tools already wrote and prices this model's tokens at the published API rate. Free on your computer.