All tasks / Tools
Capy
Platform for running and orchestrating cloud coding agents from a web or desktop app, Slack, Linear or an API.
- Capy Corporation
- Cloud
- From $20/mo
Where it ranks
- SCodingCoding agents · Cloud · via Claude Opus 5.5
Ranked by its own benchmark result where it has one; otherwise by the best model it offers.
Facts
- Vendor
- Capy Corporation
- Approach
- Coding agents
- Where it runs
- Cloud only: needs the vendor’s service
- Interface
- Web app, Desktop app, API
- Skill level
- Beginner: works out of the box
- Price
- From $20/mo
- Pricing notes
- Lite $20/mo ($16 annual) with $20 credits; Pro $100/mo; Max $200+; Enterprise custom; $1 7-day intro on Lite; can connect Codex, Copilot or SuperGrok subscriptions.
- Source code
- Closed source
- Last verified
- 19 Oct 2026
Price from capy.ai, 19 Oct 2026.
Models it gives you
- SClaude Opus 5.5Anthropic · closed
- SGPT-6 AstraOpenAI · closed
- AGPT-6.1 SolOpenAI · closed
- AClaude Fable 5.1Anthropic · closed
- BQwen3.8-MaxAlibaba (Qwen) · closed
- BKimi K3Moonshot AI · open weights
- BGrok 4.7xAI · closed
- CGLM-5.3Z.ai · open weights
- CGemini 3.8 FlashGoogle · closed
Its own benchmark results
| Benchmark | Result | Entry on the leaderboard | As of | Source |
|---|---|---|---|---|
| Terminal-Bench 2.0 | 83.2% | Capy + GPT-5.5rank 3 of 142 entries; raw accuracy 83.15 ± 2.11 (95% CI half-width); entry date 2026-04-23; not verified; agent org: Capy; read via the site's leaderboard-read API (page is client-rendered) | 19 Oct 2026 | tbench.ai |