API hub · Updated 2026-08-06
Cloud coding agent APIs.
HTTP when you need it.
Most teams start with Critique CLI — the local finish pass. This hub is for the separate Coding Agent API surface: remote runs, crt_ keys, and when Devin’s session-first product fits better.
Quick answer
Critique’s Coding Agent API is HTTP-first (POST /api/v1/coding-agent/runs, crt_ keys, OpenCode in E2B, warm sessions, draft PRs) with pay-as-you-go credits or OpenRouter BYOK — including $0 token routes on OpenRouter :free models. Devin is session-first with quota on self-serve plans and enterprise ACU contracts; its API is positioned for larger accounts rather than copy-paste automation for every developer.
CLI first, API when automation needs HTTP
Use critique finish on the working tree for the independent check your coding agent calls. Reach for the Coding Agent API when CI, internal bots, or platform teams need remote OpenCode runs, draft PRs, and webhooks — not as a substitute for the local finish pass.
A cloud coding agent API provisions isolated compute, runs an agent loop, and returns patches and logs. That is different from an IDE plugin that only works while a human has the editor open.
Model freedom & cheap routes
Critique does not lock you to one model vendor for Coding Agent API runs. On managed billing you route through Critique’s OpenRouter-backed catalog — 42 frontier and mid-tier LLMs interchangeable as lead reviewer or specialist sub-agent — with transparent credit floors (including zero-credit provider-sponsored routes and the 0.5-credit DeepSeek V4 Flash 0731 lane). On OpenRouter billing you pass `billing.mode: "openrouter"` plus your `sk-or-v1-…` key (per run or saved in Settings). Critique runs the sandbox; OpenRouter bills tokens on your account. That unlocks the full OpenRouter catalog, including :free model routes such as `nvidia/nemotron-3-super-120b-a12b:free` — literally $0 model cost for the inference itself, within OpenRouter’s free-tier limits. You still pay Critique for orchestration, E2B isolation, and GitHub integration on bundled plans, or the $8/mo BYOK harness when you standardize on bring-your-own-key across Chat and Builder. The shape is pay-as-you-go: no per-developer seat for the API, no opaque “session ACU” contract for self-serve — pick Solo ($19/mo), burn credits when you run agents, or attach OpenRouter and only pay for what each run consumes.
| Model route | Token cost | Notes |
|---|---|---|
nvidia/nemotron-3-super-120b-a12b:freeNemotron 3 Super 120B (:free on OpenRouter) | $0 on OpenRouter | $0 model tokens on OpenRouter when you BYOK; subject to OpenRouter free-tier rate limits. |
deepseek/deepseek-v4-flash-0731DeepSeek V4 Flash 0731 | 0.5 Critique credits (managed) | 0.5 Critique credit floor on managed billing — among the cheapest managed agent runs. |
qwen/qwen3.8-flashQwen3.8 Flash | 0.5 Critique credits (managed) | Provider-sponsored route with a zero model-credit floor while available. |
deepseek/deepseek-v4-pro-0813DeepSeek V4 Pro 0813 | 0.5 Critique credits (managed) | 1 credit floor on managed catalog. |
Pay-as-you-go vs Devin quota
Solo is $19/month (750 credits), Pro is $49/month (3,000 credits with a 7-day trial), and Team is $149/month (10,000 credits). BYOK is $8/month ($8 USD, €8/mo EUR) for the Critique harness while OpenRouter or CrofAI bills model tokens directly. Verified students and OSS maintainers pay $5/month. Coding Agent runs share that pool — no per-seat API tax. OpenRouter mode ($8/mo BYOK harness (OpenRouter or CrofAI)) passes model tokens to your OpenRouter invoice; Critique bills orchestration and sandbox time.
Critique
- ◆CLI finish pass as the default product
- ◆Optional REST API with crt_ keys
- ◆Managed credits or OpenRouter BYOK
- ◆Draft PR + review on agent-opened PRs
Devin (public, early 2026)
- ·Session-first Devin Cloud UI
- ·Quota on self-serve; dollar overage after
- ·Enterprise API + ACU contracts
- ·Strong for product-led task delegation
Market map
| Product | Best for | HTTP API | Draft PR | Pricing |
|---|---|---|---|---|
| Critique Cloud Coding Agent API | Teams on GitHub who want HTTP automation with draft PRs and Critique change control | Yes — POST /api/v1/coding-agent/runs with crt_ keys | Yes — publish.mode draft_pr | Solo $19/mo, Pro $49/mo, Team $149/mo shared credits; $8/mo BYOK harness (OpenRouter or CrofAI) for model tokens |
| Cursor cloud agents | Cursor IDE users queuing fixes from the editor | Primarily via Cursor product surfaces; Critique can queue Composer via BYOA | Yes — through Cursor/GitHub flows | Cursor subscription + usage; not a standalone crt_-style HTTP catalog |
| OpenAI Codex / Claude Code | Terminal-first coding agents tied to vendor accounts | Vendor SDKs and CLIs; not a unified sandbox+draft-PR HTTP contract | Varies by integration | Direct OpenAI or Anthropic billing |
| Devin / enterprise agent platforms | Session-first delegation; enterprise ACU API | Enterprise API; self-serve is UI + quota (see /compare/devin) | Typically yes | Free / Pro $20 / Max $200 / Teams $80 min + overage |
| Roll your own (E2B + agent loop) | Platform teams with time to operate sandboxes and git publish | You build it | You build it | E2B + model spend + engineering time |
Critique vs Devin
Devin (by Cognition) is a cloud coding agent for long-horizon tasks: plan, edit, run tools, and ship from a product UI. Public plans bundle daily/weekly quota; the HTTP API is primarily an enterprise-style surface.
Choose Critique when
- ◆You already have Codex/Claude Code/Cursor writing code and need an independent finish pass.
- ◆You want structured evidence on the local diff, not another cloud “AI employee” session.
- ◆Shared credits beat opaque session quota for finish-check volume.
- ◆Optional Coding Agent API when you do need HTTP — without making the UI the only path.
Choose Devin when
- ·You want a polished session-first autonomous agent UI with minimal local tooling.
- ·Your org is standardizing on Devin enterprise contracts as the implementation agent.
- ·You need Devin-specific product features (DeepWiki, Ask Devin) in one vendor bundle.
FAQs
01What is the cheapest cloud coding agent API?
For $0 model tokens, use Critique with OpenRouter BYOK and a :free model id (for example nvidia/nemotron-3-super-120b-a12b:free), subject to OpenRouter free-tier limits. For lowest managed runs without BYOK setup, route to 0.5-credit-floor models like DeepSeek V4 Flash or MiMo v2.5 on Critique Solo ($19/mo). Devin Free exists but with different quota and UI-first ergonomics.
02How is Critique different from the Devin API?
Critique documents self-serve REST endpoints, crt_ scopes, SSE activity, and optional draft PR publish on your GitHub App install. Devin’s public pricing lists API access in an enterprise-oriented row; self-serve Devin is quota-based sessions with dollar overage at underlying model rates.
03Can I use OpenRouter free models with a coding agent API?
Yes on Critique when billing.mode is openrouter and you pass your sk-or-v1 key. Model inference on :free routes is $0 on OpenRouter; Critique still charges for harness, E2B, and GitHub integration per your plan unless you are on BYOK-only economics for the whole account.
04Is Critique pay-as-you-go?
Yes. Shared credits burn per run on managed billing; unused credits do not require per-developer seats. OpenRouter BYOK shifts model spend to your OpenRouter account while Critique charges a flat harness fee or bundled credits for sandbox orchestration.
05Does Critique lock me to one model?
No. Every run accepts a modelId. Managed mode uses Critique’s OpenRouter-backed catalog with published credit floors. BYOK mode uses any OpenRouter model string, including free and experimental routes.
Default path
Start with the CLI.
Add the API later.
Most buyers comparing “coding agent APIs” still need an independent finish check on local changes. Install Critique CLI first; open the API docs when HTTP automation is the actual job.
Sources: devin.ai/pricing, Devin billing docs, OpenRouter limits. Verify pricing before procurement.