Codex cloudvsDevin
Generated from the two spec rows. Green marks the better value where a spec has a clear direction. Everything else is just different.
Codex cloud
OpenAI · Autonomous SWE
#55
Panel
6.50 spec wins
- Reliability
- 6.2
- Usefulness
- 7.0
- Cost
- 5.8
- Longevity
- 7.0
“Ships models named Sol, Terra and Luna, so your pull request is now reviewed by a planetarium.”
Devin
Cognition · Autonomous SWE
#139MCP
Panel
5.34 spec wins
- Reliability
- 5.3
- Usefulness
- 5.8
- Cost
- 4.3
- Longevity
- 5.5
“Replaced ACUs with credits in April 2026, so now the meter runs in a unit you already understand.”
Spec by spec
| Spec | Codex cloud | Devin |
|---|---|---|
| Architecture | ||
| Category | Autonomous SWE | Autonomous SWE |
| Runs | cloud, sandbox | cloud, sandbox, local |
| Platforms | web | web, macos, linux, windows |
| Context window | not documented | not documented |
| Protocols | ||
| MCP client | No | Yes |
| MCP server | No | Yes |
| Capabilities | ||
| Runs terminal commands | Yes | Yes |
| Multi-file edits | Yes | Yes |
| Git operations | Yes | Yes |
| Browser control | NoThe Browser capability and cloud browser belong to ChatGPT/ChatGPT Work, not to Codex cloud chats, whose containers only get configurable HTTP internet access (https://learn.chatgpt.com/docs/cloud/internet-access). | YesCloud sessions ship a first-party interactive Browser tool alongside the shell and IDE, with saved browser profiles for authenticated sites (https://docs.devin.ai/work-with-devin/browser-auth). |
| Sandboxed execution | YesEach chat gets its own container from the `universal` image, cached for up to 12 hours (https://learn.chatgpt.com/docs/environments/cloud-environment). | YesCloud sessions run on a dedicated Devin machine built from environment blueprints and snapshots, and the Devin CLI adds OS-level isolation locally (https://docs.devin.ai/cli/sandbox). |
| Multi-agent orchestration | Yes | Yes |
| Headless / CI mode | Yes | Yes |
| Models | ||
| Backbone | GPT-5.6 Sol, GPT-5.6 Terra, GPT-5.6 Luna | Undisclosed (Cognition-managed models) |
| Bring your own model | NoThe Amazon Bedrock model-provider path is explicitly limited to local Codex surfaces and states that Codex cloud is not available (https://learn.chatgpt.com/docs/amazon-bedrock). | NoA cross-provider model picker (`--model` / `/model` / config `agent.model`) selects between Anthropic, OpenAI, Google, Cognition and open-source models, but every one of them is served by Cognition: the CLI model reference documents no API key, base URL, gateway, Bedrock, Vertex or Azure deployment of your own, matching pricing.byok = false. |
| Local models | NoCloud chats run on OpenAI-hosted models only; the `model_provider` config that redirects inference is read by local clients, not by cloud containers. | NoNo base URL, gateway or local endpoint setting exists in the Devin CLI config reference (https://docs.devin.ai/cli/reference/configuration/config-file). |
| Cost | ||
| Pricing model | subscription | mixed |
| Starts at | $20/mo | $20/mo |
| Free tier | No | Yes |
| Bring your own key | NoCloud tasks require a ChatGPT plan; an OpenAI API key does not unlock them. | NoUsage is billed in Cognition ACUs and no LLM provider key can be supplied; Devin Outposts (https://docs.devin.ai/cloud/outposts/overview) only moves session compute onto your own machines. |
| Openness | ||
| Open source | No | No |
| License | proprietary | proprietary |
| GitHub stars | n/a | n/a |
Which one would each critic pick
| Critic | Codex cloud | Devin | Pick |
|---|---|---|---|
| El Juez | — | — | not enough reviews |
| El Amigo | 7.3 | 6.3 | Codex cloud — Pick Codex cloud if you already pay for ChatGPT and want to hand a task off from a GitHub pull request or a Slack thread and come back later; pick Jules if you live in the Google world. |
| El Crítico | 6.5 | 5.3 | Codex cloud — Each environment can be granted internet access and holds your secrets, so the agent is a container with your credentials and a network policy you configured once and forgot. |
| El Profesor | 6.8 | 5.0 | Codex cloud — Clone, setup scripts, parallel execution, then a summary and diff with logs to inspect; a research preview since May 16, 2025 on codex-1, with no benchmark published for the current models. |
| La Inversora | 8.0 | 6.8 | Codex cloud — OpenAI folded the Codex app into the ChatGPT desktop app in July 2026 and sells Pro from $100 with 5x or 20x limits; the coding agent is a retention feature for the subscription. |
| La Jefa | 7.0 | 5.8 | Codex cloud — Business is $20 per user, $1,200 a month for sixty, extra usage is credits priced per model, and there is an Enterprise tier, the shape procurement already knows from ChatGPT. |
| El Hacker | 3.5 | 2.5 | Codex cloud — Proprietary, GPT-5.6 only, and the docs say API keys do not unlock cloud features, so my key buys nothing; an MCP client exists, and that is the entire surface. |
Picks are derived from each critic's own scores. Humans vote on matchups on the duels page.