opencode and Qwen Code, fact by fact
| Fact | opencode | Qwen Code |
|---|---|---|
| Starsopencode has 183,972 more stars (7.5×). | 212,333Verified 8 Oct 2026 | 28,361Verified 8 Oct 2026 |
| Newest commitBoth committed on the same day. | 8 Oct 20260 days old when we read itVerified 8 Oct 2026 | 8 Oct 20260 days old when we read itVerified 8 Oct 2026 |
| Contributorsopencode has 34 more contributors (1.1×). | 454Verified 8 Oct 2026 | 420Verified 8 Oct 2026 |
| LicenseMIT against Apache-2.0. | MITVerified 8 Oct 2026 | Apache-2.0Verified 8 Oct 2026 |
| Latest stable releaseBoth released on the same day. | v1.18.35published 6 Oct 2026Verified 8 Oct 2026 | sdk-typescript-v0.1.18published 5 Oct 2026Verified 8 Oct 2026 |
| npm downloadsopencode has 3,213,780 more npm downloads a week (32×). | 3,318,599 a weekopencode-aiVerified 8 Oct 2026 | 104,819 a week@qwen-code/qwen-codeVerified 8 Oct 2026 |
| Homebrew installsopencode has 18,649 more Homebrew installs in 30 days (7.7×). | 21,432 in 30 daysopencodeVerified 8 Oct 2026 | 2,783 in 30 daysqwen-codeVerified 8 Oct 2026 |
| Repository | anomalyco/opencodeTypeScriptVerified 8 Oct 2026 | QwenLM/qwen-codeTypeScriptVerified 8 Oct 2026 |
What we know about opencode
OpenCode reaches 75+ LLM providers and local models from a single config file, because it resolves every model through the AI SDK and the Models.dev catalogue instead of a hand-written provider list.
“OpenCode uses the AI SDK and Models.dev to support 75+ LLM providers and it supports running local models.”
Explore an unfamiliar codebase before you change it: the built-in plan agent refuses file edits and asks before each bash command.
“**plan** - Read-only agent for analysis and code exploration · - Denies file edits by default · - Asks permission before running bash commands · - Ideal for exploring unfamiliar codebases or planning changes”
Run one task against two vendors' models in the same session: `/connect` adds a provider key and the model picker switches without a restart.
“Add the API keys for the provider using the /connect command.”
Run the agent inside CI on your own runner: mentioning /opencode or /oc on a GitHub issue or pull request executes the task in GitHub Actions.
“OpenCode integrates with your GitHub workflow. Mention /opencode or /oc in your comment, and OpenCode will execute tasks within your GitHub Actions runner.”
A fresh install edits files and runs shell commands with no approval prompt, because every permission except `doom_loop` and `external_directory` starts at allow.
“Most permissions default to "allow".”
Memory grows through a long terminal session: the maintainers opened a central memory thread on 2026-04-02, asked users for heap snapshots taken once the process reaches 1-2 GB, and the thread is still open 139 days later.
“We have scattered reports of memory issues so we are going to tackle them all in a central place.”
`/share` copies the transcript to OpenCode's servers, and the resulting link needs no password.
“Shared conversations are publicly accessible to anyone with the link.”
A team that must lock the agent down before its first run should choose Codex CLI, which starts inside an OS-enforced sandbox with the network switched off.
“By default, the agent runs with network access turned off.”
What opencode costs
OpenCode Go, the optional subscription, costs $5 for the first month and $10 a month after that, and one workspace can hold only one subscriber.
“OpenCode Go is a low cost subscription — $5 for your first month, then $10/month — that gives you reliable access to popular open coding models.”
A workspace can hold only one Go subscriber, so a second developer needs a second workspace.
“Only one member per workspace can subscribe to OpenCode Go.”
What we know about Qwen Code
Qwen Code binds the local agent to Telegram, DingTalk, WeChat or Feishu with one command, `qwen channel`, and ships TypeScript, Python and Java SDKs beside the CLI.
“- **Beyond the terminal** — IDE plugins, Desktop app, daemon mode, SDKs, and IM bots (Telegram / DingTalk / WeChat / Feishu).”
Run the agent from a group chat your team already uses, with `qwen channel`.
“| **IM Bot** | `qwen channel` | Connect to Telegram, DingTalk, WeChat, or Feishu |”
Embed the agent in your own program through the TypeScript, Python or Java SDK instead of shelling out to a CLI.
“| **SDK** | — | [TypeScript](./packages/sdk-typescript/README.md), [Python](./packages/sdk-python/README.md), [Java](./packages/sdk-java/qwencode/README.md) |”
Batch a repository-wide edit in CI with `qwen -p "..."`, which runs without the terminal UI.
“| **Headless** | `qwen -p "..."` | Scripts, CI/CD, batch processing — no UI |”
Qwen Code is no longer free: the Qwen OAuth free tier was discontinued on 2026-04-15, and requests on an old token are now rejected.
“The Qwen OAuth free tier was discontinued on 2026-04-15. Existing cached tokens may continue working briefly, but new requests will be rejected.”
You cannot finish sign-in on a server: OAuth needs a browser, which CI, SSH and container sessions do not have.
“In non-interactive or headless environments (e.g., CI, SSH, containers), you typically cannot complete the OAuth browser login flow.”
Image input regressed in the shipping line: a crash on image load since 0.21.2 is open, and the current release is v0.21.14.
“[Regression] Qwen code crashes on image load since 0.21.2”
A developer who chose Qwen Code because it was free should now price the Alibaba ModelStudio Coding Plan, or move to goose, which runs a local Ollama model at no per-token cost.
“Cost & quota : the free tier has been discontinued as of 2026-04-15.”
What Qwen Code costs
The free tier is gone as of 2026-04-15; the vendor's recommended replacement is the Alibaba ModelStudio Coding Plan, whose weekly quota is priced on Alibaba's own page, which I did not read today.
“Alibaba ModelStudio : official recommended setup. Opens a sub-menu with Coding Plan (for individual developers · weekly quota included), Token Plan (for teams and companies · usage-based billing with a dedicated endpoint), or Standard API Key (connect with an existing ModelStudio API key).”
Questions people ask
- Are opencode and Qwen Code still maintained?
- opencode committed to anomalyco/opencode (dev) on 8 Oct 2026. Qwen Code committed to QwenLM/qwen-code (main) on 8 Oct 2026. Both readings come from the default branch of each repository, on the date shown beside them.
- What do opencode and Qwen Code cost?
- opencode: OpenCode Go, the optional subscription, costs $5 for the first month and $10 a month after that, and one workspace can hold only one subscriber. A workspace can hold only one Go subscriber, so a second developer needs a second workspace. Qwen Code: The free tier is gone as of 2026-04-15; the vendor's recommended replacement is the Alibaba ModelStudio Coding Plan, whose weekly quota is priced on Alibaba's own page, which I did not read today. Every figure here is quoted from the vendor's own page and linked beside the claim.
- Is opencode or Qwen Code open source?
- opencode's repository anomalyco/opencode reports the MIT licence. Qwen Code's repository QwenLM/qwen-code reports the Apache-2.0 licence. We read the licence GitHub reports for the repository, which is not the same question as whether the hosted product is free.
How we check this page
- Machine facts. Stars, contributors, the newest commit on the default branch, the licence GitHub reports and the latest stable release come from the GitHub API, and download counts from npm, PyPI, Homebrew and the VS Code Marketplace. Each value carries the day it was last confirmed, never the day this page was built. The line under each label is arithmetic on those two values.
- Judgments. Every claim about what a tool suits, what it is bad at and what it costs is quoted from a page we read, and that page is linked beside the claim. Where there is no link, we wrote no claim.
- Index status. Both opencode and Qwen Code carry claims we read, quoted and linked. So this page is offered to search engines.
Related comparisons
Pairs we can answer for come first.
