Playbooks · Coding tasks
Run Kimi, GLM and DeepSeek in the harness you have
Written November 13, 2026
Umans Code serves Kimi K3.1 Pro, GLM 5.3 and DeepSeek V4.1 Flash to Claude Code, OpenCode, Cursor and more — one key, per-token prices.
The setup shape
Umans Code runs three open-weight models — DeepSeek V4.1 Flash, Kimi K3.1 Pro and GLM 5.3 — on its own GPU infrastructure, behind one API key. The tools it names are the ones developers already run: Claude Code, Cursor, Zed, Copilot, OpenCode, Kilo Code, Pi and more. You add credit, create a key, and point the tool you already run at Umans instead of replacing it.
Setup, in the guide's own summary, is one command or two environment variables. The OpenCode path is the lightest: Umans AI Coding Plan is listed on models.dev, so OpenCode finds it natively — add it under Providers and paste the key, or use the CLI route the guide gives. The Claude Code and related paths use the Umans CLI, which opens a browser to authenticate on first run and saves the key. A manual route also exists: the base URL is https://api.code.umans.ai, with an Anthropic-style endpoint and an OpenAI-style endpoint, and umans-coder as the model name to start from. Keys are created in the dashboard under API Keys, and a new key is shown only once.
The model table
- DeepSeek V4.1 Flash (
umans-deepseek-v4.1-flash): Umans calls it its featured model and the default for new chats. A 1M-token context, native image understanding, and four reasoning modes with think-high as the default. Priced at $0.15 per 1M input tokens and $0.60 per 1M output tokens, with cache reads at $0.028. - Kimi K3.1 Pro (
umans-kimi-k3.1-pro): Moonshot's newest open model, post-trained from Kimi K3, aimed at repository-scale runs. Also a 1M context with native image understanding, thinking at max effort by default, with lower effort settings available. Priced at $2.00 / $10.00 per 1M tokens, cache reads at $0.20. - GLM 5.3 (
umans-glm-5.3): Z.ai's flagship coding model, the GLM 5.2 successor, positioned for complex, long-horizon tasks. A 1M context. It always thinks — the setting can be dialled from low to max but not turned off. Priced at $1.40 / $4.40 per 1M tokens, cache reads at $0.26.
All three carry the same 1M context figure in Umans' table, so the choice between them is price and reasoning behaviour, not window size. The spread is wide: DeepSeek's flash model costs a fraction of the Kimi tier per output token, which is why Umans makes it the default rather than the premium pick.
The routing caveat
Two model IDs do not name a fixed model. umans-coder, the recommended default, and umans-flash, the fast tier for supporting roles, route to whatever Umans currently picks. Umans states plainly that the picks change as it evaluates models: today both run DeepSeek V4.1 Flash at its rates, and umans-coder previously ran a GLM flash model and Kimi K2.7-Code before that. The live target is published through the service's model-info endpoint.
That is a reasonable default for a developer who does not want to track model releases, and a real caveat for one who does. A workflow tuned against one model's behaviour can find itself running another model under the same ID. If reproducibility matters, pin one of the three named model IDs instead of the routing IDs.
What to watch
- The catalog moves: Umans retired several model IDs during September and November 2026, with successors named for each. A pinned ID needs an occasional look at the current list.
- Umans says it does not train on your data, and that you pay only for tokens consumed, with each request debited for what the model used.
- Reasoning controls from either API style are accepted on either endpoint, per the guide, which keeps tool configuration simple.
Related playbooks
- Run Muse Spark in another harness via the Model API
- Run an open-weight agent with egress denied: what the Qwen sandbox incident does and does not prove
- Run three independent lines of research at the same time in Claude Code, then combine the short summaries
- Run Sonnet with an Opus advisor in Claude Code
Sources
- Frontier open-source coding models for any tool — Umans Code docs
- Umans Code for organizations — Umans Code docs
Back to: Coding tasks playbooks hub · Also: Run MiniMax in Claude Code