Run Kimi K3.1 Pro Outlaw in Claude Code
Kimi K3.1 Pro with the refusal direction taken out: the strongest model on the line (55 on the Artificial Analysis Intelligence Index for the base model), with a million tokens of context, tool calling, reasoning and vision. The pick for the hardest agent work, at the line's highest price.
Uncensored Kimi K3.1 Pro sets it against the rest of the line, and uncensored Kimi goes through the Kimi releases one by one.
| Model id | kimi-k3.1-pro-outlaw |
|---|---|
| Context | 1.05M tokens |
| Input price | $7.50 / million tokens |
| Output price | $37.50 / million tokens |
| Tool calling | Supported |
Set it up
Point Claude Code's base URL at Wild West (no /v1), set the auth token to your key, name this model, and set the context length to its real value of 1,048,576:
# Put these in your shell profile, then run: claude export ANTHROPIC_BASE_URL=https://wildwestapi.com export ANTHROPIC_AUTH_TOKEN=sk-ww-... export ANTHROPIC_MODEL=kimi-k3.1-pro-outlaw export ANTHROPIC_DEFAULT_HAIKU_MODEL=glm-5.3-outlaw export CLAUDE_CODE_MAX_CONTEXT_TOKENS=1048576
Or put the same values under env in ~/.claude/settings.json:
// ~/.claude/settings.json { "env": { "ANTHROPIC_BASE_URL": "https://wildwestapi.com", "ANTHROPIC_AUTH_TOKEN": "sk-ww-...", "ANTHROPIC_MODEL": "kimi-k3.1-pro-outlaw", "ANTHROPIC_DEFAULT_HAIKU_MODEL": "glm-5.3-outlaw", "CLAUDE_CODE_MAX_CONTEXT_TOKENS": "1048576" } }
ANTHROPIC_DEFAULT_HAIKU_MODEL is the cheap background model, set to glm-5.3-outlaw above. CLAUDE_CODE_MAX_CONTEXT_TOKENS is set because Claude Code assumes 200K for an id it does not recognise. Use ANTHROPIC_AUTH_TOKEN and leave ANTHROPIC_API_KEY unset. Full setup and every caveat is in the Claude Code guide.
FAQ
Can Kimi K3.1 Pro Outlaw edit files and run commands in Claude Code?
Yes. It supports tool calling, which is what Claude Code needs to use its Read, Edit, Write and Bash tools. A model without tool calling could only chat.
How much does it cost?
$7.50 per million input tokens and $37.50 per million output tokens through Wild West. Put a spend cap on the key so an agent loop cannot overrun it.
Is this an official Anthropic setup?
No. Anthropic does not officially support routing Claude Code to non-Claude models through a gateway. It works because Wild West translates the Messages API, but it is not a configuration Anthropic backs.