Skip to content

Providers

claude-multi ships ready-to-use templates for these providers. Each template pre-fills ANTHROPIC_BASE_URL, model mappings, and related env vars into your instance’s settings.json. You only need to supply your API key.

TemplateDisplay nameEndpointOpus modelSonnet/Haiku model
glmGLM Coding Planapi.z.aiglm-5.2[1m]glm-5.1, glm-5-turbo
minimaxMiniMaxapi.minimax.ioMiniMax-M3MiniMax-M3
deepseekDeepSeekapi.deepseek.comdeepseek-v4-pro[1m]deepseek-v4-flash
mimoXiaomi MiMoapi.xiaomimimo.commimo-v2.5-promimo-v2.5
mimo-tokenXiaomi MiMo (Token Plan)token-plan-cn.xiaomimimo.commimo-v2.5-promimo-v2.5
kimiMoonshot Kimiapi.moonshot.aikimi-k2.7-codekimi-k2.6, kimi-k2.5
qwenAlibaba Qwendashscope-intl.aliyuncs.comqwen3-coder-nextqwen3-coder-flash
qwen-codingAlibaba Qwen Coding Plancoding-intl.dashscope.aliyuncs.comqwen3-coder-nextqwen3-coder-flash

All providers expose an Anthropic-compatible API, so claude-multi points the same Claude Code binary at whichever endpoint you pick.

Some providers offer two access models, a pay-per-token API and a subscription/coding plan, each with a different base URL. Use the right template for your account type:

ProviderPay-per-token templateSubscription template
Xiaomi MiMomimomimo-token (regional URL, swap in CN/SG/EU endpoint from your console)
Alibaba Qwenqwenqwen-coding
GLM (Z.ai)no Anthropic URLglm (Anthropic endpoint is coding-plan-only)
MiniMaxminimaxsame URL, different key type
Moonshot Kimikimipay-per-token only
DeepSeekdeepseekpay-per-token only
  • GLM: The Anthropic-compatible endpoint (api.z.ai/api/anthropic) is exclusive to the Z.ai Coding Plan subscription. The standard pay-per-token API only exposes an OpenAI-compatible URL.
  • MiMo Token Plan: The default base URL is the CN regional endpoint. If your subscription is on SG or EU, update ANTHROPIC_BASE_URL in ~/.claude-<name>/settings.json with the endpoint shown in your subscription console.
  • Kimi: No subscription plan, strictly pay-per-token at api.moonshot.ai.
  • MiniMax: Both Token Plan and pay-per-token use the same api.minimax.io endpoint; the API key type determines which quota is consumed. MiniMax-M3 has a 1M token context window and supports text, image, and video inputs.