Providers

ccode supports a variety of model providers out of the box. Each provider gets its own profile in your config file. This page covers the setup for each supported provider type.

For the full list of available YAML fields, see the Config Reference.

Anthropic direct

The simplest setup. ccode launches Claude Code without setting any environment variables.

Subscription passthrough

If you have a Claude Pro, Max, Team, or Enterprise subscription, the default: {} profile launches Claude Code as-is:

profiles:
  default: {}

API key billing

For pay-per-token billing through Anthropic’s API, set anthropic_api_key:

profiles:
  anthropic:
    anthropic_api_key: sk-ant-your-key-here

Get your API key at console.anthropic.com.

First-party cloud providers

These run Claude models on AWS, GCP, or Azure infrastructure. Authentication uses your cloud provider’s credentials, not an Anthropic auth token.

Amazon Bedrock

profiles:
  bedrock:
    claude_code_use_bedrock: true

AWS credentials are handled by IAM (roles, SSO, environment variables, credential files). See Anthropic’s Bedrock docs.

Optional settings: anthropic_bedrock_base_url, claude_code_skip_bedrock_auth, aws_bearer_token_bedrock, anthropic_bedrock_service_tier.

Amazon Bedrock Mantle

profiles:
  mantle:
    claude_code_use_mantle: true

A variant of Bedrock with a dedicated endpoint. See Anthropic’s Mantle docs.

Google Vertex AI

profiles:
  vertex:
    claude_code_use_vertex: true
    anthropic_vertex_project_id: your-gcp-project-id

Uses Google Cloud application default credentials (gcloud auth). See Anthropic’s Vertex AI docs.

Microsoft Foundry (Azure)

profiles:
  foundry:
    claude_code_use_foundry: true
    anthropic_foundry_base_url: https://your-resource.services.ai.azure.com/anthropic
    anthropic_foundry_api_key: YOUR_FOUNDRY_API_KEY_HERE

See Anthropic’s Foundry docs.

Third-party providers (native Anthropic format)

These providers expose an Anthropic-compatible API endpoint. Each needs anthropic_base_url and anthropic_auth_token.

Tip: Most third-party providers need CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS set to "1" in their env: block. This strips Anthropic-specific headers that non-Anthropic providers reject.

DeepSeek

Sign up at platform.deepseek.com.

profiles:
  deepseek:
    anthropic_base_url: https://api.deepseek.com/anthropic
    anthropic_auth_token: YOUR_DEEPSEEK_API_KEY_HERE
    anthropic_model: "deepseek-v4-pro[1m]"
    anthropic_default_opus_model: "deepseek-v4-pro[1m]"
    anthropic_default_sonnet_model: "deepseek-v4-pro[1m]"
    anthropic_default_haiku_model: deepseek-v4-flash
    claude_code_subagent_model: deepseek-v4-flash
    claude_code_effort_level: max
    env:
      CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS: "1"

OpenRouter

Sign up at openrouter.ai. OpenRouter gives access to 400+ models behind a single endpoint.

profiles:
  openrouter:
    anthropic_base_url: https://openrouter.ai/api
    anthropic_auth_token: YOUR_OPENROUTER_API_KEY_HERE
    anthropic_model: anthropic/claude-sonnet-4.6
    anthropic_default_opus_model: anthropic/claude-opus-4.7
    anthropic_default_sonnet_model: anthropic/claude-sonnet-4.6
    anthropic_default_haiku_model: anthropic/claude-haiku-4.5
    claude_code_subagent_model: anthropic/claude-haiku-4.5
    env:
      CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS: "1"

OpenRouter presets: You can create presets at openrouter.ai/workspaces/default/presets and use them as model names with the @preset/slug syntax.

Z.AI (Zhipu GLM)

Sign up at z.ai (international) or open.bigmodel.cn (China).

profiles:
  zai:
    anthropic_base_url: https://api.z.ai/api/anthropic
    anthropic_auth_token: YOUR_ZAI_API_KEY_HERE
    anthropic_model: glm-5.1
    anthropic_default_opus_model: glm-5.1
    anthropic_default_sonnet_model: glm-5.1
    anthropic_default_haiku_model: glm-4.5-air
    claude_code_subagent_model: glm-4.5-air
    env:
      CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS: "1"

Moonshot Kimi

Sign up at kimi.ai.

profiles:
  kimi:
    anthropic_base_url: https://api.moonshot.ai/anthropic
    anthropic_auth_token: YOUR_KIMI_API_KEY_HERE
    anthropic_model: kimi-k2.6
    env:
      CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS: "1"

Alibaba Qwen (DashScope)

Sign up at alibabacloud.com.

profiles:
  qwen:
    anthropic_base_url: https://dashscope-intl.aliyuncs.com/apps/anthropic
    anthropic_auth_token: YOUR_DASHSCOPE_API_KEY_HERE
    anthropic_model: qwen3.6-plus
    env:
      CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS: "1"

MiniMax

Sign up at minimax.io.

profiles:
  minimax:
    anthropic_base_url: https://api.minimax.io/anthropic
    anthropic_auth_token: YOUR_MINIMAX_API_KEY_HERE
    anthropic_model: MiniMax-M2.7
    env:
      CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS: "1"

Local and self-hosted models

Point anthropic_base_url at your local server. Several tools support the Anthropic Messages API format natively:

• llama.cpp - native /v1/messages support (github.com/ggml-org/llama.cpp)
• vLLM - native /v1/messages since v0.4 (github.com/vllm-project/vllm)
• Ollama - Anthropic-compatible endpoint (ollama.com)
• LM Studio - Anthropic-compatible endpoint (lmstudio.ai)

profiles:
  local:
    anthropic_base_url: http://localhost:8080/v1
    anthropic_auth_token: not-needed
    anthropic_model: your-local-model
    env:
      CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS: "1"
      DISABLE_INTERLEAVED_THINKING: "1"
      CLAUDE_CODE_DISABLE_NONSTREAMING_FALLBACK: "1"

For tools that only speak OpenAI format, use a translation proxy:

• LiteLLM - github.com/BerriAI/litellm

Common gotchas

Community resources

For an actively maintained reference of model IDs, pricing, and per-provider configs, see the Alorse/cc-compatible-models repo on GitHub.