Providers

Using any LLM provider in Anthracode.

Anthracode uses the AI SDK and Models.dev to support 75+ LLM providers and it supports running local models.

To add a provider you need to:

Add the API keys for the provider using the /connect command.
Configure the provider in your Anthracode config.

Credentials

When you add a provider’s API keys with the /connect command, they are stored in ~/.local/share/anthracode/auth.json.

Config

You can customize the providers through the provider section in your Anthracode config.

Base URL

You can customize the base URL for any provider by setting the baseURL option. This is useful when using proxy services or custom endpoints.

{

  "provider": {
    "anthropic": {
      "options": {
        "baseURL": "https://api.anthropic.com/v1"
      }
    }
  }
}

Directory

Let’s look at some of the providers in detail. If you’d like to add a provider to the list, feel free to open a PR.

302.AI

Head over to the 302.AI console, create an account, and generate an API key.
Run the /connect command and search for 302.AI.
```
/connect
```
Enter your 302.AI API key.
```
┌ API key
│
│
└ enter
```
Run the /models command to select a model.
```
/models
```

Amazon Bedrock

To use Amazon Bedrock with Anthracode:

Head over to the Model catalog in the Amazon Bedrock console and request access to the models you want.

You need to have access to the model you want in Amazon Bedrock.
Configure authentication using one of the following methods:

Environment Variables (Quick Start)
Section titled “Environment Variables (Quick Start)”

Set one of these environment variables while running anthracode:
Terminal window
```
# Option 1: Using AWS access keys
AWS_ACCESS_KEY_ID=XXX AWS_SECRET_ACCESS_KEY=YYY anthracode

# Option 2: Using named AWS profile
AWS_PROFILE=my-profile anthracode

# Option 3: Using Bedrock bearer token
AWS_BEARER_TOKEN_BEDROCK=XXX anthracode
```
Or add them to your bash profile:
~/.bash_profile
```
export AWS_PROFILE=my-dev-profile
export AWS_REGION=us-east-1
```
Configuration File (Recommended)
Section titled “Configuration File (Recommended)”

For project-specific or persistent configuration, use anthracode.jsonc:
anthracode.jsonc
```
{

  "provider": {
    "amazon-bedrock": {
      "options": {
        "region": "us-east-1",
        "profile": "my-aws-profile"
      }
    }
  }
}
```
Available options:
- region - AWS region (e.g., us-east-1, eu-west-1)
- profile - AWS named profile from ~/.aws/credentials
- endpoint - Custom endpoint URL for VPC endpoints (alias for generic baseURL option)
Configuration file options take precedence over environment variables.

Advanced: VPC Endpoints
Section titled “Advanced: VPC Endpoints”

If you’re using VPC endpoints for Bedrock:
anthracode.jsonc
```
{

  "provider": {
    "amazon-bedrock": {
      "options": {
        "region": "us-east-1",
        "profile": "production",
        "endpoint": "https://bedrock-runtime.us-east-1.vpce-xxxxx.amazonaws.com"
      }
    }
  }
}
```
The endpoint option is an alias for the generic baseURL option, using AWS-specific terminology. If both endpoint and baseURL are specified, endpoint takes precedence.

Authentication Methods
Section titled “Authentication Methods”
- AWS_ACCESS_KEY_ID / AWS_SECRET_ACCESS_KEY: Create an IAM user and generate access keys in the AWS Console
- AWS_PROFILE: Use named profiles from ~/.aws/credentials. First configure with aws configure --profile my-profile or aws sso login
- AWS_BEARER_TOKEN_BEDROCK: Generate long-term API keys from the Amazon Bedrock console
- AWS_WEB_IDENTITY_TOKEN_FILE / AWS_ROLE_ARN: For EKS IRSA (IAM Roles for Service Accounts) or other Kubernetes environments with OIDC federation. These environment variables are automatically injected by Kubernetes when using service account annotations.
Authentication Precedence
Section titled “Authentication Precedence”

Amazon Bedrock uses the following authentication priority:
1. Bearer Token - AWS_BEARER_TOKEN_BEDROCK environment variable or token from /connect command
2. AWS Credential Chain - Profile, access keys, shared credentials, IAM roles, Web Identity Tokens (EKS IRSA), instance metadata
When a bearer token is set (via /connect or AWS_BEARER_TOKEN_BEDROCK), it takes precedence over all AWS credential methods including configured profiles.
Run the /models command to select the model you want.
```
/models
```

{

  "provider": {
    "amazon-bedrock": {
      // ...
      "models": {
        "anthropic-claude-sonnet-4.5": {
          "id": "arn:aws:bedrock:us-east-1:xxx:application-inference-profile/yyy"
        }
      }
    }
  }
}

Anthropic

Once you’ve signed up, run the /connect command and select Anthropic.
```
/connect
```
Here you can select the Claude Pro/Max option and it’ll open your browser and ask you to authenticate.
```
┌ Select auth method
│
│ Manually enter API Key
└
```
Now all the Anthropic models should be available when you use the /models command.
```
/models
```

There are plugins that allow you to use your Claude Pro/Max models with Anthracode. Anthropic explicitly prohibits this.

Previous versions of Anthracode came bundled with these plugins but that is no longer the case as of 1.3.0

Other companies support freedom of choice with developer tooling - you can use the following subscriptions in Anthracode with zero setup:

ChatGPT Plus
Github Copilot
Gitlab Duo

Atomic Chat

You can configure anthracode to use local models through Atomic Chat, a desktop application that runs local LLMs behind an OpenAI-compatible API server (default endpoint http://127.0.0.1:1337/v1).

{

  "provider": {
    "atomic-chat": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Atomic Chat (local)",
      "options": {
        "baseURL": "http://127.0.0.1:1337/v1"
      },
      "models": {
        "<your-model-id>": {
          "name": "<your-model-name>"
        }
      }
    }
  }
}

In this example:

atomic-chat is the custom provider ID. This can be any string you want.
npm specifies the package to use for this provider. Here, @ai-sdk/openai-compatible is used for any OpenAI-compatible API.
name is the display name for the provider in the UI.
options.baseURL is the endpoint for the local server. Change the host and port to match your Atomic Chat setup.
models is a map of model IDs to their display names. Each ID must match the id returned by GET /v1/models — run curl http://127.0.0.1:1337/v1/models to list the ids currently loaded in Atomic Chat.

Azure OpenAI

Head over to the Azure portal and create an Azure OpenAI resource. You’ll need:
- Resource name: This becomes part of your API endpoint (https://RESOURCE_NAME.openai.azure.com/)
- API key: Either KEY 1 or KEY 2 from your resource
Go to Azure AI Foundry and deploy a model.

The deployment name must match the model name for anthracode to work properly.
Run the /connect command and search for Azure.
```
/connect
```
Enter your API key.
```
┌ API key
│
│
└ enter
```
Set your resource name as an environment variable:
Terminal window
```
AZURE_RESOURCE_NAME=XXX anthracode
```
Or add it to your bash profile:
~/.bash_profile
```
export AZURE_RESOURCE_NAME=XXX
```
Run the /models command to select your deployed model.
```
/models
```

Azure Cognitive Services

Head over to the Azure portal and create an Azure OpenAI resource. You’ll need:
- Resource name: This becomes part of your API endpoint (https://AZURE_COGNITIVE_SERVICES_RESOURCE_NAME.cognitiveservices.azure.com/)
- API key: Either KEY 1 or KEY 2 from your resource
Go to Azure AI Foundry and deploy a model.

The deployment name must match the model name for anthracode to work properly.
Run the /connect command and search for Azure Cognitive Services.
```
/connect
```
Enter your API key.
```
┌ API key
│
│
└ enter
```
Set your resource name as an environment variable:
Terminal window
```
AZURE_COGNITIVE_SERVICES_RESOURCE_NAME=XXX anthracode
```
Or add it to your bash profile:
~/.bash_profile
```
export AZURE_COGNITIVE_SERVICES_RESOURCE_NAME=XXX
```
Run the /models command to select your deployed model.
```
/models
```

Baseten

Head over to the Baseten, create an account, and generate an API key.
Run the /connect command and search for Baseten.
```
/connect
```
Enter your Baseten API key.
```
┌ API key
│
│
└ enter
```
Run the /models command to select a model.
```
/models
```

Cerebras

Head over to the Cerebras console, create an account, and generate an API key.
Run the /connect command and search for Cerebras.
```
/connect
```
Enter your Cerebras API key.
```
┌ API key
│
│
└ enter
```
Run the /models command to select a model like Qwen 3 Coder 480B.
```
/models
```

Cloudflare AI Gateway

Cloudflare AI Gateway lets you access models from OpenAI, Anthropic, Workers AI, and more through a unified endpoint. With Unified Billing you don’t need separate API keys for each provider.

Head over to the Cloudflare dashboard, navigate to AI > AI Gateway, and create a new gateway. Note your Account ID and Gateway ID.
Run the /connect command and search for Cloudflare AI Gateway.
```
/connect
```

Enter your Account ID when prompted.

┌ Enter your Cloudflare Account ID
│
│
└ enter

Enter your Gateway ID when prompted.

┌ Enter your Cloudflare AI Gateway ID
│
│
└ enter

Enter your Cloudflare API token.
```
┌ Gateway API token
│
│
└ enter
```

Run the /models command to select a model.

/models

You can also add models through your anthracode config.

{

  "provider": {
    "cloudflare-ai-gateway": {
      "models": {
        "openai/gpt-4o": {},
        "anthropic/claude-sonnet-4": {}
      }
    }
  }
}

Alternatively, you can set environment variables instead of using /connect.

export CLOUDFLARE_ACCOUNT_ID=your-32-character-account-id
export CLOUDFLARE_GATEWAY_ID=your-gateway-id
export CLOUDFLARE_API_TOKEN=your-api-token

Cloudflare Workers AI

Cloudflare Workers AI lets you run AI models on Cloudflare’s global network directly via REST API, with no separate provider accounts needed for supported models.

Head over to the Cloudflare dashboard, navigate to Workers AI, and select Use REST API to get your Account ID and create an API token.
Run the /connect command and search for Cloudflare Workers AI.
```
/connect
```

Enter your Account ID when prompted.

┌ Enter your Cloudflare Account ID
│
│
└ enter

Enter your Cloudflare API key.
```
┌ API key
│
│
└ enter
```
Run the /models command to select a model.
```
/models
```
Alternatively, you can set environment variables instead of using /connect.
~/.bash_profile
```
export CLOUDFLARE_ACCOUNT_ID=your-32-character-account-id
export CLOUDFLARE_API_KEY=your-api-token
```

Cortecs

Head over to the Cortecs console, create an account, and generate an API key.
Run the /connect command and search for Cortecs.
```
/connect
```
Enter your Cortecs API key.
```
┌ API key
│
│
└ enter
```
Run the /models command to select a model like Kimi K2 Instruct.
```
/models
```

DeepSeek

Head over to the DeepSeek console, create an account, and click Create new API key.
Run the /connect command and search for DeepSeek.
```
/connect
```
Enter your DeepSeek API key.
```
┌ API key
│
│
└ enter
```
Run the /models command to select a DeepSeek model like DeepSeek V4 Pro.
```
/models
```

Deep Infra

Head over to the Deep Infra dashboard, create an account, and generate an API key.
Run the /connect command and search for Deep Infra.
```
/connect
```
Enter your Deep Infra API key.
```
┌ API key
│
│
└ enter
```
Run the /models command to select a model.
```
/models
```

FrogBot

Head over to the FrogBot dashboard, create an account, and generate an API key.
Run the /connect command and search for FrogBot.
```
/connect
```
Enter your FrogBot API key.
```
┌ API key
│
│
└ enter
```
Run the /models command to select a model.
```
/models
```

Fireworks AI

Head over to the Fireworks AI console, create an account, and click Create API Key.
Run the /connect command and search for Fireworks AI.
```
/connect
```
Enter your Fireworks AI API key.
```
┌ API key
│
│
└ enter
```
Run the /models command to select a model like Kimi K2 Instruct.
```
/models
```

GitHub Copilot

To use your GitHub Copilot subscription with anthracode:

Run the /connect command and search for GitHub Copilot.
```
/connect
```

Navigate to github.com/login/device and enter the code.

┌ Login with GitHub Copilot
│
│ https://github.com/login/device
│
│ Enter code: 8F43-6FCF
│
└ Waiting for authorization...

Now run the /models command to select the model you want.
```
/models
```

Google Vertex AI

To use Google Vertex AI with Anthracode:

Head over to the Model Garden in the Google Cloud Console and check the models available in your region.

You need to have a Google Cloud project with Vertex AI API enabled.
Set the required environment variables:
- GOOGLE_CLOUD_PROJECT: Your Google Cloud project ID
- VERTEX_LOCATION (optional): The region for Vertex AI (defaults to global)
- Authentication (choose one):
  - GOOGLE_APPLICATION_CREDENTIALS: Path to your service account JSON key file
  - Authenticate using gcloud CLI: gcloud auth application-default login
Set them while running anthracode.
Terminal window
```
GOOGLE_APPLICATION_CREDENTIALS=/path/to/service-account.json GOOGLE_CLOUD_PROJECT=your-project-id anthracode
```
Or add them to your bash profile.
~/.bash_profile
```
export GOOGLE_APPLICATION_CREDENTIALS=/path/to/service-account.json
export GOOGLE_CLOUD_PROJECT=your-project-id
export VERTEX_LOCATION=global
```

Run the /models command to select the model you want.
```
/models
```

Groq

Head over to the Groq console, click Create API Key, and copy the key.
Run the /connect command and search for Groq.
```
/connect
```
Enter the API key for the provider.
```
┌ API key
│
│
└ enter
```
Run the /models command to select the one you want.
```
/models
```

Hugging Face

Hugging Face Inference Providers provides access to open models supported by 17+ providers.

Head over to Hugging Face settings to create a token with permission to make calls to Inference Providers.
Run the /connect command and search for Hugging Face.
```
/connect
```
Enter your Hugging Face token.
```
┌ API key
│
│
└ enter
```
Run the /models command to select a model like Kimi-K2-Instruct or GLM-4.6.
```
/models
```

Helicone is an LLM observability platform that provides logging, monitoring, and analytics for your AI applications. The Helicone AI Gateway routes your requests to the appropriate provider automatically based on the model.

Head over to Helicone, create an account, and generate an API key from your dashboard.
Run the /connect command and search for Helicone.
```
/connect
```
Enter your Helicone API key.
```
┌ API key
│
│
└ enter
```
Run the /models command to select a model.
```
/models
```

For more providers and advanced features like caching and rate limiting, check the Helicone documentation.

Optional Configs

In the event you see a feature or model from Helicone that isn’t configured automatically through anthracode, you can always configure it yourself.

Here’s Helicone’s Model Directory, you’ll need this to grab the IDs of the models you want to add.

{

  "provider": {
    "helicone": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Helicone",
      "options": {
        "baseURL": "https://ai-gateway.helicone.ai",
      },
      "models": {
        "gpt-4o": {
          // Model ID (from Helicone's model directory page)
          "name": "GPT-4o", // Your own custom name for the model
        },
        "claude-sonnet-4-20250514": {
          "name": "Claude Sonnet 4",
        },
      },
    },
  },
}

Custom Headers

Helicone supports custom headers for features like caching, user tracking, and session management. Add them to your provider config using options.headers:

{

  "provider": {
    "helicone": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Helicone",
      "options": {
        "baseURL": "https://ai-gateway.helicone.ai",
        "headers": {
          "Helicone-Cache-Enabled": "true",
          "Helicone-User-Id": "anthracode",
        },
      },
    },
  },
}

Session tracking

Helicone’s Sessions feature lets you group related LLM requests together. Use the anthracode-helicone-session plugin to automatically log each Anthracode conversation as a session in Helicone.

npm install -g anthracode-helicone-session

Add it to your config.

{
  "plugin": ["anthracode-helicone-session"]
}

The plugin injects Helicone-Session-Id and Helicone-Session-Name headers into your requests. In Helicone’s Sessions page, you’ll see each Anthracode conversation listed as a separate session.

Common Helicone headers

Header	Description
`Helicone-Cache-Enabled`	Enable response caching (`true`/`false`)
`Helicone-User-Id`	Track metrics by user
`Helicone-Property-[Name]`	Add custom properties (e.g., `Helicone-Property-Environment`)
`Helicone-Prompt-Id`	Associate requests with prompt versions

See the Helicone Header Directory for all available headers.

llama.cpp

You can configure anthracode to use local models through llama.cpp’s llama-server utility

{

  "provider": {
    "llama.cpp": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "llama-server (local)",
      "options": {
        "baseURL": "http://127.0.0.1:8080/v1"
      },
      "models": {
        "qwen3-coder:a3b": {
          "name": "Qwen3-Coder: a3b-30b (local)",
          "limit": {
            "context": 128000,
            "output": 65536
          }
        }
      }
    }
  }
}

In this example:

llama.cpp is the custom provider ID. This can be any string you want.
npm specifies the package to use for this provider. Here, @ai-sdk/openai-compatible is used for any OpenAI-compatible API.
name is the display name for the provider in the UI.
options.baseURL is the endpoint for the local server.
models is a map of model IDs to their configurations. The model name will be displayed in the model selection list.

IO.NET

IO.NET offers 17 models optimized for various use cases:

Head over to the IO.NET console, create an account, and generate an API key.
Run the /connect command and search for IO.NET.
```
/connect
```
Enter your IO.NET API key.
```
┌ API key
│
│
└ enter
```
Run the /models command to select a model.
```
/models
```

LM Studio

You can configure anthracode to use local models through LM Studio.

{

  "provider": {
    "lmstudio": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "LM Studio (local)",
      "options": {
        "baseURL": "http://127.0.0.1:1234/v1"
      },
      "models": {
        "google/gemma-3n-e4b": {
          "name": "Gemma 3n-e4b (local)"
        }
      }
    }
  }
}

In this example:

lmstudio is the custom provider ID. This can be any string you want.
npm specifies the package to use for this provider. Here, @ai-sdk/openai-compatible is used for any OpenAI-compatible API.
name is the display name for the provider in the UI.
options.baseURL is the endpoint for the local server.
models is a map of model IDs to their configurations. The model name will be displayed in the model selection list.

Moonshot AI

To use Kimi K2 from Moonshot AI:

Head over to the Moonshot AI console, create an account, and click Create API key.
Run the /connect command and search for Moonshot AI.
```
/connect
```
Enter your Moonshot API key.
```
┌ API key
│
│
└ enter
```
Run the /models command to select Kimi K2.
```
/models
```

MiniMax

Head over to the MiniMax API Console, create an account, and generate an API key.
Run the /connect command and search for MiniMax.
```
/connect
```
Enter your MiniMax API key.
```
┌ API key
│
│
└ enter
```
Run the /models command to select a model like M2.1.
```
/models
```

NVIDIA

NVIDIA provides access to Nemotron models and many other open models through build.nvidia.com for free.

Head over to build.nvidia.com, create an account, and generate an API key.
Run the /connect command and search for NVIDIA.
```
/connect
```
Enter your NVIDIA API key.
```
┌ API key
│
│
└ enter
```
Run the /models command to select a model like nemotron-3-super-120b-a12b.
```
/models
```

On-Prem / NIM

You can also use NVIDIA models locally via NVIDIA NIM by setting a custom base URL.

{

  "provider": {
    "nvidia": {
      "options": {
        "baseURL": "http://localhost:8000/v1"
      }
    }
  }
}

Environment Variable

Alternatively, set your API key as an environment variable.

export NVIDIA_API_KEY=nvapi-your-key-here

Nebius Token Factory

Head over to the Nebius Token Factory console, create an account, and click Add Key.
Run the /connect command and search for Nebius Token Factory.
```
/connect
```
Enter your Nebius Token Factory API key.
```
┌ API key
│
│
└ enter
```
Run the /models command to select a model like Kimi K2 Instruct.
```
/models
```

Ollama

You can configure anthracode to use local models through Ollama.

{

  "provider": {
    "ollama": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Ollama (local)",
      "options": {
        "baseURL": "http://localhost:11434/v1"
      },
      "models": {
        "llama2": {
          "name": "Llama 2"
        }
      }
    }
  }
}

In this example:

ollama is the custom provider ID. This can be any string you want.
npm specifies the package to use for this provider. Here, @ai-sdk/openai-compatible is used for any OpenAI-compatible API.
name is the display name for the provider in the UI.
options.baseURL is the endpoint for the local server.
models is a map of model IDs to their configurations. The model name will be displayed in the model selection list.

Ollama Cloud

To use Ollama Cloud with Anthracode:

Head over to https://ollama.com/ and sign in or create an account.
Navigate to Settings > Keys and click Add API Key to generate a new API key.
Copy the API key for use in Anthracode.
Run the /connect command and search for Ollama Cloud.
```
/connect
```
Enter your Ollama Cloud API key.
```
┌ API key
│
│
└ enter
```
Important: Before using cloud models in Anthracode, you must pull the model information locally:
Terminal window
```
ollama pull gpt-oss:20b-cloud
```
Run the /models command to select your Ollama Cloud model.
```
/models
```

OpenAI

We recommend signing up for ChatGPT Plus or Pro.

Once you’ve signed up, run the /connect command and select OpenAI.
```
/connect
```
Here you can select the ChatGPT Plus/Pro option and it’ll open your browser and ask you to authenticate.
```
┌ Select auth method
│
│ ChatGPT Plus/Pro
│ Manually enter API Key
└
```
Now all the OpenAI models should be available when you use the /models command.
```
/models
```

Using API keys

If you already have an API key, you can select Manually enter API Key and paste it in your terminal.

OpenRouter

Head over to the OpenRouter dashboard, click Create API Key, and copy the key.
Run the /connect command and search for OpenRouter.
```
/connect
```
Enter the API key for the provider.
```
┌ API key
│
│
└ enter
```
Many OpenRouter models are preloaded by default, run the /models command to select the one you want.
```
/models
```
You can also add additional models through your anthracode config.
anthracode.jsonc
```
{

  "provider": {
    "openrouter": {
      "models": {
        "somecoolnewmodel": {}
      }
    }
  }
}
```

You can also customize them through your anthracode config. Here’s an example of specifying a provider

{

  "provider": {
    "openrouter": {
      "models": {
        "moonshotai/kimi-k2": {
          "options": {
            "provider": {
              "order": ["baseten"],
              "allow_fallbacks": false
            }
          }
        }
      }
    }
  }
}

LLM Gateway

Head over to the LLM Gateway dashboard, click Create API Key, and copy the key.
Run the /connect command and search for LLM Gateway.
```
/connect
```
Enter the API key for the provider.
```
┌ API key
│
│
└ enter
```
Many LLM Gateway models are preloaded by default, run the /models command to select the one you want.
```
/models
```
You can also add additional models through your anthracode config.
anthracode.jsonc
```
{

  "provider": {
    "llmgateway": {
      "models": {
        "somecoolnewmodel": {}
      }
    }
  }
}
```

You can also customize them through your anthracode config. Here’s an example of specifying a provider

{

  "provider": {
    "llmgateway": {
      "models": {
        "glm-4.7": {
          "name": "GLM 4.7"
        },
        "gpt-5.2": {
          "name": "GPT-5.2"
        },
        "gemini-2.5-pro": {
          "name": "Gemini 2.5 Pro"
        },
        "claude-3-5-sonnet-20241022": {
          "name": "Claude 3.5 Sonnet"
        }
      }
    }
  }
}

SAP AI Core

SAP AI Core provides access to 40+ models from OpenAI, Anthropic, Google, Amazon, Meta, Mistral, and AI21 through a unified platform.

Go to your SAP BTP Cockpit, navigate to your SAP AI Core service instance, and create a service key.

The service key is a JSON object containing clientid, clientsecret, url, and serviceurls.AI_API_URL. You can find your AI Core instance under Services > Instances and Subscriptions in the BTP Cockpit.
Run the /connect command and search for SAP AI Core.
```
/connect
```

Enter your service key JSON.

┌ Service key
│
│
└ enter

Or set the AICORE_SERVICE_KEY environment variable:

AICORE_SERVICE_KEY='{"clientid":"...","clientsecret":"...","url":"...","serviceurls":{"AI_API_URL":"..."}}' anthracode

Or add it to your bash profile:

export AICORE_SERVICE_KEY='{"clientid":"...","clientsecret":"...","url":"...","serviceurls":{"AI_API_URL":"..."}}'

Optionally set deployment ID and resource group:
Terminal window
```
AICORE_DEPLOYMENT_ID=your-deployment-id AICORE_RESOURCE_GROUP=your-resource-group anthracode
```
These settings are optional and should be configured according to your SAP AI Core setup.
Run the /models command to select from 40+ available models.
```
/models
```

STACKIT

STACKIT AI Model Serving provides fully managed sovereign hosting environment for AI models, focusing on LLMs like Llama, Mistral, and Qwen, with maximum data sovereignty on European infrastructure.

Head over to STACKIT Portal, navigate to AI Model Serving, and create an auth token for your project.

You need a STACKIT customer account, user account, and project before creating auth tokens.
Run the /connect command and search for STACKIT.
```
/connect
```
Enter your STACKIT AI Model Serving auth token.
```
┌ API key
│
│
└ enter
```
Run the /models command to select from available models like Qwen3-VL 235B or Llama 3.3 70B.
```
/models
```

OVHcloud AI Endpoints

Head over to the OVHcloud panel. Navigate to the Public Cloud section, AI & Machine Learning > AI Endpoints and in API Keys tab, click Create a new API key.
Run the /connect command and search for OVHcloud AI Endpoints.
```
/connect
```
Enter your OVHcloud AI Endpoints API key.
```
┌ API key
│
│
└ enter
```
Run the /models command to select a model like gpt-oss-120b.
```
/models
```

Scaleway

To use Scaleway Generative APIs with Anthracode:

Head over to the Scaleway Console IAM settings to generate a new API key.
Run the /connect command and search for Scaleway.
```
/connect
```
Enter your Scaleway API key.
```
┌ API key
│
│
└ enter
```
Run the /models command to select a model like devstral-2-123b-instruct-2512 or gpt-oss-120b.
```
/models
```

Together AI

Head over to the Together AI console, create an account, and click Add Key.
Run the /connect command and search for Together AI.
```
/connect
```
Enter your Together AI API key.
```
┌ API key
│
│
└ enter
```
Run the /models command to select a model like Kimi K2 Instruct.
```
/models
```

Venice AI

Head over to the Venice AI console, create an account, and generate an API key.
Run the /connect command and search for Venice AI.
```
/connect
```
Enter your Venice AI API key.
```
┌ API key
│
│
└ enter
```
Run the /models command to select a model like Llama 3.3 70B.
```
/models
```

Vercel AI Gateway

Vercel AI Gateway lets you access models from OpenAI, Anthropic, Google, xAI, and more through a unified endpoint. Models are offered at list price with no markup.

Head over to the Vercel dashboard, navigate to the AI Gateway tab, and click API keys to create a new API key.
Run the /connect command and search for Vercel AI Gateway.
```
/connect
```
Enter your Vercel AI Gateway API key.
```
┌ API key
│
│
└ enter
```
Run the /models command to select a model.
```
/models
```

You can also customize models through your anthracode config. Here’s an example of specifying provider routing order.

{

  "provider": {
    "vercel": {
      "models": {
        "anthropic/claude-sonnet-4": {
          "options": {
            "order": ["anthropic", "vertex"]
          }
        }
      }
    }
  }
}

Some useful routing options:

Option	Description
`order`	Provider sequence to try
`only`	Restrict to specific providers
`zeroDataRetention`	Only use providers with zero data retention policies

xAI

Three ways to authenticate: a SuperGrok subscription via browser OAuth, the same SuperGrok subscription via a headless device-code flow (for VPS / SSH / Docker), or a pay-as-you-go API key from the xAI console.

Run the /connect command and search for xAI.
```
/connect
```
Select xAI Grok OAuth (SuperGrok Subscription). Anthracode opens xAI’s consent screen in your browser and waits for the callback on http://127.0.0.1:56121/callback.
Run the /models command to select a Grok model.
```
/models
```

Anthracode refreshes the OAuth access token automatically. Any Grok or X Premium plan that includes Grok API access works; you do not need a separate XAI_API_KEY.

Option B — SuperGrok device-code (headless / remote server / VPS)

Use this when Anthracode is running somewhere a browser can’t reach the loopback redirect: a VPS, a remote dev box over SSH, inside Docker, in CI, etc. No callback port is opened on the host running Anthracode — instead xAI hands the CLI a short code that you type into a browser on any other device (laptop, phone, …).

Run the /connect command on the remote host and search for xAI.
```
/connect
```
Select xAI Grok OAuth (Headless / Remote / VPS). Anthracode prints a verification URL and a short user code.
```
Open https://x.ai/device on any device and enter code: ABCD-1234
```
Open the URL on a device that has a browser (your laptop or phone), enter the code, and approve the consent screen. Anthracode polls xAI’s token endpoint and stores the resulting OAuth tokens once you approve. Token refresh works the same as Option A.

Option C — API key

Head over to the xAI console, create an account, and generate an API key.
Run the /connect command and search for xAI.
```
/connect
```
Select Manually enter API Key and paste your xAI API key.
```
┌ API key
│
│
└ enter
```
Run the /models command to select a model like Grok Beta.
```
/models
```

Z.AI

Head over to the Z.AI API console, create an account, and click Create a new API key.
Run the /connect command and search for Z.AI.
```
/connect
```
If you are subscribed to the GLM Coding Plan, select Z.AI Coding Plan.
Enter your Z.AI API key.
```
┌ API key
│
│
└ enter
```
Run the /models command to select a model like GLM-4.7.
```
/models
```

ZenMux

Head over to the ZenMux dashboard, click Create API Key, and copy the key.
Run the /connect command and search for ZenMux.
```
/connect
```
Enter the API key for the provider.
```
┌ API key
│
│
└ enter
```
Many ZenMux models are preloaded by default, run the /models command to select the one you want.
```
/models
```
You can also add additional models through your anthracode config.
anthracode.jsonc
```
{

  "provider": {
    "zenmux": {
      "models": {
        "somecoolnewmodel": {}
      }
    }
  }
}
```

Custom provider

To add any OpenAI-compatible provider that’s not listed in the /connect command:

Run the /connect command and scroll down to Other.

$ /connect

┌  Add credential
│
◆  Select provider
│  ...
│  ● Other
└

Enter a unique ID for the provider.
Terminal window
```
$ /connect

┌  Add credential
│
◇  Enter provider id
│  myprovider
└
```
Choose a memorable ID, you’ll use this in your config file.

Enter your API key for the provider.

$ /connect

┌  Add credential
│
▲  This only stores a credential for myprovider - you will need to configure it in anthracode.jsonc, check the docs for examples.
│
◇  Enter your API key
│  sk-...
└

Create or update your anthracode.jsonc file in your project directory:
anthracode.jsonc
```
{

  "provider": {
    "myprovider": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "My AI ProviderDisplay Name",
      "options": {
        "baseURL": "https://api.myprovider.com/v1"
      },
      "models": {
        "my-model-name": {
          "name": "My Model Display Name"
        }
      }
    }
  }
}
```
Here are the configuration options:
- npm: AI SDK package to use, @ai-sdk/openai-compatible for OpenAI-compatible providers (for /v1/chat/completions). If your provider/model uses /v1/responses, use @ai-sdk/openai.
- name: Display name in UI.
- models: Available models.
- options.baseURL: API endpoint URL.
- options.apiKey: Optionally set the API key, if not using auth.
- options.headers: Optionally set custom headers.
More on the advanced options in the example below.
Run the /models command and your custom provider and models will appear in the selection list.

Example

Here’s an example setting the apiKey, headers, and model limit options.

{

  "provider": {
    "myprovider": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "My AI ProviderDisplay Name",
      "options": {
        "baseURL": "https://api.myprovider.com/v1",
        "apiKey": "{env:ANTHROPIC_API_KEY}",
        "headers": {
          "Authorization": "Bearer custom-token"
        }
      },
      "models": {
        "my-model-name": {
          "name": "My Model Display Name",
          "limit": {
            "context": 200000,
            "output": 65536
          }
        }
      }
    }
  }
}

Configuration details:

apiKey: Set using env variable syntax, learn more.
headers: Custom headers sent with each request.
limit.context: Maximum input tokens the model accepts.
limit.output: Maximum tokens the model can generate.

The limit fields allow Anthracode to understand how much context you have left. Standard providers pull these from models.dev automatically.

Troubleshooting

If you are having trouble with configuring a provider, check the following:

Check the auth setup: Run anthracode auth list to see if the credentials for the provider are added to your config.

This doesn’t apply to providers like Amazon Bedrock, that rely on environment variables for their auth.
For custom providers, check the anthracode config and:
- Make sure the provider ID used in the /connect command matches the ID in your anthracode config.
- The right npm package is used for the provider. For example, use @ai-sdk/cerebras for Cerebras. And for all other OpenAI-compatible providers, use @ai-sdk/openai-compatible (for /v1/chat/completions); if a model uses /v1/responses, use @ai-sdk/openai. For mixed setups under one provider, you can override per model via provider.npm.
- Check correct API endpoint is used in the options.baseURL field.