Search Get TALOS

The Archive · Desktop reference

Providers

The 29 providers TALOS Desktop knows: protocol, key, endpoint and sign-in.

Reference for TALOS Desktop 0.1.25 generated from the source of the release · released

Set keys and addresses in Settings → Model laboratory → Providers. The installed app keeps keys in the operating system’s keyring, in its own space, and never reads them from environment variables.

External agent

esterno chat

An agent installed on this computer.

Protocol
Agent Client Protocol
Key
None
Models
its catalog is read live: GET /api/v1/providers/esterno/models
First response
180 s by default

OpenAI

openai chat

OpenAI models, direct API (Responses).

Protocol
OpenAI Responses
Key
API key (Bearer)
Endpoint
https://api.openai.com/v1 · editable
Models
its catalog is read live: GET /api/v1/providers/openai/models
First response
60 s by default

DeepSeek

deepseek chat

DeepSeek models, direct API (OpenAI-compatible).

Protocol
OpenAI Chat Completions
Key
API key (Bearer)
Endpoint
https://api.deepseek.com · editable
Models
its catalog is read live: GET /api/v1/providers/deepseek/models
First response
60 s by default

Kimi

kimi chat

Kimi models, direct international connection.

Protocol
OpenAI Chat Completions
Key
API key (Bearer)
Endpoint
https://api.moonshot.ai/v1 · editable
Models
its catalog is read live: GET /api/v1/providers/kimi/models
First response
60 s by default

MiniMax

minimax chat

MiniMax models, direct international connection.

Protocol
OpenAI Chat Completions
Key
API key (Bearer)
Endpoint
https://api.minimax.io/v1 · editable
Models
its catalog is read live: GET /api/v1/providers/minimax/models
First response
60 s by default

Qwen

qwen chat

Qwen models, direct international connection.

Protocol
OpenAI Chat Completions
Key
API key (Bearer)
Endpoint
https://dashscope-intl.aliyuncs.com/compatible-mode/v1 · editable
Models
its catalog is read live: GET /api/v1/providers/qwen/models
First response
60 s by default

Z.AI

zai chat

GLM models through the Z.AI direct API.

Protocol
OpenAI Chat Completions
Key
API key (Bearer)
Endpoint
https://api.z.ai/api/paas/v4 · editable
Models
its catalog is read live: GET /api/v1/providers/zai/models
First response
60 s by default
Keys
z.ai

Anthropic

anthropic chat

Anthropic models, direct API (Messages).

Protocol
Anthropic Messages
Key
API key (header)
Endpoint
https://api.anthropic.com/v1
Models
its catalog is read live: GET /api/v1/providers/anthropic/models
First response
60 s by default

Google Gemini

gemini chat

Gemini models, direct Google AI Studio API.

Protocol
Gemini
Key
API key (query)
Endpoint
https://generativelanguage.googleapis.com/v1beta
Models
its catalog is read live: GET /api/v1/providers/gemini/models
First response
60 s by default

OpenRouter

openrouter chat

Aggregator: hundreds of models behind a single key.

Protocol
OpenAI Chat Completions
Key
API key (Bearer)
Endpoint
https://openrouter.ai/api/v1 · editable
Sign-in
in the browser, from Providers
First response
60 s by default

Ollama Local

ollama chat

Local Ollama engine on this computer.

Protocol
OpenAI Chat Completions
Key
API key (Bearer) · optional
Endpoint
http://127.0.0.1:11434 · editable
First response
60 s by default

LM Studio

lmstudio chat

Local LM Studio engine on this computer.

Protocol
OpenAI Chat Completions
Key
API key (Bearer) · optional
Endpoint
http://127.0.0.1:1234 · editable
Models
its catalog is read live: GET /api/v1/providers/lmstudio/models
First response
60 s by default

Groq

groq chat

Models through Groq.

Protocol
OpenAI Chat Completions
Key
API key (Bearer)
Endpoint
https://api.groq.com/openai/v1 · editable
Models
its catalog is read live: GET /api/v1/providers/groq/models
First response
60 s by default

Cerebras

cerebras chat

Models through Cerebras.

Protocol
OpenAI Chat Completions
Key
API key (Bearer)
Endpoint
https://api.cerebras.ai/v1 · editable
Models
its catalog is read live: GET /api/v1/providers/cerebras/models
First response
60 s by default

Mistral

mistral chat

Models through Mistral.

Protocol
OpenAI Chat Completions
Key
API key (Bearer)
Endpoint
https://api.mistral.ai/v1 · editable
Models
its catalog is read live: GET /api/v1/providers/mistral/models
First response
60 s by default

Together

together chat

Models through Together.

Protocol
OpenAI Chat Completions
Key
API key (Bearer)
Endpoint
https://api.together.ai/v1 · editable
Models
its catalog is read live: GET /api/v1/providers/together/models
First response
60 s by default

Fireworks

fireworks chat

Models through Fireworks.

Protocol
OpenAI Chat Completions
Key
API key (Bearer)
Endpoint
https://api.fireworks.ai/inference/v1 · editable
Models
its catalog is read live: GET /api/v1/providers/fireworks/models
First response
60 s by default

DeepInfra

deepinfra chat

Models through DeepInfra.

Protocol
OpenAI Chat Completions
Key
API key (Bearer)
Endpoint
https://api.deepinfra.com/v1/openai · editable
Models
its catalog is read live: GET /api/v1/providers/deepinfra/models
First response
60 s by default

Novita

novita chat

Models through Novita.

Protocol
OpenAI Chat Completions
Key
API key (Bearer)
Endpoint
https://api.novita.ai/openai/v1 · editable
Models
its catalog is read live: GET /api/v1/providers/novita/models
First response
60 s by default

Nebius

nebius chat

Models through Nebius.

Protocol
OpenAI Chat Completions
Key
API key (Bearer)
Endpoint
https://api.tokenfactory.nebius.com/v1 · editable
Models
its catalog is read live: GET /api/v1/providers/nebius/models
First response
60 s by default

xAI

xai chat

Models through xAI.

Protocol
OpenAI Chat Completions
Key
API key (Bearer)
Endpoint
https://api.x.ai/v1 · editable
Models
its catalog is read live: GET /api/v1/providers/xai/models
First response
60 s by default

Ollama Cloud

ollama-cloud chat

Models through Ollama Cloud.

Protocol
OpenAI Chat Completions
Key
API key (Bearer)
Endpoint
https://ollama.com/v1 · editable
Models
its catalog is read live: GET /api/v1/providers/ollama-cloud/models
First response
60 s by default

Hugging Face

huggingface chat

Hugging Face model inference, catalog and downloads.

Protocol
OpenAI Chat Completions
Key
API key (Bearer)
Endpoint
https://router.huggingface.co/v1 · editable
Models
its catalog is read live: GET /api/v1/providers/huggingface/models
First response
60 s by default

Z.AI (Anthropic endpoint)

zai-anthropic chat

GLM models through the Z.AI coding plan endpoint.

Protocol
Anthropic Messages
Key
API key (Bearer)
Endpoint
https://api.z.ai/api/anthropic/v1 · editable
Models
its catalog is read live: GET /api/v1/providers/zai-anthropic/models
First response
60 s by default
Keys
z.ai

MiniMax (Anthropic endpoint)

minimax-anthropic chat

MiniMax models through the Anthropic-compatible endpoint (international access).

Protocol
Anthropic Messages
Key
API key (header)
Endpoint
https://api.minimax.io/anthropic/v1 · editable
Models
its catalog is read live: GET /api/v1/providers/minimax-anthropic/models
First response
60 s by default

Azure AI Foundry

azure chat

Models from your own Azure resource.

Protocol
OpenAI Chat Completions
Key
API key (header)
Endpoint
yours, set in Providers
Models
its catalog is read live: GET /api/v1/providers/azure/models
First response
60 s by default

Amazon Bedrock

bedrock chat

Models available in the chosen region.

Protocol
OpenAI Chat Completions
Key
API key (Bearer)
Endpoint
yours, set in Providers
Models
its catalog is read live: GET /api/v1/providers/bedrock/models
First response
60 s by default

Google Vertex AI

vertex chat

Models of the chosen project and region.

Protocol
OpenAI Chat Completions
Key
API key (Bearer)
Endpoint
yours, set in Providers
Models
its catalog is read live: GET /api/v1/providers/vertex/models
First response
60 s by default

Local engine (llama.cpp)

local chat

The llama-server supervisor of this computer.

Protocol
llama.cpp server
Key
None (local)
First response
60 s by default

Type to search the guides.