Provider & Models List
Tarsk supports a large and growing number of model providers. Each provider requires its own API key (or token for some). You can enable multiple providers simultaneously and switch between models per thread.
Direct Providers
Section titled “Direct Providers”These providers host their own models. Bring an API key from the provider’s website.
Anthropic
Section titled “Anthropic”Models: Claude Opus 5, Claude Sonnet 5, Claude Fable 5.1, Claude Opus 4.8, Claude Haiku 4.5 Get a key: console.anthropic.com
Claude models excel at coding, reasoning, and following complex instructions.
OpenAI
Section titled “OpenAI”Models: GPT-6 Astra, GPT-5.6, GPT-5.5 Pro, GPT-5.4 mini, Codex series Get a key: platform.openai.com
Models: Gemini 3.8 Flash, Gemini 3.6 Flash, Gemini 3.5 Flash Lite, Gemini 3.1 Pro Preview, Gemma 4 Get a key: aistudio.google.com
Gemini 3.8 Flash is a fast, cost-effective option with a large context window.
Models: Grok 4.6, Grok 4.5, Grok 4.3, Grok Build 0.1, Grok 4.20 Get a key: console.x.ai
DeepSeek
Section titled “DeepSeek”Models: DeepSeek V4 Pro, DeepSeek V4 Flash Get a key: platform.deepseek.com
DeepSeek V4 Pro is a strong reasoning model. DeepSeek V4 Flash trades some depth for speed and cost.
Mistral
Section titled “Mistral”Models: Devstral 2, Mistral Medium 3.5, Mistral Small 4, Mistral Large 3, Codestral Get a key: console.mistral.ai
Devstral is Mistral’s code-focused model family. Codestral targets code completion and generation.
Perplexity
Section titled “Perplexity”Models: Sonar Pro, Sonar Reasoning Pro, Sonar Deep Research Get a key: perplexity.ai
Sonar models are augmented with live web search.
Cohere
Section titled “Cohere”Models: North Mini Code, Command A Plus, Command A Reasoning, Command A, Command R+ Get a key: dashboard.cohere.com
Models: Qwen3.8 27B, Qwen3.6 27B, Compound, GPT OSS 120B, GPT OSS 20B Get a key: console.groq.com
Groq provides very fast inference via custom hardware.
Cerebras
Section titled “Cerebras”Models: Qwen3.8 27B, GPT OSS 120B Get a key: cloud.cerebras.ai
Moonshot AI
Section titled “Moonshot AI”Models: Kimi K3, Kimi K2.7 Code, Kimi K2.6
Variants: moonshotai (international), moonshotai-cn (China endpoint)
Get a key: platform.moonshot.ai
MiniMax
Section titled “MiniMax”Models: MiniMax-M3, MiniMax-M2.7, MiniMax-M2.5
Variants: minimax (international), minimax-cn (China endpoint)
Get a key: platform.minimax.io
Zhipu AI / Z.AI
Section titled “Zhipu AI / Z.AI”Models: GLM-5.3, GLM-5.2, GLM-5V-Turbo, GLM-5
Variants: zhipuai, zai
Get a key: bigmodel.cn
Alibaba
Section titled “Alibaba”Models: Qwen3.8 Max, Qwen3.8 Flash, Qwen3.7 Max, Qwen3 Coder Plus, Qwen3 Coder Flash Get a key: dashscope.aliyuncs.com
NVIDIA
Section titled “NVIDIA”Models: Nemotron 3 series, DeepSeek V4 Pro, Kimi K3, Qwen3.5 397B, Mistral Large 3, GLM-5.2 Get a key: build.nvidia.com
Hugging Face
Section titled “Hugging Face”Models: GLM-5.3, Qwen3.8, DeepSeek V4 Pro, Kimi K3, MiniMax-M3 Get a key: huggingface.co/settings/tokens
Aggregator Providers
Section titled “Aggregator Providers”Aggregators route requests to multiple underlying models through a single API key. They are useful for accessing many models without managing separate keys.
OpenRouter
Section titled “OpenRouter”Models: Hundreds of models from Anthropic, OpenAI, Google, xAI, Meta, Mistral, and more Get a key: openrouter.ai Credits: Balance visible in Settings
OpenRouter is the most comprehensive aggregator. A single key accesses almost every major model. Some models are free; paid models are charged per-token.
AIHubMix
Section titled “AIHubMix”Models: Claude, GPT, Gemini, DeepSeek, Kimi, GLM, Qwen, Grok via a single API Get a key: aihubmix.com Credits: Balance visible in Settings
SiliconFlow
Section titled “SiliconFlow”Models: Qwen, DeepSeek, Kimi, GLM, MiniMax, Llama
Variants: siliconflow (international), siliconflow-cn (China endpoint)
Get a key: cloud.siliconflow.com
Models: DeepSeek, Kimi, Qwen, GLM Get a key: platform.iflow.cn
ModelScope
Section titled “ModelScope”Models: Qwen, GLM Get a key: modelscope.cn
Together AI
Section titled “Together AI”Models: GLM, MiniMax, DeepSeek, Kimi, Qwen, Llama, GPT OSS Get a key: api.together.ai
Fireworks AI
Section titled “Fireworks AI”Models: Kimi, GLM, DeepSeek, MiniMax, GPT OSS Get a key: fireworks.ai
Deep Infra
Section titled “Deep Infra”Models: GLM, MiniMax, DeepSeek, Kimi, Qwen, Gemma, Llama, GPT OSS Get a key: deepinfra.com
NovitaAI
Section titled “NovitaAI”Models: GLM, MiniMax, DeepSeek, Kimi, ERNIE, Qwen, Llama, GPT OSS Get a key: novita.ai
Nebius
Section titled “Nebius”Models: GLM, MiniMax, DeepSeek, Kimi, Qwen, Gemma, Hermes, Nemotron, GPT OSS Get a key: tokenfactory.nebius.com
ZenMux
Section titled “ZenMux”Models: Multi-provider aggregator — DeepSeek, Kimi, GLM, Qwen, Grok, GPT, Claude, Gemini, MiniMax Get a key: zenmux.ai
OpenCode
Section titled “OpenCode”Models: Multi-provider aggregator — Claude, GPT, Gemini, Kimi, GLM, MiniMax, Qwen, Grok Get a key: opencode.ai
Models: Claude, GPT, Gemini, Grok, GLM, Kimi, MiniMax (via Poe subscription) Get a key: poe.com
Cloud Platforms
Section titled “Cloud Platforms”These providers give you access to foundation models through your existing cloud account.
Models: GPT-6 Astra, GPT-5.6, Claude Opus 5, Grok 4.6, Mistral Medium, Phi, DeepSeek V4, Kimi, Llama
Auth: AZURE_RESOURCE_NAME + AZURE_API_KEY
Docs: learn.microsoft.com/en-us/azure/ai-services/openai
Google Vertex
Section titled “Google Vertex”Models: Gemini 3.8 Flash, Gemini 3.1 Pro Preview, Claude, DeepSeek, GLM, Qwen, Llama, GPT OSS
Auth: GOOGLE_VERTEX_PROJECT + GOOGLE_VERTEX_LOCATION + GOOGLE_APPLICATION_CREDENTIALS
Docs: cloud.google.com/vertex-ai
Amazon Bedrock
Section titled “Amazon Bedrock”Models: Claude, GPT, Nova, Llama, Mistral, DeepSeek, Kimi, Qwen, MiniMax, GLM, Grok, NVIDIA Nemotron
Auth: AWS_ACCESS_KEY_ID + AWS_SECRET_ACCESS_KEY + AWS_REGION
Docs: docs.aws.amazon.com/bedrock
Token Providers
Section titled “Token Providers”These providers use a personal access token rather than a separate API key.
GitHub Copilot
Section titled “GitHub Copilot”Models: GPT-6 Astra, Claude Fable 5.1, Gemini 3.8 Flash, Grok 4.6, MAI-Code-1.1-Flash
Auth: Paste a GitHub access token (GITHUB_TOKEN) in Settings → Providers
GitLab Duo
Section titled “GitLab Duo”Models: Agentic Chat on Claude and GPT models
Auth: GITLAB_TOKEN
Docs: docs.gitlab.com/ee/user/gitlab_duo
Local Providers
Section titled “Local Providers”Run models on your own hardware.
LM Studio
Section titled “LM Studio”Models: Local models you download (Qwen3, GPT OSS, and more)
Auth: LMSTUDIO_API_KEY
Docs: lmstudio.ai
Ollama Cloud
Section titled “Ollama Cloud”Models: Cloud-hosted Kimi, GLM, Qwen, Gemma, DeepSeek, MiniMax, and Nemotron models
Auth: OLLAMA_API_KEY
Docs: docs.ollama.com/cloud
Specialised Providers
Section titled “Specialised Providers”| Provider | Models | Notes |
|---|---|---|
zai-coding-plan | GLM-5.3, GLM-5.2, GLM-5-Turbo | Z.AI planning-focused variants |
zhipuai-coding-plan | GLM-5.3, GLM-5.2, GLM-5V-Turbo | Zhipu AI coding + planning split |
kimi-for-coding | Kimi K3, Kimi K2.7 Code | Kimi specialised coding mode |