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 4.6, Claude Sonnet 4.6, Claude Sonnet 4.5, 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-5, GPT-4.1, GPT-4.1 mini, o3, o3-pro, o4-mini, Codex series Get a key: platform.openai.com
Models: Gemini 3.1 Pro Preview, Gemini 3 Pro Preview, Gemini 2.5 Pro, Gemini 2.5 Flash, Gemini 2.5 Flash Lite Get a key: aistudio.google.com
Gemini 2.5 Flash is a fast, cost-effective option with a large context window.
Models: Grok 4, Grok 4.1 Fast, Grok 3, Grok Code Fast 1 Get a key: console.x.ai
DeepSeek
Section titled “DeepSeek”Models: DeepSeek Reasoner (R1), DeepSeek Chat (V3) Get a key: platform.deepseek.com
DeepSeek R1 is a strong reasoning model. DeepSeek V3 is competitive with frontier models for coding tasks.
Mistral
Section titled “Mistral”Models: Devstral Medium, Magistral Medium, Mistral Large 3, Mistral Small 3.2, 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: Command A, Command A Reasoning, Command R+, Command R Get a key: dashboard.cohere.com
Models: Llama 4 Scout 17B, Llama 4 Maverick 17B, Kimi K2 Instruct, GPT OSS 120B, Qwen3 32B Get a key: console.groq.com
Groq provides very fast inference via custom hardware.
Cerebras
Section titled “Cerebras”Models: Qwen 3 235B Instruct, GPT OSS 120B, Llama 3.1 8B, Z.AI GLM-4.7 Get a key: cloud.cerebras.ai
Moonshot AI
Section titled “Moonshot AI”Models: Kimi K2.5, Kimi K2 Thinking, Kimi K2 Turbo
Variants: moonshotai (international), moonshotai-cn (China endpoint)
Get a key: platform.moonshot.ai
MiniMax
Section titled “MiniMax”Models: MiniMax-M2.5, MiniMax-M2.1, MiniMax-M2
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, GLM-4.7, GLM-4.6, GLM-4.5
Variants: zhipuai, zai
Get a key: bigmodel.cn
Alibaba
Section titled “Alibaba”Models: Qwen3 Coder 480B, Qwen3.5 397B, Qwen3 235B, Qwen Max, Qwen3 Coder Flash Get a key: dashscope.aliyuncs.com
NVIDIA
Section titled “NVIDIA”Models: Nemotron series, Phi series, DeepSeek V3.x, Kimi K2, Qwen3 Coder 480B, GLM-4.7 Get a key: build.nvidia.com
Hugging Face
Section titled “Hugging Face”Models: GLM-5, GLM-4.7, MiMo-V2-Flash, MiniMax-M2.5, DeepSeek-R1, Kimi K2, Qwen3 Coder 480B 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-5, Gemini, DeepSeek, Kimi, GLM, Qwen 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, DeepSeek 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, Llama, Qwen, Claude, 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, Llama, Gemma, Hermes, INTELLECT 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-5, GPT-4.1, o3, o4-mini, Grok 4, Claude, Mistral, Phi, DeepSeek, 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 Pro Preview, Gemini 2.5 Pro, Gemini 2.5 Flash, 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, Llama, Mistral, DeepSeek, Kimi, Qwen, MiniMax, GLM, NVIDIA Nemotron, Nova
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: Claude Opus 4.6, Claude Sonnet 4.6, GPT-5, Gemini 3 Pro Preview, Grok Code Fast 1 Auth: Connect via your GitHub account — no separate API key needed if you have a Copilot subscription
GitHub Models
Section titled “GitHub Models”Models: Phi-4, AI21 Jamba, Llama, Mistral and more (preview access)
Auth: GITHUB_TOKEN
Docs: github.com/marketplace/models
GitLab Duo
Section titled “GitLab Duo”Models: Claude Opus 4.6, Claude Sonnet 4.5, Claude Haiku 4.5, GPT-5, GPT-5 Mini
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 Ollama models — Kimi K2, GLM, Qwen3, Gemma, DeepSeek, MiniMax
Auth: OLLAMA_API_KEY
Docs: docs.ollama.com/cloud
Specialised Providers
Section titled “Specialised Providers”| Provider | Models | Notes |
|---|---|---|
zai-coding-plan | GLM-5, GLM-4.7-FlashX, GLM-4.5 | Z.AI planning-focused variants |
zhipuai-coding-plan | GLM-5, GLM-4.7, GLM-4.6, GLM-4.5 | Zhipu AI coding + planning split |
kimi-for-coding | Kimi K2.5, Kimi K2 Thinking | Kimi specialised coding mode |