More Providers

OpenAI-compatible language model providers for GitHub Copilot Chat.

Adds 311 model providers to VS Code's Copilot Chat. Just enter your API key and start chatting.

Providers

Major Providers (17)

Anthropic anthropic
Cerebras cerebras
Cohere cohere
DeepInfra deepinfra
DeepSeek deepseek
Fireworks AI fireworks
GitHub Models github-models
Google AI google
Groq groq
Hugging Face Inference huggingface
Mistral mistral
NVIDIA API Catalog nvidia
OpenRouter openrouter
Perplexity perplexity
Replicate replicate
Together AI together
xAI xai

Chinese / APAC (48)

01.AI (Yi) zeroone
Alibaba alibaba
Alibaba Coding Plan alibaba-coding-plan
Alibaba Coding Plan (China) alibaba-coding-plan-cn
Alibaba DashScope (Qwen) dashscope
Alibaba Token Plan alibaba-token-plan
Alibaba Token Plan (China) alibaba-token-plan-cn
AMD amd
APIYI apiyi
Baichuan AI baichuan
Baidu Qianfan baidu-qianfan
Baidu Qianfan AI baidu-qianfan-ai
Bailing bailing
Byteplus ModelArk byteplus
iFlow iflowcn
Kimi kimi
Kimi (CN) kimi-cn
Kimi For Coding kimi-for-coding
Kimi For Coding (kimi.ai) kimi-code-plan-global
MiniMax minimax
MiniMax (CN) minimax-cn
MiniMax Token Plan (minimax.io) minimax-coding-plan
MiniMax Token Plan (minimaxi.com) minimax-cn-coding-plan
Moark moark
ModelScope modelscope
SCNet Token Plan scnet-token-plan
SenseNova sensenova
SiliconFlow siliconflow
SiliconFlow (China) siliconflow-cn
StepFun stepfun
StepFun (Global) stepfun-ai
StepFun Step Plan (China) stepfun-step-plan
StepFun Step Plan (Global) stepfun-ai-step-plan
Tencent Cloud Hunyuan tencent-cloud
Tencent Coding Plan (China) tencent-coding-plan
Tencent Token Plan tencent-token-plan
Tencent TokenHub tencent-tokenhub
Vispark vispark
Volcengine (Doubao / Ark) volcengine
Volcengine Ark Coding Plan volcengine-coding-plan
Xiaomi xiaomi
Xiaomi MiMo xiaomi-mimo
Xiaomi Token Plan (China) xiaomi-token-plan-cn
Xiaomi Token Plan (Europe) xiaomi-token-plan-ams
Xiaomi Token Plan (Singapore) xiaomi-token-plan-sgp
Z.ai z-ai
Z.ai (CN) z-ai-cn
Zhipu AI Coding Plan zhipuai-coding-plan

Cloud / Hosted (141)

302.AI 302ai
Abacus abacus
abliteration.ai abliteration-ai
above.dev above
Agnes AI agnes
ai& aiand
AI-ROUTER ai-router
ainetcafe ainetcafe
Aixy aixy
AKI.IO aki-io
Ambient ambient
Any-LLM Control Plane any-llm
AnyAPI anyapi
Apertis AI apexit
Arcee arcee
Auriko auriko
B.AI b-ai
Baseten (Model APIs) baseten
Bee by HEOSSI bee
Berget.AI berget
Blue Claw blueclaw
Bothub bothub
Charm Hyper hyper
Claudinio claudinio
ClinePass cline-pass
CloudFerro Sherlock cloudferro-sherlock
CoralBricks coralbricks
Cortecs cortecs
CrofAI crof
CrossModel crossmodel
Crusoe crusoe
D.Run (China) drun
DaoXE daoxe
DigitalOcean digitalocean
DInference dinference
EBCloud ebcloud
Echo echo
engy engy
evroc evroc
Fal.ai fal
FastRouter fastrouter
FreeModel freemodel
FrogBot frogbot
GitHub Copilot github-copilot
GMI Cloud gmi-cloud
GreenPT greenpt
Hetzner hetzner
HPC-AI hpc-ai
Hyperbolic AI hyperbolic
Impossibl impossibl
Inception AI inception
Inceptron inceptron
Inco inco
Infer by Flow7 infer
Inference inference
InferX inferx
Infomaniak infomaniak
IO.NET io-net
IteraCompute iteracompute
Jalapeno Cloud jalapeno
Jiekou.AI jiekou
Kenari kenari
klokintegration.se klokintegration
Kluster AI kluster-ai
Kosmik Compute kosmik
KUAE Cloud Coding Plan kuae-cloud-coding-plan
Lambda AI lambda-ai
Lepton AI lepton
Lilac lilac
LLM Tech llmtech
LLMTR llmtr
Logfare logfare
LongCat longcat
LucidQuery lucidquery
Meganova meganova
Melious melious
Meta meta
Mix (B.AI) mix-b-ai
Mixlayer mixlayer
Modal modal
Model Oracle AI model-oracle-ai
Modelis modelis
NaN nan
NanoGPT nanogpt
NEAR AI Cloud near-ai
Nebius Token Factory nebius
Nebula (B.AI) nebula-b-ai
Neon neon
NeoSmith neosmith
Neuralwatt neuralwatt
Nova nova
Novita AI novita
Novita AI novita-ai
Ofox ofox
OL Station (B.AI) ol-station-b-ai
Ollama Cloud ollama-cloud
OpenCode Go opencode-go
OpenCode Zen opencode
OpenReason openreason
Opper opper
OrcaRouter orcarouter
Pareto Inference pareto
Pendra pendra
Perplexity Agent perplexity-agent
Pioneer pioneer
QiHang qihang-ai
Qiniu qiniu-ai
Regolo AI regolo-ai
routing.run routing-run
RunInfra runinfra
Sakana AI sakana
SambaNova Cloud sambanova
SCX.ai scx
STACKIT stackit
Standard Compute standardcompute
Subconscious subconscious
submodel submodel
Synthetic synthetic
T-Systems LLMhub llmhub
Tempr Gateway tempr
TensorX tensorx
The Grid AI the-grid-ai
Thinking Machines thinkingmachines
Tinfoil tinfoil
TokenGo tokengo
TrustedRouter trustedrouter
Umans AI umans-ai
Umans AI Coding Plan umans-ai-coding-plan
UnoRouter unorouter
Upstage AI upstage
Vancine vancine
Vercel v0 v0
Vivgrid vivgrid
Vultr vultr
Wafer wafer.ai
Wallaby wallaby
Xpersona xpersona
Z.AI Coding Plan zai-coding-plan
Zeldoc zeldoc
Zenifra zenifra
ZenMux zenmux

Enterprise / Cloud Platforms (12)

Aleph Alpha aleph-alpha
Amazon Bedrock aws-bedrock
Amazon Bedrock (Mantle) aws-bedrock-mantle
Azure AI Foundry azure-foundry
Azure OpenAI azure-openai
Cloudflare Workers AI cloudflare-workers-ai
Databricks Model Serving databricks
Google Cloud Vertex AI gcp-vertex
IBM watsonx.ai ibm-watsonx
OCI Generative AI oci
Oracle Cloud Infrastructure GenAI oracle-oci
Snowflake Cortex snowflake-cortex

Proxy / Gateway (17)

AgentRouter agentrouter
AI Badgr aibadgr
Braintrust Gateway braintrust
Eden AI edenai
Helicone helicone
Kilo Gateway kilo-gateway
LLM Gateway llmgateway
LowRouter lowrouter
Martian martian
Merge Gateway merge-gateway
OpenAI Compatible (Custom Endpoint) openai-compatible
Orq.ai orq
Portkey portkey
Requesty requesty
TokenRouter tokenrouter
Vercel AI Gateway vercel
WaveSpeed LLM wavespeed

Local / Self-Hosted (26)

Aphrodite Engine aphrodite
Atomic Chat atomic-chat
GPT4All gpt4all
Jan (Local) jan
KoboldCPP koboldcpp
Lemonade Server lemonade
LiteLLM Proxy litellm-proxy
llama.cpp / llama-server llama-cpp
Llamafile llamafile
LM Studio (Local) lm-studio
LocalAI localai
lucky-cat-api lucky-cat-api
Lynkr lynkr
New API new-api
Ollama ollama
One API one-api
Petals petals
pointy-arrow-api pointy-arrow-api
Privatemode AI privatemode-ai
radio-house-api radio-house-api
SGLang sglang
Tabby Coding Assistant tabby
Text Generation Inference (TGI) tgi
Triton Inference Server triton-inference
vLLM vllm
Xinference xinference

Specialized / Other (50)

AI/ML API aiml-api
AI21 Labs ai21
Anyscale Endpoints anyscale
Bifrost AI bifrost
Black Forest Labs bfl
Bytez bytez
Chutes AI chutes
Clarifai clarifai
Comet API comet-api
CompactifAI compactifai
CoreWeave wandb
DataRobot datarobot
Decart AI decart
Deepgram (Text) deepgram
ElevenLabs (Text) elevenlabs
EmpirioLabs AI empiriolabs
Featherless AI featherless
FriendliAI friendli
Galadriel galadriel
Gradient AI gradientai
Heroku AI heroku
Jina AI jina
LaoZhang API laozhang
Llama API llama-api
LlamaGate llamagate
Manus AI manus
ModelsLab modelslab
Morph Chat morph
NLP Cloud nlp-cloud
Nscale nscale
OVHcloud AI Endpoints ovhcloud
Poe poe
Poolside poolside
Predibase predibase
PublicAI publicai
Recraft recraft
RunwayML runwayml
Sarvam AI sarvam
Scaleway Generative APIs scaleway
ShareAI shareai
Spheron Network spheron
Stability AI stability-ai
Telnyx Inference telnyx
TensorMesh tensormesh
Topaz AI topaz
Unify AI unify-ai
Venice.ai venice
Voyage AI voyage
Weights & Biases Inference wandb-inference
Writer API writer

Getting Started

Open VS Code and install the extension.
Open Copilot Chat and click the model picker.
Choose a provider (e.g. "Groq" or "DeepSeek").
Enter your API key when prompted.
Models are fetched automatically from the provider's API.

Run More Providers: Open Settings from the Command Palette (Ctrl+Shift+P) to configure base URLs, per-provider and per-model API modes (Chat Completions or Responses), per-model reasoning effort, display names, context lengths, and tool/vision capabilities.

Run More Providers: Refresh Model Info Cache to refresh cached model metadata.

A provider's base URL can be overridden from More Providers: Open Settings or VS Code settings (moreproviders.<provider>.apiBaseUrl).

License

MIT

More Providers: 311 OpenAI-Compatible Providers for GitHub Copilot

khrotu

More Providers

Providers

Getting Started

License