Skip to main content

​
Supported Providers

The Igris LLM Gateway supports 59 providers out of the box. Each is accessible through the same unified API — no code changes needed to switch between them. Add a provider by creating a virtual key in the dashboard and selecting from the list below. The slug column is what you use in the virtual key type selector and in model strings (@vk_<your-slug>/<model-name>).

​
OpenAI-compatible providers

These providers expose an OpenAI-compatible /v1/chat/completions endpoint. The gateway passes requests through with minimal transformation — just credential injection and streaming normalization.
SlugNameBase URLAuthEndpoints
openaiOpenAIhttps://api.openai.com/v1bearerchat.completions, embeddings, images.generate, audio.transcriptions, audio.speech
groqGroqhttps://api.groq.com/openai/v1bearerchat.completions
mistral-aiMistral AIhttps://api.mistral.ai/v1bearerchat.completions, embeddings
deepseekDeepSeekhttps://api.deepseek.com/v1bearerchat.completions
cerebrasCerebrashttps://api.cerebras.ai/v1bearerchat.completions
sambanovaSambaNovahttps://api.sambanova.ai/v1bearerchat.completions
together-aiTogether AIhttps://api.together.xyz/v1bearerchat.completions, embeddings
fireworks-aiFireworks AIhttps://api.fireworks.ai/inference/v1bearerchat.completions, embeddings
perplexity-aiPerplexityhttps://api.perplexity.aibearerchat.completions
x-aixAIhttps://api.x.ai/v1bearerchat.completions
anyscaleAnyscalehttps://api.endpoints.anyscale.com/v1bearerchat.completions, embeddings
deepinfraDeepInfrahttps://api.deepinfra.com/v1/openaibearerchat.completions, embeddings
openrouterOpenRouterhttps://openrouter.ai/api/v1bearerchat.completions, embeddings
nebiusNebius AI Studiohttps://api.studio.nebius.ai/v1bearerchat.completions, embeddings
lambdaLambdahttps://api.lambdalabs.com/v1bearerchat.completions
dashscopeAlibaba DashScopehttps://dashscope-intl.aliyuncs.com/compatible-mode/v1bearerchat.completions, embeddings
hyperbolicHyperbolichttps://api.hyperbolic.xyz/v1bearerchat.completions
moonshotMoonshot AIhttps://api.moonshot.cn/v1bearerchat.completions
novita-aiNovita AIhttps://api.novita.ai/v3/openaibearerchat.completions
upstageUpstagehttps://api.upstage.ai/v1/solarbearerchat.completions, embeddings
siliconflowSiliconFlowhttps://api.siliconflow.cn/v1bearerchat.completions, embeddings
lingyi01.AI (Lingyi)https://api.lingyiwanwu.com/v1bearerchat.completions
inference-netInference.nethttps://api.inference.net/v1bearerchat.completions
leptonLepton AIhttps://api.lepton.run/api/v1bearerchat.completions
kluster-aiKluster AIhttps://api.kluster.ai/v1bearerchat.completions
nscaleNscalehttps://inference.api.nscale.com/v1bearerchat.completions
featherless-aiFeatherless AIhttps://api.featherless.ai/v1bearerchat.completions
bytezBytezhttps://api.bytez.com/v1bearerchat.completions
krutrimKrutrimhttps://cloud.olakrutrim.com/v1bearerchat.completions
302ai302.AIhttps://api.302.ai/v1bearerchat.completions
cometapiCometAPIhttps://api.cometapi.com/v1bearerchat.completions
matteraiMatterAIhttps://api.matterai.so/v1bearerchat.completions
nextbitNextbithttps://api.nextbit.io/v1bearerchat.completions
z-aiZ.AIhttps://api.z.ai/api/paas/v4bearerchat.completions
iointelligenceIO Intelligencehttps://api.intelligence.io.solutions/api/v1bearerchat.completions
aibadgrAIBadgrhttps://api.aibadgr.com/v1bearerchat.completions
ovhcloudOVHcloud AI Endpointshttps://oai.endpoints.kepler.ai.cloud.ovh.net/v1bearerchat.completions
predibasePredibasehttps://serving.app.predibase.com/v1bearerchat.completions
monsterapiMonsterAPIhttps://llm.monsterapi.ai/v1bearerchat.completions
deepbricksDeepbrickshttps://api.deepbricks.ai/v1bearerchat.completions
lemonfox-aiLemonfox AIhttps://api.lemonfox.ai/v1bearerchat.completions

​
Providers with divergent APIs

These providers have non-OpenAI APIs. The gateway handles request/response transformation internally.
SlugNameBase URLAuthEndpoints
anthropicAnthropichttps://api.anthropic.com/v1x-api-keychat.completions
googleGoogle Geminihttps://generativelanguage.googleapis.comquery-paramchat.completions, embeddings
cohereCoherehttps://api.cohere.com/v1bearerchat.completions, embeddings
ai21AI21 Labshttps://api.ai21.com/studio/v1bearerchat.completions
reka-aiReka AIhttps://api.reka.ai/v1bearerchat.completions
zhipuZhipu AIhttps://open.bigmodel.cn/api/paas/v4bearerchat.completions, embeddings
Notes:
  • Anthropic uses x-api-key header (not Bearer). The gateway injects this automatically.
  • Google authenticates via ?key=<API_KEY> query param, appended by the gateway. Use igris.chat.completions.create({ model: "@vk_google/gemini-2.0-flash", ... }) or raw HTTP. The Google subpath adapter (@igris-security/sdk/adapters/google) returns connection config for manual wiring since the official SDK doesn’t expose a unified baseURL override.
  • Cohere and AI21 speak their own chat API formats. The gateway translates OpenAI chat completions requests to their native format transparently.

​
Embeddings-only providers

SlugNameBase URLAuthEndpoints
voyageVoyage AIhttps://api.voyageai.com/v1bearerembeddings
jinaJina AIhttps://api.jina.ai/v1bearerembeddings
nomicNomichttps://api-atlas.nomic.ai/v1bearerembeddings

​
Passthrough / image / 3D providers

These providers use the passthrough endpoint — the gateway forwards the raw request body without transformation. Use them for image generation, 3D model generation, or any non-chat workload.
SlugNameBase URLAuthEndpoints
stability-aiStability AIhttps://api.stability.aibearerimages.generate, passthrough
segmindSegmindhttps://api.segmind.com/v1bearerimages.generate, passthrough
recraft-aiRecraft AIhttps://external.api.recraft.ai/v1bearerimages.generate, passthrough
tripo3dTripo3Dhttps://api.tripo3d.ai/v2bearerpassthrough
meshyMeshyhttps://api.meshy.ai/v2bearerpassthrough

​
Self-hosted providers

These providers require you to supply a customBaseUrl on the virtual key. The gateway will reject requests if customBaseUrl is not set.
SlugNameAuthEndpoints
ollamaOllamabearerchat.completions, embeddings
huggingfaceHuggingFace Inferencebearerchat.completions, embeddings, passthrough
tritonNVIDIA Tritonbearerchat.completions, passthrough
modalModalbearerchat.completions, passthrough
For Ollama running locally: 
// Virtual key dashboard: set customBaseUrl to http://localhost:11434
await igris.chat.completions.create({
	model: "@vk_ollama_local/llama3.2",
	messages: [{ role: "user", content: "Hello" }],
});

​
Adding a new provider

Providers are code-only — adding one requires a PR to packages/proxy/src/llm-providers/. See the provider README for the implementation template.

​
Requesting a provider

Open an issue at github.com/cybertron288/igris/issues with the provider name, API docs URL, and auth style.