Skip to main content

Providers

The AI Gateway supports 16 AI providers with 213 certified models. All providers use a unified API interface.

Provider Summary​

ProviderModelsCapabilities
OpenAI45Chat, Embeddings, TTS, STT, Images
Anthropic9Chat with Vision
Google (Gemini)41Chat, Embeddings, TTS, Images, Video
Mistral54Chat, Embeddings, STT, Moderation
Cohere16Chat, Embeddings, Reranking
Grok (xAI)10Chat, Images
DeepSeek2Chat, Reasoning
Groq-Fast inference (uses certified models)
ElevenLabs12TTS, Music, Sound Effects
Mubert-Music Generation
Stability AI1Image Generation
Black Forest Labs11Image Generation (FLUX)
Runway10Video Generation
Luma AI2Video Generation
Custom/vLLM-Self-hosted models via vLLM
Kubernetes-Self-hosted models on Kubernetes

OpenAI​

Industry-leading models for chat, embeddings, audio, and image generation.

Capabilities: Chat, Embeddings, Text-to-Speech, Speech-to-Text, Image Generation

ModelTypeBest For
openai/gpt-4oChatGeneral-purpose, vision, function calling
openai/gpt-4o-miniChatFast, cost-effective tasks
openai/o1ChatComplex reasoning tasks
openai/text-embedding-3-largeEmbeddingHigh-quality embeddings
openai/tts-1-hdTTSHigh-quality speech synthesis
openai/whisper-1STTAudio transcription
openai/dall-e-3ImageHigh-quality image generation

Anthropic​

Claude models with excellent reasoning, coding, and long-context capabilities.

Capabilities: Chat with Vision, Function Calling

ModelTypeBest For
anthropic/claude-sonnet-4-20250514ChatBalanced performance and speed
anthropic/claude-opus-4-20250514ChatMost capable, complex tasks
anthropic/claude-3-5-sonnet-latestChatPrevious generation, still excellent
anthropic/claude-3-5-haiku-latestChatFast, simple tasks

Google (Gemini)​

Multimodal models with massive context windows and diverse capabilities.

Capabilities: Chat, Embeddings, TTS, Image Generation, Video Generation

ModelTypeBest For
gemini/gemini-2.0-flashChatFast multimodal processing
gemini/gemini-1.5-proChat2M context window
gemini/gemini-1.5-flashChatFast, cost-effective
gemini/text-embedding-004EmbeddingText embeddings
gemini/imagen-3.0-generate-002ImageHigh-quality images
gemini/veo-2VideoVideo generation

Note: In the backend provider enum, Google models use the gemini provider identifier. When configuring models via the API, use gemini as the provider value.

Mistral​

European AI with strong multilingual and code capabilities.

Capabilities: Chat, Embeddings, Speech-to-Text, Moderation

ModelTypeBest For
mistral/mistral-large-latestChatMost capable Mistral model
mistral/mistral-small-latestChatFast, cost-effective
mistral/pixtral-large-latestChatVision capabilities
mistral/codestral-latestChatCode generation
mistral/mistral-embedEmbeddingText embeddings

Cohere​

Enterprise-focused models with RAG and reranking specialization.

Capabilities: Chat, Embeddings, Reranking

ModelTypeBest For
cohere/command-r-plusChatComplex tasks with RAG
cohere/command-rChatGeneral chat with RAG
cohere/command-a-03-2025ChatReasoning capabilities
cohere/embed-english-v3.0EmbeddingEnglish text embeddings
cohere/embed-multilingual-v3.0EmbeddingMultilingual embeddings
cohere/rerank-v3.5RerankSearch result reranking

Grok (xAI)​

xAI's models with real-time knowledge and image generation.

Capabilities: Chat, Vision, Image Generation

ModelTypeBest For
grok/grok-3ChatMost capable Grok model
grok/grok-3-fastChatFast inference
grok/grok-3-miniChatEfficient, smaller model
grok/grok-2-latestChatVision capabilities
grok/auroraImageImage generation

DeepSeek​

Chinese AI with strong reasoning and coding capabilities.

Capabilities: Chat, Reasoning

ModelTypeBest For
deepseek/deepseek-chatChatGeneral chat, coding
deepseek/deepseek-reasonerChatComplex reasoning tasks

ElevenLabs​

Industry-leading voice synthesis and audio generation.

Capabilities: Text-to-Speech, Music Generation, Sound Effects

ModelTypeBest For
elevenlabs/eleven_multilingual_v2TTS29-language voice synthesis
elevenlabs/eleven_turbo_v2_5TTSFast, low-latency TTS
elevenlabs/eleven_flash_v2_5TTSUltra-fast TTS
elevenlabs/eleven_music_v1MusicMusic generation
elevenlabs/eleven_sfx_v1AudioSound effects

Mubert​

AI-powered music generation platform.

Capabilities: Music Generation

ModelTypeBest For
mubert/mubert-renderMusicAI-generated music and soundtracks

Stability AI​

Open-source image generation models.

Capabilities: Image Generation

ModelTypeBest For
stability/stable-diffusion-3.5-largeImageHigh-quality image generation

Black Forest Labs​

FLUX models for state-of-the-art image generation.

Capabilities: Image Generation

ModelTypeBest For
bfl/flux-2ImageLatest FLUX model
bfl/flux-1.1-proImageProfessional quality
bfl/flux-1.1-pro-ultraImageUltra-high quality
bfl/flux-1-devImageDevelopment/testing
bfl/flux-1-schnellImageFast generation

Runway​

Video generation for creative applications.

Capabilities: Video Generation, Image Generation

ModelTypeBest For
runway/gen4-turboVideoLatest Runway model
runway/gen3a-turboVideoFast video generation
runway/gen3a-turbo-img2vidVideoImage-to-video

Luma AI​

AI video generation with Ray models.

Capabilities: Video Generation

ModelTypeBest For
luma/ray-2VideoHigh-quality video
luma/ray-flash-2VideoFast video generation

Custom / vLLM / Kubernetes​

Self-hosted models deployed on your own infrastructure.

Provider Identifiers:

  • custom - Generic custom provider with configurable endpoint
  • vllm - vLLM-based inference servers
  • kubernetes - Models deployed on Kubernetes via the deployment system

Capabilities: Varies based on the model deployed

These providers are used for self-hosted model deployments. See Deploying Models for details on deploying your own models.

Using Models​

When calling the AI Gateway, use the Strongly-generated model ID - the unique identifier assigned when a model is added to your account.

// Get your model ID from your configured models list
const modelId = '507f1f77bcf86cd799439011';

const response = await fetch('https://ai-gateway.strongly.ai/v1/chat/completions', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'X-User-Id': userId,
    'X-App-Id': appId  // or X-Workflow-Id or X-Workspace-Id
  },
  body: JSON.stringify({
    model: modelId,  // Strongly-generated model ID
    messages: [{ role: 'user', content: 'Hello!' }]
  })
});

Switching Providers​

To switch between providers, use the Strongly ID for the model you want to use:

// Each model has its own unique Strongly ID
const openaiModel = '507f1f77bcf86cd799439011';     // Your GPT-4o instance
const anthropicModel = '507f1f77bcf86cd799439012';  // Your Claude instance
const googleModel = '507f1f77bcf86cd799439013';     // Your Gemini instance

// Use any model by passing its Strongly ID
const model = openaiModel;

Note: The same vendor model (e.g., GPT-4o) can be configured multiple times with different API keys. Each configuration gets a unique Strongly ID.