GatewaySupported Models

Supported Models

Tangle Gateway provides access to models from 20+ providers through a single API.

Providers

ProviderSlugModels
OpenAIopenaiGPT-4o, GPT-4o-mini, o1, o3, o4, DALL-E, Whisper, TTS
AnthropicanthropicClaude Opus, Sonnet, Haiku
GooglegoogleGemini 2.5 Pro, Flash, Flash-Lite
GroqgroqLlama 3.1/3.2 (fast inference)
Together AItogetherOpen-source models (Llama, Qwen, Mixtral)
DeepSeekdeepseekDeepSeek Chat, DeepSeek Coder
MistralmistralMistral Large, Codestral, Pixtral
FireworksfireworksPhi, StarCoder, open models
CoherecohereCommand R/R+
xAIxaiGrok 2, Grok 3
CerebrascerebrasLlama (fast inference)
SambaNovasambanovaFast open-model inference
AI21ai21Jamba
NvidianvidiaNemotron
Z.aizaiGLM-4.7, GLM-5
MoonshotmoonshotKimi

Plus decentralized operators on the Tangle network running Blueprints:

BlueprintModelsHow to route
LLM InferenceLlama, Qwen, Mistral, any vLLM-compatible modelX-Tangle-Routing: operator or auto
Vector StoreEmbedding models for RAG/v1/collections and /v1/rag/query
Custom BlueprintsAny model the operator deploysPin by Blueprint ID or operator slug

Operators set their own pricing and the gateway scores them on reputation, latency, and price. See Operator Routing for details.

Model ID format

Use provider/model-name:

anthropic/claude-sonnet-4-6
openai/gpt-4o-mini
groq/llama-3.1-70b-versatile

Or use bare names — the gateway resolves the provider by prefix:

PrefixResolves to
gpt-, o1-, o3-, o4-OpenAI
claude-Anthropic
gemini-, gemma-Google
llama-, mixtral-Groq
deepseek-DeepSeek
mistral-, codestral-Mistral
grok-xAI
glm-Z.ai
command-Cohere

Modalities

ModalityEndpointExamples
Text/v1/chat/completionsAll chat models
Images/v1/images/generationsDALL-E, FLUX
Audio/v1/audio/transcriptions, /v1/audio/speechWhisper, TTS
Embeddings/v1/embeddingstext-embedding-3-small/large
Video/v1/video/*Avatar generation, dubbing (via ph0ny)

Dynamic discovery

The model catalog is available at GET /api/models with pricing, context length, and modality information for every model.