Feature Matrix

February 14, 2026 · View on GitHub

✅ - Supported
⚠️ - Partially supported/under construction
❌ - Not supported
Empty field means the feature is unsupported by the provider.

Inference

ProviderChatModelsEmbeddingsFilesImagesAudioUploadsModerationResponsesVideosTokenizeFIMFine-tuningBatch
OpenAI
Anthropic
Google
Cohere
DeepSeek
Groq
Mistral
xAI
MoonshotAI
Perplexity
Voyage
DeepInfra
OpenRouter
Requesty
Upstage
Z.ai
Alibaba
Blablador
MiniMax
Custom*

*Custom means any OpenAI compatible provider, such as Azure OpenAI, Ollama, KoboldCpp, etc.

OpenAI Specific

ConversationsAssistantsThreadsMessagesRunsRun stepsVector storesVector store filesVector store file batchesRealtimeEvalsGraders
✅️✅️✅️✅️

Google Specific

CachingSemantic RetrievalLiveSpeech

Anthropic Specific

Skills

Voyage Specific

Multimodal EmbeddingContextualized EmbeddingRerankers

Cohere Specific

Rerank

MiniMax Specific

Music GenerationLyrics Generation

Mistral Specific

AgentsClassifiersOCRAgents

Misc

Some providers offer /admin APIs, LlmTornado won't ship support for these, as there is little to no overlap among them. We recommend using autogenerated APIs for the consumption of these services.