LatentKit

Models & Providers

Which providers and model capabilities LatentKit supports, and how model selection actually works.

LatentKit maintains a provider and model catalog. Your workspace connects providers and chooses models per route in the console; application code never sends model names. This page explains the available capabilities and where to find the live list for your workspace.

How model selection works

  1. The catalog defines providers and their models, each tagged with capabilities and prices.
  2. Your workspace enables models on a connection (BYOK or Platform Access).
  3. A route (routing policy) lists ordered connection-model entries.
  4. At request time, LatentKit filters route entries by the endpoint's required capability and health, then executes in policy order.

The model that answered is reported back in response.model and response.provider.

Supported providers

ProviderTypeNotes
OpenAIDirectChat, vision, embeddings, images, TTS, and transcription models
AnthropicDirectClaude chat and vision models
Google GeminiDirectChat, vision, and multimodal models with large context windows
Mistral AIDirectChat and code models
DeepSeekDirectChat and reasoning models
Moonshot AI (Kimi)DirectCurrent Kimi K3, K2.7 Code, and K2.6 text/vision/video-input models
xAI (Grok)DirectGrok chat/reasoning models plus image and video generation
OpenRouterAggregatorOpenAI-compatible access to many third-party models (Llama, and more) through one connection
AWS BedrockCloud platformOpenAI-compatible Bedrock Mantle access; BYOK with an optional regional endpoint override
Microsoft Foundry / Azure OpenAICloud platformOpenAI-compatible v1 endpoint; BYOK endpoint and deployment names are workspace-specific
Google Vertex AICloud platformOpenAI-compatible endpoint for Gemini and partner models; BYOK project/location endpoint required
Fireworks AIInference platformOpenAI-compatible hosted models including Kimi, DeepSeek, and MiniMax
DeepInfraInference platformOpenAI-compatible hosted text, vision, and reasoning models
fal.aiMedia platformDirect image and video generation model endpoints
ReplicateMedia platformOfficial image and video models with synchronous wait and bounded polling

The broader active catalog also includes Alibaba/Qwen, ByteDance/Volcano Ark, Cerebras, Cohere, Groq, Jina AI, MiniMax, Perplexity, Scaleway, Together AI, Z.ai, and the dedicated speech providers listed below. In total, the shipped catalog contains 30 active provider definitions; individual model visibility still depends on the applied database migrations and workspace connection.

For speech-to-text, the audio capability matrix additionally covers OpenAI transcribe models, AssemblyAI, Deepgram, ElevenLabs Scribe, Google Cloud Speech-to-Text, and Gemini audio — see Audio and STT for the current status of each.

For text-to-speech, OpenAI and ElevenLabs (Flash, Turbo, Multilingual v2, and v3) carry the audio_output capability — see Speech. ElevenLabs voice models route through BYOK connections only.

The catalog evolves continuously and model availability differs per workspace plan and connection. The Providers section in the console is the live source of truth for the models your workspace can route to right now.

Custom providers

Workspaces can also register custom OpenAI-compatible providers (self-hosted or third-party gateways that speak the OpenAI API shape) from the console, then route to them like any other connection.

Capabilities

Every catalog model is tagged with capabilities. Endpoints require capabilities, and only matching route models are eligible:

CapabilityEndpoints that require it
text/v1/chat, /v1/complete
vision/v1/vision; added automatically when chat messages contain image input
video_inputAdded automatically when supported chat messages contain video input
embeddings/v1/embeddings, /v1/embed
image_generation/v1/image
audio_input/v1/transcription, /v1/translation
audio_output/v1/speech, /v1/audio; added when chat requests "modalities": ["audio"]
video_generation/v1/video
function_callingAdded automatically when a request includes tools, tool_choice, or tool messages

If no route model satisfies the required capabilities, the request fails with NO_HEALTHY_PROVIDER — see Error reference.

Pricing and cost reporting

Per-token prices come from the same catalog the console displays. Each successful response includes a cost_usd field computed from provider-reported token usage and catalog prices, so your logs and the console usage dashboards agree.

BYOK vs Platform Access models

  • BYOK connections can use any catalog model the provider account has access to; LatentKit does not bill model usage. The provider bills your own account at its own rate — LatentKit adds no margin to BYOK usage. The cost_usd on a BYOK response is an estimate of that provider charge (the response is tagged billing_mode: "byok_estimate"), not a workspace charge.
  • Platform Access (managed) connections bill usage against workspace credits. Some modalities — notably audio — may be BYOK-only until managed billing supports their pricing dimensions.

The first provider-breadth wave is BYOK-only. Azure OpenAI and Vertex AI need a connection-specific endpoint, while AWS Bedrock can use the seeded US East Mantle endpoint or a regional override. fal.ai and Replicate currently use curated model rows rather than the generic Sync Models flow.

Picking models for a use case

GoalApproach
Cheapest acceptable answersUse the cost routing strategy or order low-cost models first
Maximum stability for tests/evalsPin one model in the policy and pass seed — see Determinism
High availabilityOrder equivalent models from different providers as fallbacks
Speed vs depth per requestUse route response_profile assignments (fast / balanced / thinking)

On this page