Supported Providers
TokenSense supports multiple AI providers. Pick your provider below to see setup instructions and supported models.
Point your workflow at your TokenSense endpoint instead of the provider directly. TokenSense identifies the provider from the model name and routes automatically.
Available
OpenAI
GPT-6.1 Sol, GPT-6 Astra, Sol, and Luna; Responses and embeddings.
AvailableAnthropic
Claude Fable 5.1, Opus 5.5, Sonnet 5.5, and Haiku — native Messages.
AvailableGoogle Gemini
Gemini 3.8 Flash, 3.1 Flash-Lite, and Pro Preview — native text generation.
AvailablexAI (Grok)
Grok 4.7 and compatible Chat Completions models.
AvailableMistral
Mistral Medium 3.5, Small 4, and embeddings.
AvailableKimi (Moonshot AI)
Kimi K3, K2.7 Code, and K2.6 — with per-model cache-hit pricing.
Availablefal
Flux 2 Pro, Dev, and Schnell image generation, billed per image.
Which provider covers which modality
| Modality | Providers |
|---|---|
| Chat / LLM | OpenAI, Anthropic, Google Gemini, xAI, Mistral, Kimi (Moonshot AI) |
| Embeddings | OpenAI, Mistral |
| Image generation | OpenAI and fal (check billing coverage); current Gemini image adapter pending |
| Audio (speech + transcription) | OpenAI |
