Concepts

Available models

Tessera’s base catalogue covers chat, embeddings, reranking, transcription and speech with open models and an OpenAI-compatible API.

Included catalogue

Every tier can access the same catalogue. Tiers differ by capacity, SLA, support, context and priority, not by hiding models behind a premium plan.

ModelEndpointPrimary useLicense
Qwen/Qwen3.6-35B-A3B/v1/chat/completionsChat, RAG, classification, extractionApache 2.0
Qwen3-Embedding-8B/v1/embeddingsSemantic search and retrievalApache 2.0
Qwen3-Reranker-4B/v1/rerankSecond-stage reranking for RAGApache 2.0
Whisper large-v3/v1/audio/transcriptionsMultilingual transcriptionMIT
Kokoro 82M TTS/v1/audio/speechVoice for IVR and agentsApache 2.0

Practical compatibility

  • Use the official OpenAI SDK and change `base_url` to `https://api.tesseraai.cloud/v1`.
  • Keep your `messages`, `tools`, `response_format` and streaming structures where the endpoint supports them.
  • Commercial model aliases can map internally to preserve contractual stability.

Model freeze and upgrades

Contracts can freeze a model family for 12 months. Upgrades are offered as opt-in to avoid silent changes in quality, token cost or latency.