Tessera Documentation

Managed AI inference for mid-market companies. OpenAI-compatible API.

Get started in 60 seconds

Change a base_url, export your API key, fire the first request. No custom SDK: your OpenAI client works as-is.

from openai import OpenAI

client = OpenAI(
  base_url="https://api.tesseraai.cloud/v1",
  api_key="sk-tessera-…",
)

resp = client.chat.completions.create(
  model="Qwen/Qwen3.6-35B-A3B",
  messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)

Essential resources

What most developers reach for in their first week.

Migrating from OpenAI

base_url swap, model mapping table and documented behavioural differences.

5 min

Available models

Qwen/Qwen3.6-35B-A3B, Whisper large-v3, Kokoro TTS and Qwen3-Embedding-8B. Capabilities, context and licenses.

Rate limits

Sustained RPM, bursts, per-bundle-service sublimits. How to handle 429 and backoff.

Tool calling

OpenAI-compatible function calling. Parallel tools and structured JSON output examples.

Webhooks

Per-request usage events, plugged into your billing or cost-center system without the dashboard.

DPA template

Signable document, public subprocessor list and physical GPU location for your DPO.