Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.tera.gw/llms.txt

Use this file to discover all available pages before exploring further.

Tera serves open-weight models through a single OpenAI-compatible API surface. Pick a model id and pass it as the model field. This page is regenerated from the live model catalog. The authoritative source is GET /v1/models.

​
Available now

Qwen3.5-4B

Smallest reasoning-capable Qwen. 262k context. Cheapest tokens on Tera.

Qwen2.5-7B-Instruct

Fast, general-purpose chat. 8k context. Tool calling.

Qwen3.5-27B

Reasoning model with reasoning_content.

Kokoro-82M

Lightweight text-to-speech. Returns WAV bytes.

gpt-oss-20b

OpenAI’s open-weight 20B with 131k context. MXFP4.

gpt-oss-120b

OpenAI’s open-weight 120B. 131k context, MXFP4, 2× A100 deploy.

​
Choosing a model

If you want…Use
Cheapest tokens, long contextQwen3.5-4B
Fastest general chatQwen2.5-7B-Instruct
Reasoning / planning / mathQwen3.5-27B
OpenAI open-weight, mediumgpt-oss-20b
OpenAI open-weight, largegpt-oss-120b
Text-to-speechKokoro-82M

​
Pricing

See the pricing table for per-million-token rates.

​
Don’t see what you need?

We add models as customers ask for them. Email hello@tera.gw with the HuggingFace id and we’ll evaluate.