ModelsModels / Qwen
Qwen3-32B
Open weights · Apache-2.0by QwenReleased Apr 27, 2025
Qwen3-32B is made by Qwen. It takes text in and answers in text, with a context window of 40,960 tokens.
Start using Qwen3-32B in 3 steps
Read the docs- Get an API keyFree to create. It works for every model in the catalogue.Get an API key
- Add creditsPay as you go. Credits work on every model.Add credits
- Point your client at TīrthaAny OpenAI-compatible client works. Use your key and this base URL, and name the model.base_url: "https://api.tirtha.ai/v1" api_key: "YOUR_TIRTHA_KEY" model: "catalog/qwen3-32b"
Price
Inputper 1M tokens
Outputper 1M tokens
Cached inputper 1M tokens
The live price, read from billing as this page loads. You pay only for the tokens you use, from your credits.
At a glance
MakerQwen
Acceptstext
Context40,960 tokens
Max output16,384 tokens
LicenceApache-2.0
ReleasedApr 27, 2025
Tested on Tīrtha Bench
Not on the public set yet: we have run Qwen3-32B on the public 800-task tool-call set only on a server we do not use for it; its score shows here once it runs where we serve it. The bench shows every model we have run so far.
What it supports
- Text inYes
- ReasoningYesThinks before it answers
- StreamingYes
- Sampling settingsFixed todayThe maker suggests temperature 0.6, top p 0.95, top k 20. Tīrtha fixes temperature at 0 today.
From the maker
- Model card: Qwen/Qwen3-32B on Hugging Face
- Last updated by the maker: Jul 26, 2025
Facts here are read from the maker's published card; claims and benchmarks on that card are the maker's own, not measured by Tīrtha.
Licence
Weights: Apache-2.0. Read the licence.