Tīrtha is still being built, so some features and models may not work as expected yet. Billing always follows the prices shown. Something broken? Email [email protected].

Tīrtha

Models / Qwen

Qwen3.8-27B

by Qwen

Used for coding and agents.

Best forCodingAgents and tools

Open weights · Apache-2.0Released Aug 5, 2026

Qwen3.8-27B is made by Qwen. It takes text and images, with a context window of 262,144 tokens. On Tīrtha it takes text.

Context262,144 tokens
Max output16,384 tokens
Takes on TīrthaText
Use Qwen3.8-27B now
catalog/qwen3.8-27b

Add credits · Read the docs

Tīrtha Bench review

What people use it for, in its maker's words:

CodingAgents and tool use
Context262,144 tokens
Takes in on Tīrthatext

Try it

Model id catalog/qwen3.8-27b · base URL https://api.tirtha.ai/v1. Any OpenAI-compatible client works: change the base URL and keep your code.

curl https://api.tirtha.ai/v1/chat/completions \ -H "Authorization: Bearer $TIRTHA_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model": "catalog/qwen3.8-27b", "messages": [{"role": "user", "content": "Hello"}]}'
# pip install openai import os from openai import OpenAI client = OpenAI(base_url="https://api.tirtha.ai/v1", api_key=os.environ["TIRTHA_API_KEY"]) r = client.chat.completions.create(model="catalog/qwen3.8-27b", messages=[{"role": "user", "content": "Hello"}]) print(r.choices[0].message.content)
// Node 18+. Set TIRTHA_API_KEY in your environment (never put your key in a web page). async function main() { const r = await fetch("https://api.tirtha.ai/v1/chat/completions", { method: "POST", headers: {"Authorization": `Bearer ${process.env.TIRTHA_API_KEY}`, "Content-Type": "application/json"}, body: JSON.stringify({model: "catalog/qwen3.8-27b", messages: [{role: "user", content: "Hello"}]}), }); console.log((await r.json()).choices[0].message.content); } main();

Limits and support

MakerQwen
Accepts on Tīrthatext
Context262,144 tokens
Max output16,384 tokens
LicenceApache-2.0
ReleasedAug 5, 2026

What it is for

In the maker's own words, from its published model card. Claims and benchmarks on that card are the maker's own, not measured by Tīrtha.

What a job costs

1,000 calls of 2,000 tokens in and 500 out cost about -

Worked out from the live price above, without cached input. Your own calls will differ in size.

Similar models on Tīrtha

Licence

Weights: Apache-2.0. Read the licence.

From the maker: Model card: Qwen/Qwen3.8-27B on Hugging Face · Last updated by the maker: Aug 14, 2026Facts from the maker's card are the maker's own, not measured by Tīrtha.