Qwen3 235B
qwen/qwen3-235b-a22bRun Qwen3 235B in a hosted Python Task with extended thinking and file inputs.
Alibaba's largest open-source Qwen3 model via OpenRouter with 235B parameters. Apache 2.0 licensed with exceptional multilingual capabilities and strong performance across diverse tasks.
This model is deprecated and not recommended for new projects.
What Qwen3 235B supports in qbash
- Extended thinkingReasons through a problem before it replies.
- Document inputReads PDF, TEXT, DOC, XLS, RTF and 7 more files.
What is qbash?
qbash is where you build Tasks: Python programs that run a business process on managed infrastructure. Your code runs the steps and calls a model like Qwen3 235B only at the ones that need judgment, with integrations, memory and files available in the same script.
A developer writes the Task once, and anyone on the team runs it from a form, on a schedule, from a webhook or from chat. Each Task is versioned and every run is logged.
Specifications
- Context window
- 128Ktokens
- Max output
- 8,192tokens
- Temperature
- 0 to 1default 1
Use Qwen3 235B in a Python Task
qbash.ai.raw calls Qwen3 235B from a Task and returns its reply as a string.
notes = qbash.inputs.get("notes")
summary = qbash.ai.raw(
f"Summarize these meeting notes in five bullets:\n\n{notes}",
model="qwen/qwen3-235b-a22b",
system="You are a concise analyst.",
)
qbash.output({"summary": summary})
Extended thinking with Qwen3 235B
Turn on Thinking in the same Settings popover to have Qwen3 235B reason through a problem before it replies.
Qwen3 235B pricing
| Input | $0.455 per 1M tokens |
|---|---|
| Output | $1.82 per 1M tokens |
Standard rates in USD.
Supported file formats
Documents
- TEXT
- DOC
- XLS
- RTF
- DOCX
- XLSX
- PPTX
- PPT
- ODT
- ODP
- ODS