Qwen3 235B

ChatInput: TextReleased Jul 21, 2025

Built by Alibaba (Qwen) · China · qwen.ai

Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,...

How to use

model: "qwen/qwen3-235b"

Cap quality here and save

Hard questions go to this model, easy ones drop to something cheaper. Set a savings target (0–0.8) and the router tunes itself until realized savings converge on it.

{
  "model": "celon/auto",
  "celon": {
    "anchor": "qwen/qwen3-235b",
    "savings_target": 0.4
  }
}

Naming a model directly gets you that model — savings controls don't apply.

Context

262K

Max output

16K

Input $/1M

$0.09

Output $/1M

$0.60

Features

Tool callingJSON

Serving providers

DeepInfraNovitaFriendliW&B Inference

Providers

Price, latency, and uptime per provider serving this model. Celon routes each request to the fastest and cheapest of them. Click a row for regions and data policies.

Loading provider metrics…

Performance

Benchmark quality scores, and measured speed per provider.

Quality

Epoch Capabilities IndexComposite over 50+ benchmarks

139.0

ARC-AGI-2Abstract reasoning

1.3%

At each model's best reasoning effort. Benchmarks it wasn't run on are omitted.

Speed

Loading provider metrics…