Question 1

What is Qwen3 235B A22B?

Accepted Answer

Qwen3 235B A22B is a model from Qwen, released on Apr 29, 2025. Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. $0.455 per million input tokens, $1.82 per million output tokens. 131,072 token context window, maximum output of 8,192 tokens. Includes independent benchmarks from Artificial Analysis.

Question 2

How much does Qwen3 235B A22B cost?

Accepted Answer

On the Respan gateway, input starts at $0.09 per 1M tokens on OpenRouter, and output starts at $0.55 per 1M tokens on OpenRouter, after gateway discounts. Averaged across 4 providers, it costs $0.23 per 1M input tokens and $0.92 per 1M output tokens.

Question 3

Which providers serve Qwen3 235B A22B on Respan?

Accepted Answer

4 providers serve Qwen3 235B A22B: OpenRouter, Novita, and Nebius.

Question 4

What is Qwen3 235B A22B's context window?

Accepted Answer

Qwen3 235B A22B accepts up to 262K tokens of context on its largest provider route.

Question 5

How do I use Qwen3 235B A22B with the Respan gateway?

Accepted Answer

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "qwen3-235b-a22b". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Question 6

How fast is Qwen3 235B A22B?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was OpenRouter at 36 tokens per second, and the lowest response latency was 1.0 seconds on Novita. Speed varies with request size and provider.

Question 7

Where does Qwen3 235B A22B rank on the Respan Index?

Accepted Answer

Qwen3 235B A22B scores 14.4 out of 100 on the Respan Index v1.1, ranking #125 of 138 models. By category: Coding 4.8, Agents 12.9 (estimated), Reasoning 11.0, Knowledge & language 11.2 (estimated), and Human preference 40.9. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by llmmetric.com.

Question 8

How does Qwen3 235B A22B score on benchmarks?

Accepted Answer

Qwen3 235B A22B has 7 published benchmark scores, including WeirdML 37.3%, GPQA Diamond 70.7%, and AIME 2025 80.8%. Each score links to where it was published; the data is collected by llmmetric.com.

Provider	Context	Input	Output	Capabilities
OpenRouter`openrouter/qwen/qwen3-235b-a22b-2507`	262K	$0.09/M	$0.55/M
NovitaSave 10%`novita/qwen/qwen3-235b-a22b-fp8`	41K	$0.18/M	$0.72/M	—
Nebius`nebius/Qwen/Qwen3-235B-A22B-Instruct-2507`	262K	$0.20/M	$0.60/M
OpenRouter`openrouter/qwen/qwen3-235b-a22b`	131K	$0.45/M	$1.82/M

Qwen3 235B A22B

Providers

Certified where it counts.

Pricing

Cost by volume

Throughput and latency

Output speed

Response latency

Benchmarks

Respan Indexv1.1

Coding1

Reasoning3

Apps

Qwen3 235B A22B FAQ

Works with your entire stack

Built for AI agents.
Break less.
Ship more.

Math2

Arena1