How much does Qwen3 235B A22B Instruct 2507 cost?

On the Respan gateway, Qwen3 235B A22B Instruct 2507 costs from $0.09 per 1M input tokens and $0.55 per 1M output tokens on DeepInfra and OpenRouter, after gateway discounts. Averaged across its 4 providers, it costs $0.12 per 1M input tokens and $0.58 per 1M output tokens.

Which providers serve Qwen3 235B A22B Instruct 2507 on Respan?

Qwen3 235B A22B Instruct 2507 is available through 4 providers: DeepInfra, OpenRouter, Parasail, and Nebius.

What is Qwen3 235B A22B Instruct 2507's context window?

Qwen3 235B A22B Instruct 2507 accepts up to 262K tokens of context on its largest provider route.

How do I use Qwen3 235B A22B Instruct 2507 with the Respan gateway?

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "qwen3-235b-a22b-instruct-2507". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Where does Qwen3 235B A22B Instruct 2507 rank on the Respan Index?

Qwen3 235B A22B Instruct 2507 scores 20.2 out of 100 on the Respan Index v1.1, ranking #117 of 161 models. By category: Coding 5.0, Agents 18.4 (estimated), Reasoning 22.4 (estimated), Knowledge & language 15.2, and Human preference 48.1. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.

How does Qwen3 235B A22B Instruct 2507 score on benchmarks?

Qwen3 235B A22B Instruct 2507 has 17 published benchmark scores, including Aider-Polyglot 57.3%, TAU2-Retail 74.6%, and GPQA 77.5%. Each score links to where it was published; the data is collected by Respan.

Qwen3 235B A22B Instruct 2507

Q: What is Qwen3 235B A22B Instruct 2507?

Qwen3 235B A22B Instruct 2507 is a model from Qwen, released on Jul 21, 2025. We introduce the updated version of the **Qwen3-235B-A22B non-thinking mode**, named **Qwen3-235B-A22B-Instruct-2507**, featuring the following key enhancements:.

We introduce the updated version of the **Qwen3-235B-A22B non-thinking mode**, named **Qwen3-235B-A22B-Instruct-2507**, featuring the following key enhancements:

Input / output, from: $0.09 / $0.55 per 1M
Weekly tokens / requests: 8 / 1
Context: 262K tokens
Released: Jul 21, 2025

Try Respan for free

Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "qwen3-235b-a22b-instruct-2507".

from openai import OpenAI

client = OpenAI(

    base_url="https://api.respan.ai/api/",

    api_key="YOUR_RESPAN_API_KEY",

)

response = client.chat.completions.create(

    model="qwen3-235b-a22b-instruct-2507",

    messages=[{"role": "user", "content": "Hello!"}],

)

print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({

  baseURL: "https://api.respan.ai/api/",

  apiKey: "YOUR_RESPAN_API_KEY",

});

const response = await client.chat.completions.create({

  model: "qwen3-235b-a22b-instruct-2507",

  messages: [{ role: "user", content: "Hello!" }],

});

console.log(response.choices[0].message.content);

curl https://api.respan.ai/api/chat/completions \

  -H "Authorization: Bearer YOUR_RESPAN_API_KEY" \

  -H "Content-Type: application/json" \

  -d '{

    "model": "qwen3-235b-a22b-instruct-2507",

    "messages": [{"role": "user", "content": "Hello!"}]

}'

Read docs

Providers

4 providers, cheapest first, priced per 1M tokens after gateway discounts.

Provider	Context	Input	Output	Cache read
DeepInfra`deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507`	262K	$0.09/M	$0.55/M	$0.00/M
OpenRouter`openrouter/qwen/qwen3-235b-a22b-2507`	262K	$0.09/M	$0.55/M	$0.02/M
Parasail`parasail/Qwen/Qwen3-235B-A22B-Instruct-2507`	262K	$0.10/M	$0.60/M	$0.01/M
NebiusRetiring`nebius/Qwen/Qwen3-235B-A22B-Instruct-2507`	262K	$0.20/M	$0.60/M	$0.05/M

Is a provider down? OpenRouter status

Pricing

Averaged across 4 providers, in USD per 1M tokens after gateway discounts.

Average input: $0.12 per 1M
Average output: $0.58 per 1M
Average cache read: $0.02 per 1M

Cost by volume

Total cost from 0 to 1T tokens on the cheapest and most expensive provider.

Highest$0.20/MNebiusLowest$0.09/MDeepInfra and OpenRouter

Throughput and latency

30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.

Output speed

Higher is better

10tokens/sacross providers

Faster than 12% of the other 472 models on the gateway

Response latency

Lower is better

2.5sacross providers

Faster than 49% of the other 498 models on the gateway

Benchmarks

The Respan Index plus 17 published scores from 3 sources, each linked to where it was published.

20.2/ 100

Respan Index#117 of 161

161 ranked models. The shaded band is this model's 95% interval, 13.2 to 37.4. Grok 4 Fast Reasoning and Qwen3.5 27B fall inside it, so the gap is within the margin of error.

117Qwen3 235B-A22B Instruct 250720.2
116Grok 4 Fast Reasoning20.4
117Qwen3.5 27B20.2

Published scores

Benchmark	Score	Source	Published
Aider-Polyglothuggingface.co	57.3%	huggingface.co	Jul 21, 2025
LiveCodeBench v6 (25.02-25.05)huggingface.co	51.8%	huggingface.co	Jul 21, 2025
WeirdMLHåvard Tveit Ihle	38.7%	Håvard Tveit Ihle	Oct 5, 2026

Benchmark	Score	Source	Published
TAU2-Retailhuggingface.co	74.6%	huggingface.co	Jul 21, 2025
BFCL-v3huggingface.co	70.9%	huggingface.co	Jul 21, 2025

Benchmark	Score	Source	Published
GPQAhuggingface.co	77.5%	huggingface.co	Jul 21, 2025
LiveBench 20241125huggingface.co	75.4%	huggingface.co	Jul 21, 2025
SuperGPQAhuggingface.co	62.6%	huggingface.co	Jul 21, 2025
ARC-AGIhuggingface.co	41.8%	huggingface.co	Jul 21, 2025

Benchmark	Score	Source	Published
AIME25huggingface.co	70.3%	huggingface.co	Jul 21, 2025
HMMT25huggingface.co	55.4%	huggingface.co	Jul 21, 2025

Benchmark	Score	Source	Published
MMLU-Reduxhuggingface.co	93.1%	huggingface.co	Jul 21, 2025
IFEvalhuggingface.co	88.7%	huggingface.co	Jul 21, 2025
MMLU-Prohuggingface.co	83%	huggingface.co	Jul 21, 2025
SimpleQAhuggingface.co	54.3%	huggingface.co	Jul 21, 2025