qwen

Qwen Qwen3 235B A22B Thinking 2507

qwen/qwen3-235b-a22b-thinking-2507

Input$0.100 /1M tokens
·
Output$0.100 /1M tokens

Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...

Code Examples

import requests

response = requests.post(
    "https://neurongate.net/v1/chat/completions",
    headers={
        "Authorization": "Bearer ng-your-api-key",
        "Content-Type": "application/json"
    },
    json={
        "model": "qwen/qwen3-235b-a22b-thinking-2507",
        "messages": [
            {"role": "user", "content": "Hello!"}
        ]
    }
)

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

Pricing Details

ExampleCost
1K input tokens (short prompt)$0.00010
1K in + 500 out (typical response)$0.00015
10K in + 2K out (document analysis)$0.00120
100K in + 10K out (large context)$0.0110

Prices in USD. Billed per actual token usage. Prepay with USDT, USDC, ETH, or BTC.

Frequently Asked Questions

Capabilities

Streaming
Yes
Function Calling / Tools
Yes
Vision (Image Input)
No
Audio Processing
No

Context Window

262K tokens

~197K words of text

Max output
262K tokens

Modalities

Input
text
Output
text

Ready to build?

Pay with crypto. No subscriptions.

Get Started Free

Similar Models