Skip to content

Qwen: Qwen3 235B A22B Thinking 2507

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

About this model

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...

Make a request

OpenAI-compatible: set the base URL and your Promptix API key, keep your existing SDK.

curl https://promptix.tn/api/v1/chat/completions \  -H "Authorization: Bearer $PROMPTIX_API_KEY" \  -H "Content-Type: application/json" \  -d '{    "model": "qwen/qwen3-235b-a22b-thinking-2507",    "messages": [      {"role": "user", "content": "Hello! What can you do?"}    ]  }'

Pricing

In TND per 1M tokens. VAT and the platform fee are added at top-up.

Input tokens

0.764 TND

per 1M tokens

Output tokens

7.642 TND

per 1M tokens

1,000 requests with 1K input and 500 output tokens cost about 4.585 TND.

Specifications

Provider
Qwen
Context window
131,072 tokens
Input modality
Text
Added
Jul 25, 2025
Supported parameters
frequency_penaltyinclude_reasoninglogprobsmax_tokenspresence_penaltyreasoningrepetition_penaltyresponse_format