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 tokens of context. This thinking-only variant enhances structured logical reasoning, mathematics, science, and long-form generation, showing strong benchmark performance across AIME, SuperGPQA, LiveCodeBench, and MMLU-Redux. It enforces a special reasoning mode and is designed for high-token outputs (up to 81,920 tokens) in challenging domains. The model is instruction-tuned for step-by-step reasoning, tool use, agentic workflows, and multilingual tasks. It is the most capable open-source variant in the Qwen3-235B series, surpassing many closed models in structured reasoning use cases.
$0.225market price $0.45
$0.0115
$1.75market price $3.50
Throughput is how fast the model writes (tokens per second, higher is better). Time to first token is how long before the answer starts (lower is better).
Share of requests served without a server error. Client errors (4xx) do not count.
Works with the OpenAI SDK pointed at our base URL. Every parameter is in the API reference.
Tokens processed per day on NagaAI.
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 tokens of context.
On NagaAI, Qwen3 235B A22B Thinking 2507 costs $0.225 per 1M input tokens and $1.75 per 1M output tokens. You pay only for what you use, with no subscription.
Qwen3 235B A22B Thinking 2507 reads up to 128k tokens in one request, counting the prompt and the answer together.
Yes. Qwen3 235B A22B Thinking 2507 can call your functions as tools and can answer in a JSON schema you give it.
It takes text as input and returns text.
Create an API key, copy the model ID from the top of this page and send requests with the OpenAI or Anthropic SDK pointed at NagaAI. The API section on this page has a ready example.
Qwen3.8 Max PrimeQwenQwen3.8 Omni FlashQwenQwen3.8 FlashQwenQwen3.8 27BQwenQwen3.8 2.4T A95BQwenQwen3.8 MaxQwenNot enough throughput data
Not enough TTFT data