Question 1

What is the cost of Qwen3 235B A22B Thinking-2507 by CoreWeave?

Accepted Answer

Qwen3 235B A22B Thinking-2507 by CoreWeave costs $0.10 per 1M input tokens and $0.10 per 1M output tokens. Cached reads cost $0.10 per 1M tokens.

Question 2

What is the context window of Qwen3 235B A22B Thinking-2507 by CoreWeave?

Accepted Answer

Qwen3 235B A22B Thinking-2507 by CoreWeave has a context window of 262K tokens. It supports up to 262K input tokens and can generate up to 262K output tokens.

Question 3

What are the capabilities of Qwen3 235B A22B Thinking-2507 by CoreWeave?

Accepted Answer

Qwen3 235B A22B Thinking-2507 by CoreWeave supports advanced reasoning, tool calling/function calling, structured output, adjustable temperature. It has open weights.

Question 4

What input and output types does Qwen3 235B A22B Thinking-2507 support?

Accepted Answer

Qwen3 235B A22B Thinking-2507 by CoreWeave accepts text as input and can generate text as output.

Question 5

Does Qwen3 235B A22B Thinking-2507 by CoreWeave support reasoning?

Accepted Answer

Yes, Qwen3 235B A22B Thinking-2507 by CoreWeave supports advanced reasoning capabilities.

Question 6

Is Qwen3 235B A22B Thinking-2507 by CoreWeave open source?

Accepted Answer

Yes, Qwen3 235B A22B Thinking-2507 by CoreWeave has open weights, meaning the model weights are publicly available for download and self-hosting.

Question 7

Does Qwen3 235B A22B Thinking-2507 support function calling?

Accepted Answer

Yes, Qwen3 235B A22B Thinking-2507 by CoreWeave supports tool calling (also known as function calling), allowing it to interact with external tools and APIs during conversations.

Question 8

What is the knowledge cutoff date for Qwen3 235B A22B Thinking-2507?

Accepted Answer

Qwen3 235B A22B Thinking-2507 by CoreWeave has a knowledge cutoff date of 2025-04. This means the model was trained on data available up until that date.

Qwen3 235B A22B Thinking-2507 API

Input Modalities

Output Modalities

Standard (per 1M tokens)

Caching (per 1M tokens)