Question 1

What is the cost of Qwen3-VL 235B A22B Thinking by Merge Gateway?

Accepted Answer

Qwen3-VL 235B A22B Thinking by Merge Gateway costs $0.29 per 1M input tokens and $2.87 per 1M output tokens. Cached reads cost $0.06 per 1M tokens.

Question 2

What is the context window of Qwen3-VL 235B A22B Thinking by Merge Gateway?

Accepted Answer

Qwen3-VL 235B A22B Thinking by Merge Gateway has a context window of 131K tokens. It supports up to 131K input tokens and can generate up to 33K output tokens.

Question 3

What are the capabilities of Qwen3-VL 235B A22B Thinking by Merge Gateway?

Accepted Answer

Qwen3-VL 235B A22B Thinking by Merge Gateway supports advanced reasoning, tool calling/function calling, adjustable temperature, file attachments. It has open weights.

Question 4

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

Accepted Answer

Qwen3-VL 235B A22B Thinking by Merge Gateway accepts text, image as input and can generate text as output.

Question 5

Does Qwen3-VL 235B A22B Thinking by Merge Gateway support reasoning?

Accepted Answer

Yes, Qwen3-VL 235B A22B Thinking by Merge Gateway supports advanced reasoning capabilities.

Question 6

Is Qwen3-VL 235B A22B Thinking by Merge Gateway open source?

Accepted Answer

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

Question 7

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

Accepted Answer

Yes, Qwen3-VL 235B A22B Thinking by Merge Gateway 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-VL 235B A22B Thinking?

Accepted Answer

Qwen3-VL 235B A22B Thinking by Merge Gateway has a knowledge cutoff date of 2025-03-31. This means the model was trained on data available up until that date.

Qwen3-VL 235B A22B Thinking API

Input Modalities

Output Modalities

Standard (per 1M tokens)

Caching (per 1M tokens)