novita

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

Context

256K

Input

text, image

Output

text

Tool calling

Supported

About this model

Qwen3-VL-235B-A22B-Thinking is a powerful MoE vision-language model with 235B total and 22B activated parameters. It excels in visual agents, spatial perception, long-context video understanding, and enhanced multimodal reasoning, with a 256K context length.

Capabilities

text

Available through the unified API

image

Available through the unified API

Quick start

View API docs
curl https://api.oneinfer.ai/v1/chat/completions \
  -H "Authorization: Bearer $ONEINFER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "0aaab8075ff948078a72021a256d2a2c",
    "messages": [
      { "role": "user", "content": "Hello!" }
    ]
  }'

Providers

Available routing options for this model through OneInfer.

novita

0aaab8075ff948078a72021a256d2a2c

Available

Input

$0.980 / 1M

Output

$3.950 / 1M

Routing

OneInfer optimized

Pricing

Current OneInfer pricing for this model.

UsagePrice
Input tokens$0.980 / 1M
Output tokens$3.950 / 1M

Performance

Published evaluation results associated with this model.

Reasoning

GPQA Diamond77.2
IFBench56.5
τ²-Bench Telecom54.1

API example

curl https://api.oneinfer.ai/v1/chat/completions \
  -H "Authorization: Bearer $ONEINFER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "0aaab8075ff948078a72021a256d2a2c",
    "messages": [
      { "role": "user", "content": "Hello!" }
    ]
  }'