Qwen3 VL 235B A22B Thinking

qwen3-vl-235b-a22b-thinking

Qwen3-VL-235B-A22B Thinking is a powerful multimodal model that combines advanced text generation with strong image and video understanding, optimized for STEM and math reasoning. It offers robust perception, spatial grounding, and long-form visual comprehension, and supports agent-style interactions such as multi-image dialogue, video timeline alignment, GUI control, and visual-to-code workflows. With competitive benchmark results and strong text-only ability, it’s suited for production uses like document AI, OCR, UI assistance, spatial tasks, and vision-language research.

Context: 131.1K tokens
Endpoint

Service Status

Status information temporarily unavailable

Apertis cannot confirm the current service state. This is not a report that the model is down.

Get API Key Compare

Pricing

Input$0.30 / 1M

Output$3.00 / 1M

Cache Write (5m)$0.30 / 1M

Cache Write (1h)$0.30 / 1M

Cache Read$0.30 / 1M

Web Search$0 / 1M

Quick Start

Select an endpoint and copy a working example for this model.

Endpoint

python

from openai import OpenAI client = OpenAI(    api_key="YOUR_API_KEY",    base_url="https://api.apertis.ai/v1") response = client.chat.completions.create(    model="qwen3-vl-235b-a22b-thinking",    messages=[        {"role": "user", "content": "Hello!"}    ],    max_tokens=1024,    temperature=0.7) print(response.choices[0].message.content) # Optional: Enable context compression to reduce token usage# response = client.chat.completions.create(#     model="qwen3-vl-235b-a22b-thinking",#     messages=[{"role": "user", "content": "Hello!"}],#     extra_body={"compression": {"enabled": True, "model": "gpt-4.1-mini"}}# )

Supported Parameters

API docs

Common7 params

modelmessagesmax_tokenstemperaturetop_pstreamtools

Extended4 params

reasoning_effortstream_optionsthinkingextra_body

Cursor IDE Model IDs

Use these namespaced identifiers in Cursor IDE to avoid conflicts with built-in models.

qwen3-vl-235b-a22b-thinking

Compare with Other Models

See how this model compares to others from the same provider.

Qwen Plus 2025-07-28 Thinking

Qwen Plus 0728 is a hybrid reasoning model built on the Qwen3 foundation, featuring a 1M-token context window and a balanced trade-off between performance, speed, and cost.

Context: 1M
Input: $0.40/M
Output: $4.00/M

Tongyi DeepResearch 30B A3B

Tongyi DeepResearch is a 30B-parameter agentic model (3B active per token) built for long-horizon, deep research and information-seeking tasks. It achieves state-of-the-art results on major agentic search and reasoning benchmarks, outperforming prior models in complex multi-step problem solving. Trained with a fully automated synthetic data pipeline and advanced on-policy RL, it supports ReAct workflows and a high-performance “Heavy” mode for test-time scaling, making it well suited for advanced research agents, tool use, and intensive inference workloads.

Context: 131.1K
Input: $0.135/M
Output: $0.675/M

Qwen3 VL 235B A22B Instruct

Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that combines strong language generation with image and video understanding, aimed at general vision-language tasks like VQA, document parsing, chart/table extraction, and multilingual OCR. It features robust perception, spatial grounding, and long-context visual comprehension, and supports agent-style workflows such as multi-image dialogue, video timeline alignment, GUI control, and visual-to-code assistance. With competitive benchmark performance and strong text-only ability, it's well suited for production uses across document AI, OCR, UI assistance, spatial reasoning, and vision-language research.

Context: 131.1K
Input: $0.30/M
Output: $1.50/M

Qwen3 Next 80B A3B Thinking

Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model designed for difficult multi-step tasks such as math proofs, code synthesis and debugging, logical reasoning, and agentic planning. It outputs structured thinking traces by default, emphasizing stability over long chains of thought, efficient inference scaling, and strong instruction following. Suited for agent frameworks, tool use, retrieval-heavy workflows, and benchmarks requiring step-by-step solutions, it supports long detailed outputs and faster generation via throughput-optimized techniques, operating exclusively in thinking mode.

Context: 262.1K
Input: $0.10/M
Output: $0.40/M