AI TOOLS RADAR
Submit
All models / QWEN
qwen logo
qwen

Qwen: Qwen3 235B A22B Thinking 2507

Source description (English)

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...

View source on OpenRouter Hugging Face
Overview

Model specifications

Context
131,072 tokens
Maximum output
117,964 tokens
Architecture
text->text
Tokenizer
Qwen3
Knowledge cutoff
2025-06-30
Moderated
No
OPENROUTER

Complete pricing

Synchronized OpenRouter rates. Token prices are shown per one million tokens.

Input
$0.23
per 1M tokens
Output
$2.3
per 1M tokens
API

Model configuration

Reasoning

Reasoning required
Yes
Default parameters
No
API

Quick start

Set OPENROUTER_API_KEY locally. Python requires requests; JavaScript runs in Node.js. Keep the key on the server.

API documentation

curl --fail-with-body https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"qwen/qwen3-235b-a22b-thinking-2507","messages":[{"role":"user","content":"Hello!"}]}'
Capabilities

Input → Output

Input
text
Output
text
Reasoning

No

API

Supported API parameters

frequency_penaltyinclude_reasoninglogprobsmax_tokenspresence_penaltyreasoningrepetition_penaltyresponse_formatseedstoptemperaturetool_choicetoolstop_ktop_logprobstop_p
Available providers

3 providers

Checked: September 7, 2026

Live providers on OpenRouter

Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.

OpenRouter

Alibaba

Not provided
Context
131K
Maximum output
118K
Input
$0.23
Output
$2.3
Cache read
Not provided
Cache write
Not provided

Novita

fp8
Context
131K
Maximum output
33K
Input
$0.3
Output
$3
Cache read
Not provided
Cache write
Not provided

Venice

fp8
Context
128K
Maximum output
16K
Input
$0.45
Output
$3.5
Cache read
Not provided
Cache write
Not provided
qwen

4 models

All models
qwen logoqwen

Qwen: Qwen3.8 Omni Flash

Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding. It is suited for audio-video analysis and summarization,...

Context
1M
Input
text · image · audio · video
Output
text
Input: $0.15Output: $0.47per 1M tokens
View model details →
qwen logoqwen

Qwen: Qwen3.8 Max (0902)

Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts text, image, and video input and returns text,...

Context
1M
Input
text · image · video
Output
text
Input: $2Output: $6per 1M tokens
View model details →
qwen logoqwen

Qwen: Qwen3.8 Flash

Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-video analysis.

Context
1M
Input
text · image · video
Output
text
Input: $0.15Output: $0.47per 1M tokens
View model details →
qwen logoqwen

Qwen: Qwen3.8 27B

Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...

Context
1M
Input
text · image · video
Output
text
Input: $0.42Output: $3per 1M tokens
View model details →