Qwen3 235B A22B (Instruct 2507)
Toolsqwen/qwen3-235b-a22bText · 262K context · Jul 2025 · 8 upstreamsupstream上游
Qwen3 235B A22B (Instruct 2507) is Qwen's open-weight, non-thinking Mixture-of-Experts model with 235B total and 22B active parameters. It is licensed Apache-2.0 and covers 119 languages and dialects, coding and tool use.
Needs your own keyTo use Qwen3 235B A22B (Instruct 2507), add a key from AIHubMix, OpenRouter, Nous Research or 5 more. AnyRouter adds no fee.
- contextngữ cảnh上下文
- 262K
- inputđầu vào输入 / 1M (list)
- $0.09
- outputđầu ra输出 / 1M (list)
- $0.35
- routestuyến路由
- 8
- speed, 24htốc độ, 24h速度,24h
- No data yetChưa có dữ liệu暂无数据
Upstreams
8- 1AIHubMixYour keynot addedBilled to your key
- 2OpenRouterYour keynot addedBilled to your key
- 3Nous ResearchYour keynot addedBilled to your key
- 4InfronYour keynot addedBilled to your key
- 5NanoGPTYour keynot addedBilled to your key
- 6FluenceYour keynot addedBilled to your key
- 7QiniuYour keynot addedBilled to your key
- 8RequestyYour keynot addedBilled to your key
Benchmarks
- GPQA Diamond
- 70.7%
Benchmark data from Epoch AI (CC-BY 4.0).
Quick start
curl
curl https://anyrouter.dev/api/v1/chat/completions \
-H "Authorization: Bearer $ANYROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen/qwen3-235b-a22b",
"messages": [
{
"role": "user",
"content": "Say hi in 3 words."
}
]
}'Details
- Owner
- Qwen
- Kind
- Chat
- Released
- Jul 2025
- Context
- 262K
- Data policy
- Provider retention
- Endpoint
/api/v1/chat/completions
- Reasoning, math and coding in thinking mode
- Fast general chat in non-thinking mode
- Agents that call external tools
Architecture and licenseKiến trúc và giấy phép架构与许可
- TypeLoại类型
- Mixture of experts[1]
- Native contextNgữ cảnh gốc原生上下文
- 131,072[1]
- LicenseGiấy phép许可
- Apache-2.0 · Open weightsTrọng số mở开放权重[1]
StrengthsĐiểm mạnh优势[1],[2]
- Thinking and non-thinking modes in one model
- Tool calling in both modes
- 119 languages and dialects
Known limitsGiới hạn đã biết已知局限[1]
- Context past 32,768 tokens needs YaRN, which can hurt short-text quality
API notesGhi chú APIAPI 说明[1]
- enable_thinking switch, plus /think and /no_think soft switches
- Supports tool calling
Links and versionsLiên kết và phiên bản链接与版本
- AnnouncementBài công bố发布公告
- qwenlm.github.io
- Model cardThẻ mô hình模型卡
- huggingface.co
- PaperBài báo论文
- arxiv.org
- DocsTài liệu文档
- qwen.readthedocs.io
SourcesNguồn来源
- [1]Qwen/Qwen3-235B-A22B model cardaccessedtruy cập访问于 2026-10-14
- [2]Qwen3: Think Deeper, Act Fasteraccessedtruy cập访问于 2026-10-14
- [3]Qwen3 Technical Reportaccessedtruy cập访问于 2026-10-14
Upstreams and pricingUpstream và giá上游与价格
Share cards9 images









AliasesBí danh别名 (1)
qwen/qwen3-235b-a22b-2507
Uptime + latency
—recent checks · all routes
No health checks recorded for this model yet.
24h
No traffic in the last 24h.
Across all upstreams
Loading usage…