Post-Cutoff
Search For AI agents

Nanbeige (Kanzhun / BOSS Zhipin)Nanbeige4.3 familyCurrentReasoning modelReleased 24 Oct 2026

Nanbeige4.3-33B

Open-weight (Apache 2.0) agentic coding model from the Nanbeige team at Kanzhun, the company behind China’s BOSS Zhipin recruitment app.

Model idNanbeige/Nanbeige4.3-33B

PricePrice not published

Checked26 October 2026

No published training cutoff

At least436events since its release on 24 October 2026

12 historic, 83 major. 20 days of news.

Nanbeige (Kanzhun / BOSS Zhipin) doesn’t publish a training cutoff, so we count from its release date. The real gap is larger.

Five things it has never heard of

How to call it

2 ways to use Nanbeige4.3-33B, with the model id each provider expects.

Providers, model ids, endpoints and docs for Nanbeige4.3-33B
ProviderModel idEndpointDocs
Hugging Face Nanbeige/Nanbeige4.3-33B huggingface.co
Hugging Face (base model) Nanbeige/Nanbeige4.3-33B-Base huggingface.co

Pricing

Price not published.

No price source linked. Checked 26 October 2026.

Specs

Input
Text
Output
Text
Context window
524,288 tokens
Max output
262,144 tokens
Open weights
Yes
Licence
Apache-2.0
Training cutoff
Not published
Released
24 October 2026
Status
Current
Type
Reasoning model

What stands out

What its maker marketed at launch, and what people found later, each with its source.

  • 512K context in a ~33B open model for coding agents

    Supports up to 524,288 tokens; chat template has enable_thinking and preserve_thinking (keep earlier reasoning across turns, recommended for multi-turn tool use and code agents); XML (recommended) or JSON tool calls.

    Source: huggingface.co

  • Teacher model for small-agent distillation

    Built as the flagship teacher of the Nanbeige4.3 series, whose agent skills are to be distilled into smaller models such as a planned Nanbeige4.3-3B.

    Source: huggingface.co

Notes

~33.1B parameters (safetensors). Self-reported to lead Qwen3.8-27B, Muse-Glimmer-30B and Gemma4-31B on most agentic coding and office benchmarks (Terminal-Bench 2.1/4.0, SWE-Atlas-QnA, NL2Repo, DeepSWE, GDPval, Tau3-Bench…); not independently verified. Recommended: temperature 1.0, top_p 0.95, up to 65,536 new tokens for agentic tasks; 0.6 and up to 262,144 for reasoning/chat. Runs on Transformers, SGLang, vLLM (Qwen3-style reasoning and tool parsers). No hosted API found.

vllm serve Nanbeige/Nanbeige4.3-33B --max-model-len 524288