Skip to content
Model infoModelsSnapshot: 15 Oct 2026

360 / Zhinao / Zhinao proprietary language models

360Zhinao Pro 32K (260106)

Native 32K Zhinao Pro backend served by the 360zhinao/360zhinao-pro selector.

Language models (LLMs)
availableClosed weightsText generation
Official documentation (opens in a new tab)Reviewed 14 Oct 2026
5 of 16 specification fields collected
Context window32K32,000 tokens
Maximum output8.2K8,192 tokens
Input billingSee rates360 Zhinao API
Output billingSee ratesPublished units and conditions below

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
32,000 tokensSource for Context / input limit (opens in a new tab)

Native backend contract on the detailed card, not the virtual route headline.

Maximum output
8,192 tokensSource for Maximum output (opens in a new tab)

Native backend contract on the detailed card, not the virtual route headline.

Input modalities
TextSource for Input modalities (opens in a new tab)
Output modalities
TextSource for Output modalities (opens in a new tab)
Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected
Streaming
Not collected
Batch processing
Not collected
Fine-tuning
Not collected
Knowledge cutoff
Not collected
Release date
Not collected
Parameters
Not collected
Architecture
Not collected
Languages
Not collected
Context caching
SupportedSource for Context caching (opens in a new tab)

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

360 Zhinao API

Provider source (opens in a new tab)
API model ID
360zhinao/360zhinao-pro
Access
Native 360 backend currently listed. API key, permissions and protocol compatibility required.
Regions
China platform; exact deployment region and data residency terms not verified.
backend
360zhinao-pro-32k-260106Source for backend (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 14 Oct 2026
CategoryUsageRateUnit
Text inferenceInput1CN¥2.001M tokens
Text inferenceOutput1CN¥5.001M tokens
Prompt cachingCache write1CN¥2.501M tokens
Prompt cachingCache read1CN¥0.201M tokens

Rate conditions

  1. Native 360 backend rate; CNY per million tokens. Contract pricing prevails.
Pricing source (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

360 Zhinao API

360zhinao/360zhinao-pro
Documented

This specific catalog entry publishes cache read and write rates.

Support evidence (opens in a new tab)
How it works
Automatic prefix cachingSource for How it works (opens in a new tab)
Minimum reusable input
16-token storage units; content shorter than 16 tokens is not cachedSource for Minimum reusable input (opens in a new tab)
Lifetime & refresh
Evicted after inactivity; timeout is unspecified and hits are not guaranteedSource for Lifetime & refresh (opens in a new tab)
How to enable it
No code or interface changes requiredSource for How to enable it (opens in a new tab)
Usage fields
prompt_cache_hit_tokens + prompt_cache_miss_tokens = prompt_tokensSource for Usage fields (opens in a new tab)
Billing rules
Actual cache hits billed at the model-card rate; contract pricing takes precedenceSource for Billing rules (opens in a new tab)
Limits & data boundaries
Exact prefix from token zero, including identical roles. Interior repetition does not qualify. Third-party hosted cache accounting follows the supplier. Not every model enables caching.Source for Limits & data boundaries (opens in a new tab)
Cache reads, writes & storage
ChargeApplies toRate / unit
Cache write1Prompt cachingCN¥2.50 / 1M tokensPricing evidence (opens in a new tab)
Cache read1Prompt cachingCN¥0.20 / 1M tokensPricing evidence (opens in a new tab)

Rate conditions

  1. Native 360 backend rate; CNY per million tokens. Contract pricing prevails.

Observed 14 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.

Caching reviewed 14 Oct 2026

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

Closed-weight classification is inferred for this specifically named native 360 model or service from the developer’s corporate/model catalog and public weight inventory. Exact weights for this identity were not found among its published checkpoints. A hosted third-party backend is not counted as a native 360 model; named speech entries are systems rather than independently verified base checkpoints.

Classification evidence (opens in a new tab)

Lifecycle dates

Public catalog listing date5 Aug 2026Source (opens in a new tab)

Sources reviewed