Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Baichuan AI / Baichuan 3

Baichuan3-Turbo-128k

General language API variant for chat, generation and document workflows.

Language models (LLMs)
availableClosed weightsText generation
Official documentation (opens in a new tab)Reviewed 14 Oct 2026
6 of 16 specification fields collected
Context window128KSee specification notes below
Maximum output2K2,048 tokens
Input billingSee ratesBaichuan native platform
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
128KSource for Context / input limit (opens in a new tab)

Official context label; exact integer is not specified. Input and output must fit the service context.

Maximum output
2,048 tokensSource for Maximum output (opens in a new tab)

Current general chat request schema specifies max_tokens from 1 to 2,048. Do not copy the medical API’s larger output allowance.

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

The explicit function-tool list omits this 128K variant; omission is not proof that every tool mode is unsupported.

Structured output
SupportedSource for Structured output (opens in a new tab)

JSON object mode, requiring a JSON instruction in system/user content. This is not a strict JSON Schema guarantee; length termination may truncate JSON.

Streaming
SupportedSource for Streaming (opens in a new tab)

General chat contract offers synchronous and SSE responses.

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
Not collected

Access & pricing

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

Baichuan native platform

Provider source (opens in a new tab)
API model ID
Baichuan3-Turbo-128k
Access
Listed in the current general API selector enum. Requires an account and API key; no authenticated inference performed.
Regions
Native China platform. No additional regional endpoint or residency guarantee inferred.
API endpoint URL
POST https://api.baichuan-ai.com/v1/chat/completionsSource for API endpoint URL (opens in a new tab)
rateLimit
Identity-verified accounts: 120 RPM; unverified: 12 RPM and 300 requests/daySource for rateLimit (opens in a new tab)

Account quota, not intrinsic model throughput; published limits can change.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 14 Oct 2026
CategoryUsageRateUnit
Text inferenceInput1CN¥24.001M tokens
Text inferenceOutput1CN¥24.001M tokens
ToolsWeb search2CN¥0.03search invocation

Rate conditions

  1. Both input and output are billed at the listed rate. Converted exactly from CNY per 1,000 tokens by multiplying by 1,000; no currency conversion. All-day published pricing.
  2. Additional charge when the API invokes the optional web-search service. Number of searches is determined by the service, not necessarily one per user question.
Pricing source (opens in a new tab)

Data & enterprise terms

Platform privacy policy covers API developers and end users. Personal data deletion may leave backups until backup refresh. No model-specific zero-retention or no-training guarantee is established here.

Read the service policy (opens in a new tab)

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.

Baichuan native platform

Baichuan3-Turbo-128k
Not verified

No model-specific prompt-cache contract or price verified.

How it works
Not collected

No model-specific prompt-cache contract or price verified.

Minimum reusable input
Not collected

No model-specific prompt-cache contract or price verified.

Lifetime & refresh
Not collected

No model-specific prompt-cache contract or price verified.

How to enable it
Not collected

No model-specific prompt-cache contract or price verified.

Usage fields
Not collected

No model-specific prompt-cache contract or price verified.

Billing rules
Not collected

No model-specific prompt-cache contract or price verified.

Limits & data boundaries
Not collected

No model-specific prompt-cache contract or price verified.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

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

Inferred from the provider’s named proprietary API or internally trained research release, checked against its public weight inventory. No exact weights for this variant were found; similarly named open-weight Baichuan releases are excluded.

Classification evidence (opens in a new tab)

Sources reviewed