Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Moonshot AI / Kimi / Moonshot v1

Moonshot v1 8K

Retired 8K text API configuration of the Moonshot v1 family.

Language models (LLMs)
retiredClosed weightsText generation
Official documentation (opens in a new tab)Reviewed 14 Oct 2026
7 of 17 specification fields collected
Context window8.2K8,192 tokens
Maximum outputNot collectedAwaiting source review
Input billingSee ratesMoonshot China (retired)
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
8,192 tokensSource for Context / input limit (opens in a new tab)

Input and output share the context budget. Only the 8K example explicitly gives 8,192 tokens.

Maximum output
Not collected
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
SupportedSource for Tool calling (opens in a new tab)

The archived Tool Use section explicitly demonstrates this selector. The same snapshot contains an older FAQ saying function calling was planned; the concrete API example and April 2024 launch log establish that the FAQ is stale.

Structured output
Not collected
Streaming
SupportedSource for Streaming (opens in a new tab)

Archived v1 documentation describes server-sent events.

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)

Historical explicit-cache example, not a current service guarantee.

outputBudget
max_tokens must fit within context after input tokens; a default example is not a model maximumSource for outputBudget (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.

Moonshot China (retired)

Provider source (opens in a new tab)
API model ID
moonshot-v1-8k
Access
Retired August 31, 2026. Official changelog says requests now return model-not-found errors. No inference performed.
Regions
Historical native platform or research access only; no current regional availability is asserted.
API endpoint URL
POST https://api.moonshot.cn/v1/chat/completionsSource for API endpoint URL (opens in a new tab)

Historical route; this model ID is retired.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 14 Oct 2026
CategoryUsageRateUnit
Historical text inferenceArchived input1CN¥12.001M tokens
Historical text inferenceArchived output1CN¥12.001M tokens

Rate conditions

  1. Historical cookbook documentation, pinned at commit 25a9e46d2391dd4817d28ab980dac69eb59b582c: both input and output are billed at the listed token rate. Effective price date and later revisions are not established. Retired model; not a current offer. No currency conversion.
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.

Moonshot China (retired)

moonshot-v1-8k
Documented
Support evidence (opens in a new tab)
How it works
Historical explicit Context Cache objectsSource for How it works (opens in a new tab)
Minimum reusable input
Not collected

Historical minimum prefix size unverified.

Lifetime & refresh
Not collected

No model-specific TTL guarantee verified.

How to enable it
Create via /v1/caching; reference cache_id in a message with role=cacheSource for How to enable it (opens in a new tab)
Usage fields
Not collected

Historical accounting fields unverified.

Billing rules
Not collected

No verified historical cache rate attached; ordinary input prices do not establish a cache discount.

Limits & data boundaries
Legacy manual cache example. The current K3 automatic cache, TTL tiers and charges must not be assigned to v1.Source for Limits & data boundaries (opens in a new tab)

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

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

Inferred from the named proprietary API configuration or internal trained research model in official documentation, checked against the developer’s published-weight inventory. Exact weights for this release were not found. Current open-weight Kimi releases are excluded; API branding alone does not establish a separate checkpoint.

Classification evidence (opens in a new tab)

Lifecycle dates

Native API retired31 Aug 2026Source (opens in a new tab)

Sources reviewed