01.AI / Yi / Yi proprietary language models

Yi-Large

Large language API variant for complex language understanding and generation.

Language models (LLMs)

historicalClosed weightsText generation

Official documentation (opens in a new tab)Reviewed 14 Oct 2026
5 of 17 specification fields collected

Context window32KSee specification notes below

Maximum outputNot collectedAwaiting source review

Input billingSee rates01.AI China API (historical)

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: 32KSource for Context / input limit (opens in a new tab)
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: Not collected
Structured output: Not collected
Streaming: SupportedSource for Streaming (opens in a new tab)
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
parameterScale: Hundred-billion-parameter scaleSource for parameterScale (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.

01.AI China API (historical)

Provider source (opens in a new tab)

API model ID: yi-large
Access: Historical direct-model catalog; public China API service has stopped. No authenticated inference or API-key provisioning performed.
Regions: Host-specific historical service; no current availability or residency guarantee inferred.
context: 32KSource for context (opens in a new tab)
API endpoint URL: POST https://api.lingyiwanwu.com/v1/chat/completionsSource for API endpoint URL (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 14 Oct 2026
Category	Usage	Rate	Unit
Historical text inference	Input¹	CN¥20.00	1M tokens
Historical text inference	Output¹	CN¥20.00	1M tokens

Rate conditions

Price in the December 5, 2024 archive, charged on input plus output tokens; conversation history is billable input. Not the final pre-shutdown price and 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.

01.AI international API (suspended)

Provider source (opens in a new tab)

API model ID: yi-large
Access: International homepage announces API suspension starting August 25 and directs users to the China site. The year is not stated; no exact suspension date is invented. The China alternative is now shut down.
Regions: Host-specific historical service; no current availability or residency guarantee inferred.
context: 32KSource for context (opens in a new tab)
API endpoint URL: POST https://api.01.ai/v1/chat/completionsSource for API endpoint URL (opens in a new tab)
outputBudget: Input plus output must fit the model context; max_tokens is caller-controlledSource for outputBudget (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 14 Oct 2026
Category	Usage	Rate	Unit
Historical text inference	Input¹	$3.00	1M tokens
Historical text inference	Output¹	$3.00	1M tokens

Rate conditions

International documentation still displays this price, but the homepage announces service suspension. Historical reference only, not a current purchasable rate. Input and output are separately priced at the same listed amount.

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.

01.AI China retrieval service (historical)

Provider source (opens in a new tab)

API model ID: yi-large-rag
Access: Retrieval-enhanced service explicitly built on Yi-Large, including web retrieval and contact-based private knowledge-base access. China public service stopped.
Regions: Host-specific historical service; no current availability or residency guarantee inferred.
context: 16KSource for context (opens in a new tab)
retrieval: Web retrieval; private knowledge base by requestSource for retrieval (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 14 Oct 2026
Category	Usage	Rate	Unit
Historical text inference	Input¹	CN¥25.00	1M tokens
Historical text inference	Output¹	CN¥25.00	1M tokens

Rate conditions

Archived retrieval-enhanced service rate, charged on total input plus output tokens. This is not the plain Yi-Large price. Separate per-search fees were not established in this snapshot.

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.

OpenRouter (no active route)

Provider source (opens in a new tab)

API model ID: 01-ai/yi-large
Access: Current endpoint inventory has no active endpoints; the live OpenRouter catalog omits this model. Historical identity does not establish an available route.
Regions: Host-specific historical service; no current availability or residency guarantee inferred.

Endpoint pricing has not been collected. Check the provider for applicable rates.

Data & enterprise terms

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

NVIDIA (historical listing)

Provider source (opens in a new tab)

API model ID: Not collected
Access: The international site advertises NVIDIA distribution, but the linked model card now renders a 404 page. Current NVIDIA inference availability and terms are not established.
Regions: Host-specific historical service; no current availability or residency guarantee inferred.

Endpoint pricing has not been collected. Check the provider for applicable rates.

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.

01.AI China API (historical)

yi-large

Not verified

No model-specific API prompt-cache contract verified.

How it works: Not collected
Minimum reusable input: Not collected
Lifetime & refresh: Not collected
How to enable it: Not collected
Usage fields: Not collected
Billing rules: Not collected
Limits & data boundaries: Not collected

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

01.AI international API (suspended)

yi-large

Not verified

No model-specific API prompt-cache contract verified.

How it works: Not collected
Minimum reusable input: Not collected
Lifetime & refresh: Not collected
How to enable it: Not collected
Usage fields: Not collected
Billing rules: Not collected
Limits & data boundaries: Not collected

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

01.AI China retrieval service (historical)

yi-large-rag

Not verified

No model-specific API prompt-cache contract verified.

How it works: Not collected
Minimum reusable input: Not collected
Lifetime & refresh: Not collected
How to enable it: Not collected
Usage fields: Not collected
Billing rules: Not collected
Limits & data boundaries: Not collected

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

OpenRouter (no active route)

01-ai/yi-large

Not verified

No model-specific API prompt-cache contract verified.

How it works: Not collected
Minimum reusable input: Not collected
Lifetime & refresh: Not collected
How to enable it: Not collected
Usage fields: Not collected
Billing rules: Not collected
Limits & data boundaries: Not collected

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

NVIDIA (historical listing)

Not verified

No model-specific API prompt-cache contract verified.

How it works: Not collected
Minimum reusable input: Not collected
Lifetime & refresh: Not collected
How to enable it: Not collected
Usage fields: Not collected
Billing rules: Not collected
Limits & data boundaries: Not collected

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 for this named proprietary API/research variant from the developer’s release description and public weight inventory. Exact weights for this variant were not found. Public Yi, Yi-1.5, Yi-Coder and Yi-VL checkpoints remain excluded; API naming alone does not prove an independently trained base.

Classification evidence (opens in a new tab)

Lifecycle dates

China public API service stopped3 Sept 2026Source (opens in a new tab)

Sources reviewed

01.AI Yi: cn docs archive (opens in a new tab)Reviewed 14 Oct 2026

01.AI Yi: weights (opens in a new tab)Reviewed 14 Oct 2026

01.AI Yi: global docs rendered (opens in a new tab)Reviewed 14 Oct 2026

01.AI Yi: global platform rendered (opens in a new tab)Reviewed 14 Oct 2026

01.AI Yi: router large (opens in a new tab)Reviewed 14 Oct 2026

01.AI Yi: nvidia rendered (opens in a new tab)Reviewed 14 Oct 2026

01.AI Yi: router models (opens in a new tab)Reviewed 14 Oct 2026

01.AI Yi: cn platform rendered (opens in a new tab)Reviewed 14 Oct 2026

Model notes

11 historical Yi variants. Historical proprietary Yi API variants and named research releases, excluding public Yi weights. China API retirement, international suspension and mixed-model routing are kept distinct from model identity.

Historical API variant retained from the December 5, 2024 catalog. The China platform stopped public inference at 24:00 on September 3, 2026. This does not establish retirement of every private enterprise deployment or underlying checkpoint.

Output examples do not establish maximum output limits. Reasoning ability in marketing does not establish a separate reasoning mode. Numeric prices below are historical observations, not current offers.

yi-large-rag is an access configuration backed by Yi-Large, not an additional confirmed weight release.

Check against your workload

Try representative inputs, measure task success and total cost, then check the exact endpoint’s data policy.

Read our methodology