Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Sber / GigaChat 3

GigaChat 3 Pro

Sber language model listed in Cloud.ru Foundation Models with a 262,144-token context and separate input and output pricing.

availableClosed weightsText generation
Official documentation (opens in a new tab)Reviewed 14 Oct 2026
4 of 17 specification fields collected
Context window262.1K262,144 tokens
Maximum outputNot collectedAwaiting source review
Input / 1M tokensRUB 73.0292Cloud.ru Foundation Models
Output / 1M tokensRUB 176.3876RUB · billing 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
262,144 tokensSource for Context / input limit (opens in a new tab)

Exact maxModelLength in the public page data; the card abbreviates this as 262K.

Maximum input tokens
Not collected
Maximum output
Not collected
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
Languages
Not collected
Context caching
Not collected

Native GigaChat session caching is not established for the Cloud.ru route.

Input modalities
TextSource for Input modalities (opens in a new tab)

LLM catalog entry. Additional modalities are not inferred from older GigaChat models.

Billing basis
Cloud.ru Foundation Models tariff version 261002, effective 2 October 2026. RUB including 22% VAT where applicable. Pay-as-you-go; input and generated tokens billed separately. Unit estimates are before reporting-period rounding: each input/output monetary component is rounded upward to the nearest kopek. This is a separate tariff from native GigaChat business pricing; its RUB 600 minimum and free cache hits are not copied to this route.Source for Billing basis (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.

Cloud.ru Foundation Models

Provider source (opens in a new tab)
API model ID
GigaChat/GigaChat-3-Pro
Access
POST https://foundation-models.api.cloud.ru/v1/chat/completions with a Cloud.ru API key and the exact catalog model selector. No account-specific entitlement tested.
Regions
Cloud.ru catalog listing; internal versus external hosting not yet specified in the reviewed model-overview table.
Context / input limit
262,144 tokensSource for Context / input limit (opens in a new tab)

Full value in embedded public catalog data.

Context caching
Not collected

No Cloud.ru-specific cache support established.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 14 Oct 2026
CategoryUsageRateUnit
Cloud.ru pay-as-you-goInput1RUB 73.02921M tokens
Cloud.ru pay-as-you-goOutput1RUB 176.38761M tokens

Rate conditions

  1. Cloud.ru Foundation Models tariff version 261002, effective 2 October 2026. RUB including 22% VAT where applicable. Pay-as-you-go; input and generated tokens billed separately. Unit estimates are before reporting-period rounding: each input/output monetary component is rounded upward to the nearest kopek. This is a separate tariff from native GigaChat business pricing; its RUB 600 minimum and free cache hits are not copied to this route.
Pricing source (opens in a new tab)

Data & enterprise terms

Retention, data residency and upstream transmission policy for this exact selector not verified.

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.

Cloud.ru Foundation Models

GigaChat/GigaChat-3-Pro
Not verified

No model-specific Cloud.ru cache policy or rate verified; native GigaChat caching is not inherited.

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.

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

Cloud.ru lists GigaChat/GigaChat-3-Pro separately from public ai-sage GigaChat checkpoints. No matching GigaChat 3 Pro weight artifact was identified in the reviewed ai-sage inventory. This classification applies to the exact hosted selector and does not claim that the whole GigaChat 3 family is closed.

Classification evidence (opens in a new tab)

Sources reviewed