GigaChat Embeddings 9.3B is GigaChat (Sber)'s embedding model with a 4K context window. A large-scale text embedding model from the GigaChat family designed for semantic search and representation tasks.
Specifications
Canonical IDgigachat-embeddings-9-3b
TypeEmbedding
StatusActive
CreatorGigaChat (Sber)GigaChat (Sber)
Context Window4K tokens
Input ModalitiesText
Output ModalitiesEmbedding
Parameters3B
Embedding Dimensions2048

Capabilities

Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text·
Image·
Audio·
Video·
Embedding✓
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Cheapest Instances to Run It

Cloud GPU instances that can host GigaChat Embeddings 9.3B, ranked by cheapest on-demand price. The model needs about 7 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.

All clouds
FP16 (full precision)
US Dollar ($)
Instance
Cloud
GPU
VRAM
Price
Cheapest region
Standard_NV4as_v4AzureAMD Radeon Instinct MI2516 GB$0.233/hr
g5g.xlargeAWST4g16 GB$0.420/hr
Standard_NV8as_v4AzureAMD Radeon Instinct MI2516 GB$0.466/hr
7 more instances can run GigaChat Embeddings 9.3B
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
GigaChat Embeddings 9.3B—4K——Current
Embed 5 Fast128K$0.080—Deprecating
Embed 5 Pro128K$0.120—Deprecating
Text Embedding 52K$0.025—Deprecating
Embed 5 Fast Image——$0.400—Available
Embed 5 Fast Text——$0.080—Available
Embed 5 Pro Image——$0.500—Available
Embed 5 Pro Text——$0.120—Available
Voyage 432K$0.060—Available
Voyage 4 Large32K$0.120—Available
Voyage 4 Lite32K$0.020—Available

Model IDs

gigachat-embeddings-9-3b
gigachat/GigaEmbeddings-3B-2025-09