Infomaniak
BGE Multilingual Gemma2
Canonical ID:
infomaniak/bge_multilingual_gemma2
Embedding model for semantic search, retrieval, clustering, and ranking pipelines
Overview
- Provider
-
Infomaniak
- Family
- text-embedding
- Release date
- 2024-07-25
- Last updated
- 2026-08-01
- Input modalities
- text
- Output modalities
- text
Pricing and Limits
Token pricing
- Input
- $0.08/1M
- Output
- $0/1M
- Cached input
- N/A
Context and output
- Context window
- 8,000
- Max output tokens
- 3,584
- Qualified ID
- infomaniak/bge_multilingual_gemma2
Model Summary
BGE Multilingual Gemma2 is a model listing in the Infomaniak provider catalog. It is categorized under the text-embedding family.
The model supports text modalities across input/output paths. Reported context capacity is 8,000. Pricing is listed at $0.08/1M input and $0/1M output.
More From Infomaniak
Related models from the same provider catalog.
Infomaniak
All-MiniLM-L12-v2
infomaniak/mini_lm_l12_v2
Infomaniak
Apertus v1.5 70B
infomaniak/swiss-ai/Apertus-v1.5-70B
Infomaniak
Gemma 4 31B IT
infomaniak/google/gemma-4-31B-it
Infomaniak
Kimi K2.6
infomaniak/moonshotai/Kimi-K2.6
Infomaniak
Ministral 3 14B Instruct
infomaniak/mistralai/Ministral-3-14B-Instruct-2512
Infomaniak
Mistral Small 4
infomaniak/mistralai/Mistral-Small-4-119B-2603
Infomaniak
Nemotron 3 Nano 30B A3B FP8
infomaniak/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8
Infomaniak
Qwen3.5 122B-A10B FP8
infomaniak/Qwen/Qwen3.5-122B-A10B-FP8
Same Family: text-embedding
Comparable models in the same family across providers.
| Model | Provider | Context | Input | Output | Flags |
|---|---|---|---|---|---|
|
All-MiniLM-L12-v2
infomaniak/mini_lm_l12_v2
|
Infomaniak
|
128 | $0/1M | $0/1M |
|
|
All-MiniLM-L6-v2
digitalocean/all-mini-lm-l6-v2
|
DigitalOcean
|
256 | $0.009/1M | $0/1M |
|
|
E5 Large v2
digitalocean/e5-large-v2
|
DigitalOcean
|
512 | $0.02/1M | $0/1M |
|
|
GTE Large (v1.5)
digitalocean/gte-large-en-v1.5
|
DigitalOcean
|
8,192 | $0.09/1M | $0/1M |
|
|
Multi-QA-mpnet-base-dot-v1
digitalocean/multi-qa-mpnet-base-dot-v1
|
DigitalOcean
|
512 | $0.009/1M | $0/1M |
|
|
Qwen3 Embedding 0.6B
nearai/Qwen/Qwen3-Embedding-0.6B
|
NEAR AI Cloud
|
32,768 | $0.01/1M | $0.01/1M |
|
|
Qwen3 Embedding 0.6B
digitalocean/qwen3-embedding-0.6b
|
DigitalOcean
|
8,000 | $0.04/1M | $0/1M |
|
|
Qwen3-Embedding-8B
inferx/Qwen3-Embedding-8B
|
InferX
|
32,768 | $0/1M | $0/1M |
|
|
Text Embedding 005
vercel/google/text-embedding-005
|
Vercel AI Gateway
|
8,192 | $0.03/1M | $0/1M |
|
|
text-embedding-3-large
azure-cognitive-services/text-embedding-3-large
|
Azure Cognitive Services
|
8,192 | $0.13/1M | $0/1M |
|