Compare

Gemma-Sea-Lion-V4-27b-IT vs Embeddinggemma-300m

Pricing per million tokens, context window, capabilities — pulled from each provider's public docs. All 2 are available via the same AIgateway OpenAI-compatible endpoint; flip the model string to switch.

Search2/4
Gemma-Sea-Lion-V4-27b-IT
aisingapore/gemma-sea-lion-v4-27b-it
Embeddinggemma-300m
google/embeddinggemma-300m
Provider
AI Singapore
Google
Family
Gemma
Gemma
Modality
text
embedding
Context window
4,096 tok
Max output
4,096 tok
Released
2025-09-23
2025-09-04
License
Open-weight
Open-weight
Input price
$0.300 /1M
$0.020 /1M
Output price
$0.500 /1M
$0.0000 /1M
Tools
Streaming
yes
Vision
yes
JSON mode
Reasoning
Prompt caching
Batch API
Try it
Open in playground →
View model →
Gemma-Sea-Lion-V4-27b-IT
aisingapore/gemma-sea-lion-v4-27b-it
Full spec →

SEA-LION stands for Southeast Asian Languages In One Network, which is a collection of Large Language Models (LLMs) which have been pretrained and instruct-tuned for the Southeast Asia (SEA) region.

Strengths
  • General-purpose chat
  • Long context
  • Tool use
Use cases
ChatbotsContent generationAgentic workflows
Embeddinggemma-300m
google/embeddinggemma-300m
Full spec →

EmbeddingGemma is a 300M parameter, state-of-the-art for its size, open embedding model from Google, built from Gemma 3 (with T5Gemma initialization) and the same research and technology used to create Gemini models. EmbeddingGemma produces vector representations of text, making it well-suited for search and retrieval tasks, including classification, clustering, and semantic similarity search. This model was trained with data in 100+ spoken languages.

Strengths
  • Semantic similarity
  • Vector search
Use cases
RAGSemantic searchRecommendation

Compare with another

Gemma-Sea-Lion-V4-27b-IT vs Gemma-2b-IT-Lora
aisingapore/gemma-sea-lion-v4-27b-it · google/gemma-2b-it-lora
Embeddinggemma-300m vs Gemma-2b-IT-Lora
google/embeddinggemma-300m · google/gemma-2b-it-lora
Gemma-Sea-Lion-V4-27b-IT vs Gemma-7b-IT-Lora
aisingapore/gemma-sea-lion-v4-27b-it · google/gemma-7b-it-lora
Gemma-4-26b-A4b-IT vs Gemma-Sea-Lion-V4-27b-IT
google/gemma-4-26b-a4b-it · aisingapore/gemma-sea-lion-v4-27b-it
Embeddinggemma-300m vs Gemma-7b-IT-Lora
google/embeddinggemma-300m · google/gemma-7b-it-lora
Gemma-4-26b-A4b-IT vs Embeddinggemma-300m
google/gemma-4-26b-a4b-it · google/embeddinggemma-300m
SWITCH BETWEEN THEM

One key, all 2, one line different.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.aigateway.sh/v1",
    api_key="sk-aig-...",
)

# Gemma-Sea-Lion-V4-27b-IT
client.chat.completions.create(
    model="aisingapore/gemma-sea-lion-v4-27b-it",
    messages=[{"role":"user","content":"hello"}],
)

# Embeddinggemma-300m
client.chat.completions.create(
    model="google/embeddinggemma-300m",
    messages=[{"role":"user","content":"hello"}],
)
Get an AIgateway keyRun an eval on these →