AI Singapore logo

SEA-LION Llama3 8B SEA-LION V2.1 Instruct

Pricing & Specs API
Free REST API for prices, specs and benchmarks
SEA-LION Llama3 8B SEA-LION V2.1 Instruct is AI Singapore's language model. An 8-billion-parameter instruction-tuned SEA-LION V2.1 model built on Llama 3, optimized for Southeast Asian language tasks.
Specifications
Canonical IDaisingapore-llama3-sealion-2-1-8b-instruct
TypeLanguage
StatusActive
CreatorAI SingaporeAI Singapore
Input ModalitiesText
Output ModalitiesText
Parameters8B

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 SEA-LION Llama3 8B SEA-LION V2.1 Instruct, ranked by cheapest on-demand price. The model needs about 19 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
g2-standard-4GCPnvidia-l424 GB$0.705/hrus-east4
g6.xlargeAWSL422 GB$0.805/hrus-east-1
g2-standard-8GCPnvidia-l424 GB$0.851/hrus-east4
7 more instances can run SEA-LION Llama3 8B SEA-LION V2.1 Instruct
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
SEA-LION 4 32B IT—33K——Available
SEA-LION Gemma 4 27B Instruct—128K$0.351$0.555Available
SEA-LION Llama3 8B SEA-LION V2.1 Instruct————Current
SEA-LION 7B————Available
SEA-LION 7B Instruct————Available

Model IDs

aisingapore-llama3-sealion-2-1-8b-instruct
huggingface-llm-llama3-8b-sealionv21-instruct