Embeddings

Vector representations, at the speed of memory.

Embed 1M tokens in 1.2 seconds. Multi-lingual, multi-modal, batched by default. The same API as OpenAI, with sub-millisecond P50 at scale.

1536 / 3072 dimensions

Two tiers. Small for retrieval at scale, large for nuanced semantic search.

Sub-millisecond P50

Batched inference and a custom kernel keep latency low at 10K vectors per second.

OpenAI-compatible

Same /v1/embeddings endpoint. Same request shape. Switch by changing the base URL.

Multi-modal

Text, image, audio: same vector space. Cross-modal search out of the box.

100+ languages

Multilingual by design. No separate model per language.

Batched privacy

Embeddings are not stored unless you opt in. We compute, return, and forget.

Pricing

Token-efficient, with volume discounts and burn incentives.

Small (1536d)
0.0001QUBIC / 1K tokens

Best for retrieval at scale

Large (3072d)
0.0002QUBIC / 1K tokens

Best for nuanced semantics

Multi-modal
0.0004QUBIC / 1K tokens

Text + image + audio

Batched (>1M)
0.00006QUBIC / 1K tokens

Async batch API

Pricing is illustrative. Final rates are governed by on-chain parameters and may vary based on network state.

Staking requirements

Tier-based access. Higher stakes unlock better economics and more capacity.

TierRequired stakeAccess
Explorer10M QUBICBest-effort, 60 RPS
Builder50M QUBICReserved, 600 RPS
Startup150M QUBICDedicated, 6K RPS
Business500M QUBICBurst to 60K RPS
EnterpriseCustomUnlimited

Example

Drop-in compatible with the OpenAI SDK.

embeddings.py
from aigarth import Aigarth

client = Aigarth(api_key="sk-aigarth-...")

texts = [
    "What is Useful Proof of Staking?",
    "How does Aigarth work?",
    "Best pizza in New York",
]

response = client.embeddings.create(
    model="aigarth-embed-1-large",
    input=texts,
)

vectors = [item.embedding for item in response.data]
print(f"Embedded {len(vectors)} texts at {len(vectors[0])} dimensions")

Enterprise benefits

Everything in the standard tier, plus the things enterprises need.

  • Dedicated vector index capacity
  • Co-located with managed Pinecone, Weaviate, Qdrant
  • Migration from OpenAI, Cohere, Voyage in days
  • HIPAA-aligned data handling
  • PII redaction in pre-processing pipeline
  • Multi-region replication for global apps
  • SOC 2 and ISO 27001 (in progress)
  • 24/7 on-call for production incidents

Ready to get started?

Open the console, generate an API key, and run your first call in minutes.