AI Inference

OpenAI-compatible APIs. A fraction of the cost.

Drop-in replacement for the OpenAI SDK. Same endpoints, same shapes, dramatically better economics. Run any model: from frontier open models to your own fine-tunes.

Any model

Frontier open models, fine-tunes, custom weights. If it can run, we serve it.

Sub-50ms P50

Edge routing, regional clusters, and tiered capacity keep latency low at any scale.

OpenAI-compatible

Same endpoints. Same request and response shape. Switch by changing the base URL.

Streaming first

Server-sent events, tool use, function calling, structured outputs. All first-class.

Verifiable

Every call produces a signed receipt. Output hashes recorded on-chain.

47 regions

Compute where your users are. Sub-50ms anywhere with a network connection.

Pricing

Token-efficient, with volume discounts and burn incentives.

Chat
0.0004QUBIC / 1K tokens

Input tokens. Output at 3× input.

Reasoning
0.0024QUBIC / 1K tokens

Chain-of-thought, longer context.

Vision
0.0080QUBIC / image

Up to 1024×1024 resolution.

Embeddings
0.0001QUBIC / 1K tokens

Batched at 256 texts/request.

Voice TTS
0.012QUBIC / 1K characters

47 voices, 31 languages.

Voice STT
0.006QUBIC / minute

Speaker diarization included.

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, shared pool
Builder50M QUBICReserved throughput, 25% burn discount
Startup150M QUBICDedicated cluster, 40% burn discount
Business500M QUBICEnterprise SLA, 55% burn discount
EnterpriseCustomCustom infrastructure and SLAs

Example

Drop-in compatible with the OpenAI SDK.

inference.py
from aigarth import Aigarth

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

response = client.chat.create(
    model="aigarth-reason-1",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What's the capital of France?"},
    ],
    stream=True,
)

for chunk in response:
    print(chunk.choices[0].delta.content or "", end="")

Enterprise benefits

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

  • Dedicated clusters with predictable performance
  • On-prem and air-gapped deployment
  • SOC 2, ISO 27001, HIPAA compliance
  • Private networking and BYO encryption
  • 24/7 on-call with 15-minute P1 response
  • Custom SLAs with financial compensation
  • Migration assistance from your current provider
  • Quarterly business reviews with a named CSM

Ready to get started?

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