Skip to content
SeedInfer

SeedInfer Documentation

Become a Provider
Choose a section

SeedInfer technical documentation

Guides for GPU node operators (providers) and for developers integrating the API (clients).

OpenAI API compatibleBase URL: https://seedinfer.com/v1Latency-aware routing

Client API integration

The SeedInfer API follows the OpenAI Chat Completions format. Point the standard openai SDK at base_url=https://seedinfer.com/v1 and use your API key.

API quickstart ↓Models & pricing ↓ Client FAQ ↓

Connection details

Base URLhttps://seedinfer.com/v1
FormatOpenAI Chat Completions
Streaming (SSE)Supported (stream: true)
Live modelgoogle/gemma-4-26b-a4b-nvfp4

Code examples (Python, Node.js, cURL)

Python (pip install openai)
import openai

client = openai.OpenAI(
    base_url="https://seedinfer.com/v1",
    api_key="sk-seedinfer-...YOUR_KEY",
)

response = client.chat.completions.create(
    model="google/gemma-4-26b-a4b-nvfp4",
    messages=[
        {"role": "system", "content": "You are a helpful AI assistant."},
        {"role": "user", "content": "Explain quantum computing in two sentences."}
    ],
    temperature=0.7,
    max_tokens=150,
)

print(response.choices[0].message.content)

Models & API pricing

Model idContextInput / 1MOutput / 1MStatus
google/gemma-4-26b-a4b-nvfp4
aliases: seedinfer/gemma-4-26b-a4b, gemma-4-26b-a4b
262,144 tokens$0.03$0.20live
seedinfer/nemotron-lightning-1m
1,048,576 tokens$0.02$0.05coming soon
qwen/qwen3.6-35b-a3b
262,144 tokens$0.06$0.50coming soon

Cached input is free (60s TTL, max 5 min). Minimum invoice for credit top-ups is $0.10.

Client FAQ

SeedInfer.com · Documentation · Payouts: USDC on Base, monthly, minimum $1.00
Docs · SeedInfer