InferX Beta — Serverless GPU Inference Platform, Built for Agent-Native Workloads

Endpoint gemma-4-31B-it-fp8

Gemma-4-31B-it-FP8 is a state-of-the-art, instruction-tuned dense model from Google, optimized for high-performance inference

Metadata

Name
gemma-4-31B-it-fp8
Provider
google
Parameter Size
31.00B
GPU Count
1
Context Length
262144
Concurrency
2.91x
Cold Start TTFT
—
Recommended Use Cases
Coding assistant, RAG
Detailed Intro
—

Log In To Use This Endpoint

This public page shows the published endpoint metadata and integration shape. Log in to get a tenant-scoped endpoint URL, inference API key, and the interactive playground. Log in

Integration

Start with the shared setup below, then choose the endpoint mode that fits your workload: token-based shared serving or a tenant-scoped dedicated GPU endpoint.

  1. Choose either the token-based shared endpoint or the dedicated GPU endpoint below.
  2. Copy that section's base URL into your client endpoint field.
  3. Copy the shared inference API key once and reuse it for either mode.
  4. Use the model name shown in the selected section.
<INFERENCE_API_KEY>

An inference API key is required for both endpoint modes. Until one is available, the fields below keep the correct request shape and use a placeholder token.

Token-Based

Use the shared OpenAI-compatible endpoint. The base URL is shared across published endpoints, and usage is billed per token.

https://model.inferx.net/endpoints/v1
gemma-4-31B-it-fp8
Sample REST Call 
curl https://model.inferx.net/endpoints/v1/chat/completions \
  -H "Authorization: Bearer $INFERX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "gemma-4-31B-it-fp8", "messages": [{"role": "user", "content": "Hello"}]}'

Dedicated GPU

Model Spec