Home › VastLLM Catalog › GPT-5 Nano

GPT-5 Nano

by OpenAI · Language Models

Context 400K tokensVisionReasoning / thinkingFunction calling

Overview

The fastest, most cost-efficient GPT-5 reasoning model for summarization, classification, and high-volume lightweight tasks. OpenAI marks this model as deprecated and recommends GPT-5.6 Luna for new workloads.

Context window400K tokens
Max output128K tokens
Input → Outputtext, image → text
CapabilitiesVision, Reasoning / thinking, Function calling

Pricing

$0.05 in · $0.4 out · $0.005 cached / 1M

UsageRate (USD)Unit
Input tokens$0.05per 1M tokens
Cached input (cache hit)$0.005per 1M tokens
Output tokens$0.4per 1M tokens

Official model pricing · currency: USD · pre-deduction settled by actual usage

Call it in 30 seconds

OpenAI-compatible · base URL https://api.tunerouter.com/v1/

POST/chat/completions
curl https://api.tunerouter.com/v1/chat/completions \
  -H "Authorization: Bearer $TUNEROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "gpt-5-nano", "messages": [{"role": "user", "content": "Hello!"}]}'

Model ID: gpt-5-nano · works with OpenAI SDKs — just point base_url at api.tunerouter.com

More from OpenAI

← Back to full catalog (120 models)