openai/gpt-5-nano

Smallest GPT-5 tier for latency-sensitive workloads.

TextTranslationAgents & toolscheaptools

Specifications

Context window: 400K
Max output tokens: 128,000
Released: 2025-08
Infra providers: 4
Throughput: 210 tok/s
Latency (TTFB, sample): 350 ms
Capabilities: Supports tools

Pricing

per million tokens

Input

$0.050

Output

$0.40

Blended (3:1)

$0.14

Use this model

Works with any OpenAI SDK — same request shape, different model id.

curl https://api.lokarouter.id/v1/chat/completions \  -H "Authorization: Bearer sk-lkr-your-key" \  -H "Content-Type: application/json" \  -d '{    "model": "openai/gpt-5-nano",    "messages": [{ "role": "user", "content": "Hello" }]  }'

Sample data for demonstration — connect your workspace for live stats.