by OpenAI · Language Models
Our cheapest GPT-5.4-class model for simple high-volume tasks. GPT-5.4 nano is built for speed and cost—classification, extraction, ranking, and lightweight sub-agents. 400K context window; configurable reasoning effort.
$0.2 in · $1.25 out · $0.02 cached / 1M
| Usage | Rate (USD) | Unit |
|---|---|---|
| Input tokens | $0.2 | per 1M tokens |
| Cached input (cache hit) | $0.02 | per 1M tokens |
| Output tokens | $1.25 | per 1M tokens |
Official model pricing · currency: USD · pre-deduction settled by actual usage
OpenAI-compatible · base URL https://api.tunerouter.com/v1/
curl https://api.tunerouter.com/v1/chat/completions \
-H "Authorization: Bearer $TUNEROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "gpt-5.4-nano", "messages": [{"role": "user", "content": "Hello!"}]}'Model ID: gpt-5.4-nano · works with OpenAI SDKs — just point base_url at api.tunerouter.com