by OpenAI · Language Models
Our strongest mini model yet for coding and subagents. GPT-5.4 Mini brings the strengths of GPT-5.4 to a faster, more efficient model designed for high-volume workloads. 400K context window; configurable reasoning effort.
$0.75 in · $4.5 out · $0.075 cached / 1M
| Usage | Rate (USD) | Unit |
|---|---|---|
| Input tokens | $0.75 | per 1M tokens |
| Cached input (cache hit) | $0.075 | per 1M tokens |
| Output tokens | $4.5 | 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-mini", "messages": [{"role": "user", "content": "Hello!"}]}'Model ID: gpt-5.4-mini · works with OpenAI SDKs — just point base_url at api.tunerouter.com