GPT-5.4 mini
steadyrouter/gpt-5.4-mini · family gpt-mini · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image.
This is a text model — providers price it per unit, not per token, so models.dev carries no token price (fields read “—”). See SteadyRouter’s docs for per-unit rates.
- Provider
- SteadyRouter (
steadyrouter) - Kind
- text (outputs text)
- Context
- 400,000 tokens
- Max output
- 128,000 tokens
- Capabilities
- tools reasoning text image
Same model, other providers
“GPT-5.4 mini” is offered by 36 providers — cheapest-effective first. Xpersona is the cheapest at $1.28 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Xpersona | $0.375 | $4 | $1.28 | 272k |
| LowRouter | $0.75 | $4.5 | $1.69 | 400k |
| OpenAI | $0.75 | $4.5 | $1.69 | 400k |
| Cloudflare AI Gateway | $0.75 | $4.5 | $1.69 | 128k |
| OpenRouter | $0.75 | $4.5 | $1.69 | 400k |
| Neon | $0.75 | $4.5 | $1.69 | 400k |
| FastRouter | $0.75 | $4.5 | $1.69 | 400k |
| Ofox | $0.75 | $4.5 | $1.69 | 400k |
| Databricks | $0.75 | $4.5 | $1.69 | 400k |
| FreeModel | $0.75 | $4.5 | $1.69 | 400k |
| AIHubMix | $0.75 | $4.5 | $1.69 | 400k |
| Abacus | $0.75 | $4.5 | $1.69 | 400k |
| SteadyRouter (this) | — | — | — | 400k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at SteadyRouter and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"gpt-5.4-mini","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):