gpt-5.4
302ai/gpt-5.4 · family gpt · in: text, image, pdf → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image pdf.
$5.63
Blended $/1M (3:1)
$2.5
Input $/1M
$15
Output $/1M
$17.50
1M in + 1M out
$0.25 −90%
Cache read $/1M
#6612 of 7,708
Cheapest rank
- Provider
- 302.AI (
302ai) - Kind
- text (outputs text)
- Context
- 1,050,000 tokens
- Max output
- 128,000 tokens
- Capabilities
- tools reasoning text image pdf
Same model, other providers
“gpt-5.4” is offered by 40 providers — cheapest-effective first. UnoRouter is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| UnoRouter | free | free | $0.00 | 1.1M |
| Xpersona | $0.75 | $6 | $2.06 | 1.1M |
| Ofox | $2 | $12 | $4.50 | 1.1M |
| Poe | $2.2 | $14 | $5.15 | 1.1M |
| 302.AI (this) | $2.5 | $15 | $5.63 | 1.1M |
| SAP AI Core | $2.5 | $15 | $5.63 | 1.1M |
| Perplexity Agent | $2.5 | $15 | $5.63 | 1.1M |
| NEAR AI Cloud | $2.5 | $15 | $5.63 | 1.1M |
| Databricks | $2.5 | $15 | $5.63 | 1.1M |
| Kilo Gateway | $2.5 | $15 | $5.63 | 1.1M |
| Abacus | $2.5 | $15 | $5.63 | 400k |
| OpenRouter | $2.5 | $15 | $5.63 | 1.1M |
| Azure | $2.5 | $15 | $5.63 | 1.1M |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at 302.AI 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","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):