GPT-5.4 nano
neon/gpt-5-4-nano · family gpt-nano · in: text, image → out: text, image · price provider-declared (via models.dev). Capabilities: tools reasoning text image.
$0.46
Blended $/1M (3:1)
$0.2
Input $/1M
$1.25
Output $/1M
$1.45
1M in + 1M out
$0.02 −90%
Cache read $/1M
#2715 of 7,710
Cheapest rank
- Provider
- Neon (
neon) - Kind
- text (outputs text, image)
- Context
- 400,000 tokens
- Max output
- 128,000 tokens
- Capabilities
- tools reasoning text image
Same model, other providers
“GPT-5.4 nano” is offered by 27 providers — cheapest-effective first. Ofox is the cheapest at $0.37 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Ofox | $0.16 | $1 | $0.37 | 400k |
| Neon (this) | $0.2 | $1.25 | $0.46 | 400k |
| NEAR AI Cloud | $0.2 | $1.25 | $0.46 | 400k |
| Databricks | $0.2 | $1.25 | $0.46 | 400k |
| Kilo Gateway | $0.2 | $1.25 | $0.46 | 400k |
| Abacus | $0.2 | $1.25 | $0.46 | 400k |
| OpenRouter | $0.2 | $1.25 | $0.46 | 400k |
| Impossibl | $0.2 | $1.25 | $0.46 | 400k |
| Cloudflare AI Gateway | $0.2 | $1.25 | $0.46 | 128k |
| FastRouter | $0.2 | $1.25 | $0.46 | 400k |
| OrcaRouter | $0.2 | $1.25 | $0.46 | 400k |
| Opper | $0.2 | $1.25 | $0.46 | 400k |
| Pioneer | $0.2 | $1.25 | $0.46 | 1M |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Neon 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-nano","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):