ModelPickr

Models / OpenAI / GPT-4.1 nano

OpenAI · gpt-nano

GPT-4.1 nano

Tiny GPT-4.1 option for classification, routing, and very high-volume tasks

$0.10 in · $0.40 out

per 1M tokens · first-party price. Reference price from OpenAI, the lab's own listing.

Provider input prices run from $0.08 to $0.20 per 1M tokens. Output prices run from $0.26 to $0.80.

Context
1,047,576
Max output
32,768
Cache read
$0.025
Cache write
—
Reasoning
No
Tool calls
Yes
Structured output
Yes
Vision
Yes
Open weights
No
License
—
Released
Apr 14, 2025
Updated in source
Apr 14, 2025
Knowledge
2024-04
Providers
22

What this model costs per month

Prices are USD per 1M tokens. A month is 30 days. Cache hits use the cache-read rate when the model has one; otherwise the cache field is ignored.

monthly = requests/day × 30 × (input tokens × (1 − cache hit) × input price + input tokens × cache hit × cache-read price + output tokens × output price) ÷ 1,000,000

Providers

Base rates from Models.dev. One row per provider.
ProviderInputOutputCache readCache writeStatus
SAP AI Core$0.08$0.26———
Abacus$0.10$0.40$0.025——
Azure$0.10$0.40$0.025—deprecated
Azure Cognitive Services$0.10$0.40$0.025—deprecated
Cloudflare AI Gateway$0.10$0.40$0.025——
DevPass$0.10$0.40$0.025——
Eden AI$0.10$0.40$0.025——
Impossibl$0.10$0.40$0.025——
Kilo Gateway$0.10$0.40$0.025——
LLM Gateway$0.10$0.40$0.025——
Merge Gateway$0.10$0.40$0.025——
NanoGPT$0.10$0.40$0.025——
NEAR AI Cloud$0.10$0.40$0.025——
OpenAIreference$0.10$0.40$0.025—deprecated
OpenRouter$0.10$0.40$0.025——
OrcaRouter$0.10$0.40$0.025——
Pioneer$0.10$0.40$0.05$0.10—
Prime Inference$0.10$0.40———
Requesty$0.11$0.44$0.028——
Cortecs$0.11$0.43$0.056——
AI/ML API$0.13$0.52$0.033——
Vercel AI Gateway$0.20$0.80$0.05——

Jobs this model qualifies for