Skip to content
Sovyron

GPT-4.1 nano

gpt-nano1.0M context33k max outputreleased Apr 14, 2025Tool calling

As of Oct 4, 2026, the cheapest GPT-4.1 nano API price is $0.08 per 1M input tokens (SAP AI Core) and $0.26 per 1M output tokens (SAP AI Core). GPT-4.1 nano is offered by 19 providers in the gpt-nano family.

Cheapest input
$0.08
Cheapest output
$0.26
Official
—
output per 1M tokens
Providers
19
offering this model
Spread
1.7×
max / min output
Free offers
0
free-tier offers

API pricing by provider

Metered per-token prices. Cheapest input and output are highlighted; † marks a context-tier surcharge. How prices are ranked.

GPT-4.1 nano API prices by provider in USD per 1M tokens, updated Oct 4, 2026
SAP AI CoreCheapest$0.08Cheapest$0.26——1.0M
Poe$0.09$0.36$0.022—1.0M
Helicone$0.1$0.4$0.025—1.0M
302.AI$0.1$0.4——1.0M
Abacus$0.1$0.4$0.025—1.0M
Cloudflare AI Gateway$0.1$0.4$0.025—1.0M
Eden AI$0.1$0.4$0.025—1.0M
Impossibl$0.1$0.4$0.025—1.0M
Kilo Gateway$0.1$0.4$0.025—1.0M
DevPass (LLM Gateway)$0.1$0.4$0.025—1.0M
LLM Gateway$0.1$0.4$0.025—1.0M
LLM Gateway$0.1$0.4$0.025—1.0M
Merge Gateway$0.1$0.4$0.025—1.0M
NanoGPT$0.1$0.4$0.025—1.0M
NEAR AI Cloud$0.1$0.4$0.025—1.0M
OpenRouter$0.1$0.4$0.025—1.0M
OrcaRouter$0.1$0.4$0.025—1.0M
Pioneer$0.1$0.4$0.05$0.11.0M
Cortecs$0.111$0.434$0.056—1.0M
Requestyeu$0.11$0.44$0.0275—1.0M

GPT-4.1 nano pricing FAQ

What is the cheapest GPT-4.1 nano API?

As of Oct 4, 2026, SAP AI Core has the lowest GPT-4.1 nano output price at $0.26 per 1M tokens, and SAP AI Core has the lowest input price at $0.08 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

How many providers offer GPT-4.1 nano?

19 providers list GPT-4.1 nano on Sovyron; 20 of them sell it at a metered per-token price.

Is GPT-4.1 nano free?

No provider in the Sovyron catalog lists a free tier for GPT-4.1 nano.

What is the context window of GPT-4.1 nano?

GPT-4.1 nano supports a 1.0M-token context window and up to 33k output tokens.

Token cost calculator

What a month costs at one provider's published rates. Enter the tokens you expect to send and receive; cached tokens use the cached-input price where the provider lists one, and count as ordinary input where it does not.

Estimated

—