LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

GPT-4.1 nano

openai·openai/gpt-4.1-nano·Deprecated·Closed·gpt-nano series
Tiny GPT-4.1 option for classification, routing, and very high-volume tasks

Specs & pricing

Input / output per 1M tokens
Official price·OpenAI
$0.10 / $0.40
Blended $0.18 · Cache read $0.025
Lowest paid·PoeGateway
$0.09 / $0.36
Blended $0.16 · 1.3× spread
Context
1,047,576
Output limit
32,768
Knowledge cutoff
2024-04
Released / updated
2025-04-14 / 2025-04-14
Capabilities
Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImagePDF

GPT-4.1 nano by openai is offered by 24 providers on this page. Its official list price is $0.10 per 1M input tokens and $0.40 per 1M output tokens. Prices vary about 1.3× across the providers that host it.

Median output speed is 284 tokens per second, with 1.22s to the first token.

The context window is 1,047,576 tokens at the reference host, but hosts report different limits, from 1,000,000 to 1,047,576, so the usable window depends on the provider you pick. It supports tool use and structured output. Accepted input modalities are Text, Image, and PDF. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2024-04.

Quality & performanceArtificial Analysis · Intelligence Index v5

Intelligence—
Value—
Output speed284 tok/s
TTFT1.22 s

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 24 providers24 with public prices

  • ProviderInput / Output
  • PoeGateway
    $0.09 / $0.36
    Cache read $0.022Context 1,047,576Output limit 32,768deprecated
  • OpenAIOfficialFirst-party
    $0.10 / $0.40
    Cache read $0.025Context 1,047,576Output limit 32,768deprecated
  • Azure Cognitive ServicesCloud
    $0.10 / $0.40
    Cache read $0.025Context 1,047,576Output limit 32,768deprecated
  • AbacusGateway
    $0.10 / $0.40
    Cache read $0.025Context 1,047,576Output limit 32,768
  • Merge GatewayGateway
    $0.10 / $0.40
    Cache read $0.025Context 1,047,576Output limit 32,768
  • DevPass (LLM Gateway)Gateway
    $0.10 / $0.40
    Cache read $0.025Context 1,000,000 ⚠Output limit 32,768
  • AzureCloud
    $0.10 / $0.40
    Cache read $0.025Context 1,047,576Output limit 32,768deprecated
  • LLM GatewayGateway
    $0.10 / $0.40
    Cache read $0.025Context 1,000,000 ⚠Output limit 32,768
  • Vercel AI GatewayCloud
    $0.10 / $0.40
    Cache read $0.03Context 1,047,576Output limit 32,768deprecated
  • Cloudflare AI GatewayCloud
    $0.10 / $0.40
    Cache read $0.03Context 1,000,000 ⚠Output limit 32,768
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
PoeGateway$0.09$0.36$0.022—1,047,57632,768deprecated
OpenAIOfficialFirst-party$0.10$0.40$0.025—1,047,57632,768deprecated
Azure Cognitive ServicesCloud$0.10$0.40$0.025—1,047,57632,768deprecated
AbacusGateway$0.10$0.40$0.025—1,047,57632,768
Merge GatewayGateway$0.10$0.40$0.025—1,047,57632,768
DevPass (LLM Gateway)Gateway$0.10$0.40$0.025—1,000,000 ⚠32,768
AzureCloud$0.10$0.40$0.025—1,047,57632,768deprecated
LLM GatewayGateway$0.10$0.40$0.025—1,000,000 ⚠32,768
Vercel AI GatewayCloud$0.10$0.40$0.03—1,047,57632,768deprecated
Cloudflare AI GatewayCloud$0.10$0.40$0.03—1,000,000 ⚠32,768

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Experimental modes2 items

ModeProviderInputOutputCache readCache write
fastOpenAI$0.20$0.80$0.05—
fastVercel AI Gateway$0.20$0.80$0.06—

Your usage cost

Common scenarios
1Poe$27.84
2OpenAI · Official$31.00
3Azure Cognitive Services$31.00
4Abacus$31.00
5Merge Gateway$31.00
6DevPass (LLM Gateway)$31.00
Switch to Poe to save $3.16/mo (10%). The gap is small, so staying on the official channel is fine.
Note: this is a gateway; verify availability and rate limits yourself.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.40$02026-08-052026-10-22
2026-10-22Input list $0.10Output list $0.40Min blended $0.16

Benchmark1 items

NameConditionsScoreMetricSource
Aider Polyglot—8.9percent correctSource ↗

The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.

Related models

GPT-5.4 nanosame series$0.20 / $1.25GPT-5 Nanosame series$0.05 / $0.40Lyria 3 Clip Previewcheaper alternative$0 / $0Lyria 3 Pro Previewcheaper alternative$0 / $0GPT-4.1 minisame lab$0.40 / $1.60GPT-4osame lab$2.50 / $10.00
Data partly from models.dev (MIT) · OpenAI official docs ↗