LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

GPT-4.1 mini

openai·openai/gpt-4.1-mini·GA·Closed·gpt-mini series
Affordable GPT-4.1 lane for fast coding help and structured extraction

Specs & pricing

Input / output per 1M tokens
Official price·OpenAI
$0.40 / $1.60
Blended $0.70 · Cache read $0.10
Lowest paid·PoeGateway
$0.36 / $1.45
Blended $0.64 · 1.9× 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 mini by openai is offered by 34 providers on this page. Public prices are shown for 32 of them. Its official list price is $0.40 per 1M input tokens and $1.60 per 1M output tokens. Prices vary about 1.9× across the providers that host it.

Median output speed is 108 tokens per second, with 1.57s 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 speed108 tok/s
TTFT1.57 s

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

Available at 34 providers32 with public prices

  • ProviderInput / Output
  • PoeGateway
    $0.36 / $1.45
    Cache read $0.091Context 1,047,576Output limit 32,768
  • OpenAIOfficialFirst-party
    $0.40 / $1.60
    Cache read $0.10Context 1,047,576Output limit 32,768
  • LLM GatewayGateway
    $0.40 / $1.60
    Cache read $0.10Context 1,000,000 ⚠Output limit 32,768
  • LLM GatewayGateway
    $0.40 / $1.60
    Cache read $0.10Context 1,000,000 ⚠Output limit 32,768
  • Azure Cognitive ServicesCloud
    $0.40 / $1.60
    Cache read $0.10Context 1,047,576Output limit 32,768deprecated
  • 302.AIGateway
    $0.40 / $1.60
    Context 1,047,576Output limit 32,768
  • LowRouterGateway
    $0.40 / $1.60
    Cache read $0.10Context 1,047,576Output limit 32,768
  • NanoGPTGateway
    $0.40 / $1.60
    Cache read $0.10Context 1,047,576Output limit 32,768
  • DevPass (LLM Gateway)Gateway
    $0.40 / $1.60
    Cache read $0.10Context 1,000,000 ⚠Output limit 32,768
  • NEAR AI CloudGateway
    $0.40 / $1.60
    Cache read $0.10Context 1,047,576Output limit 32,768
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
PoeGateway$0.36$1.45$0.091—1,047,57632,768
OpenAIOfficialFirst-party$0.40$1.60$0.10—1,047,57632,768
LLM GatewayGateway$0.40$1.60$0.10—1,000,000 ⚠32,768
LLM GatewayGateway$0.40$1.60$0.10—1,000,000 ⚠32,768
Azure Cognitive ServicesCloud$0.40$1.60$0.10—1,047,57632,768deprecated
302.AIGateway$0.40$1.60——1,047,57632,768
LowRouterGateway$0.40$1.60$0.10—1,047,57632,768
NanoGPTGateway$0.40$1.60$0.10—1,047,57632,768
DevPass (LLM Gateway)Gateway$0.40$1.60$0.10—1,000,000 ⚠32,768
NEAR AI CloudGateway$0.40$1.60$0.10—1,047,57632,768

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$0.70$2.80$0.18—
fastVercel AI Gateway$0.70$2.80$0.18—

Your usage cost

Common scenarios
1Poe$112.72
2OpenAI · Official$124.00
3LLM Gateway$124.00
4LLM Gateway$124.00
5Azure Cognitive Services$124.00
6LowRouter$124.00
Switch to Poe to save $11.28/mo (9%). 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
$1.60$02026-08-052026-10-22
2026-10-22Input list $0.40Output list $1.60Min blended $0.64

Benchmark1 items

NameConditionsScoreMetricSource
Aider Polyglot—32.4percent correctSource ↗

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

Related models

GPT Mini Latestsame series—GPT-5.4 minisame series$0.75 / $4.50GPT-Audio Minisame series—Lyria 3 Clip Previewcheaper alternative$0 / $0Lyria 3 Pro Previewcheaper alternative$0 / $0GPT-4.1same lab$2.00 / $8.00GPT-4.1 nanosame lab$0.10 / $0.40
Data partly from models.dev (MIT) · OpenAI official docs ↗