LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

GPT-5.4 mini

openai·openai/gpt-5.4-mini·GA·Closed·gpt-mini series
Strong small GPT for coding subagents, quick tool use, and high-volume work

Specs & pricing

Input / output per 1M tokens
Official price·OpenAI
$0.75 / $4.50
Blended $1.69 · Cache read $0.075
Lowest paid·XpersonaGateway
$0.38 / $4.00
Blended $1.28 · 4.2× spread
1 more $0 channels
Context
400,000
Output limit
128,000
Knowledge cutoff
2025-08-31
Released / updated
2026-03-17 / 2026-03-17
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
Modalities
TextImagePDF

GPT-5.4 mini by openai is offered by 46 providers on this page. Public prices are shown for 43 of them. Its official list price is $0.75 per 1M input tokens and $4.50 per 1M output tokens. The lowest paid channel is Xpersona at $0.375 / $4.00 per 1M, about 1.3× below the list price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. It also has 1 free ($0) channel; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.

Median output speed is 193 tokens per second, with 4.85s to the first token.

The context window is 400,000 tokens at the reference host, but hosts report different limits, from 128,000 to 400,000, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text, Image, and PDF. Its training knowledge cuts off at 2025-08-31.

Quality & performanceArtificial Analysis · Intelligence Index v5 · rep. tier Medium

Intelligence—
Value—
Output speed193 tok/s
TTFT4.85 s

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

Available at 46 providers43 with public prices · 1 free

  • ProviderInput / Output
  • GitLab DuoCloud
    duo-chat-gpt-5-4-mini
    Free
    Context 400,000Output limit 128,000
  • XpersonaGateway
    $0.38 / $4.00
    Cache read $0.038Context 272,000 ⚠Output limit 128,000
  • PoeGateway
    $0.68 / $4.09
    Cache read $0.068Context 400,000Output limit 128,000
  • OpenAIOfficialFirst-party
    $0.75 / $4.50
    Cache read $0.075Context 400,000Output limit 128,000
  • CrossModelGateway
    $0.75 / $4.50
    Cache read $0.075Context 400,000Output limit 128,000
  • LLM GatewayGateway
    $0.75 / $4.50
    Cache read $0.075Context 400,000Output limit 128,000
  • LLM GatewayGateway
    $0.75 / $4.50
    Cache read $0.075Context 400,000Output limit 128,000
  • Azure Cognitive ServicesCloud
    $0.75 / $4.50
    Cache read $0.075Context 400,000Output limit 128,000
  • CommandCodeGateway
    $0.75 / $4.50
    Cache read $0.075Context 400,000Output limit 128,000
  • 302.AIGateway
    $0.75 / $4.50
    Cache read $0.075Context 400,000Output limit 128,000
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
GitLab Duo
duo-chat-gpt-5-4-mini
CloudFree——400,000128,000
XpersonaGateway$0.38$4.00$0.038—272,000 ⚠128,000
PoeGateway$0.68$4.09$0.068—400,000128,000
OpenAIOfficialFirst-party$0.75$4.50$0.075—400,000128,000
CrossModelGateway$0.75$4.50$0.075$0.75400,000128,000
LLM GatewayGateway$0.75$4.50$0.075—400,000128,000
LLM GatewayGateway$0.75$4.50$0.075—400,000128,000
Azure Cognitive ServicesCloud$0.75$4.50$0.075—400,000128,000
CommandCodeGateway$0.75$4.50$0.075$0400,000128,000
302.AIGateway$0.75$4.50$0.075—400,000128,000

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.

Reasoning control

effort = noneeffort = loweffort = mediumeffort = higheffort = xhigheffort = maxeffort = minimal

Interleaved thinking (reasoning between tool calls) is declared by 2 of 46 providers.

1 / 46 providers expose no reasoning control (reasoning_options: []).

Experimental modes8 items

ModeProviderInputOutputCache readCache write
fastOpenAI$1.50$9.00$0.15—
flexOpenAI$0.38$2.25$0.038—
fastAzure Cognitive Services$1.50$9.00$0.15—
fastDatabricks$1.50$9.00$0.15—
fastMerge Gateway$1.50$9.00$0.15—
fastAIHubMix$1.50$9.00$0.15—
fastAzure$1.50$9.00$0.15—
fastOrcaRouter$1.50$9.00$0.15—

Your usage cost

Common scenarios
1Xpersona$234.50
2Poe$267.27
3OpenAI · Official$294.00
4CrossModel$294.00
5LLM Gateway$294.00
6LLM Gateway$294.00

1 more channels offer $0 (GitLab Duo); free tiers usually have rate limits and no SLA, excluded from ranking.

Switch to Xpersona to save $59.50/mo (20%)
Note: this is a gateway; verify availability and rate limits yourself.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$4.50$02026-08-052026-08-13
2026-08-13Input list $0.75Output list $4.50Min blended $1.28

Benchmark16 items

NameConditionsScoreMetricSource
SWE-Bench Provariant: reasoning effort xhigh54.4resolve rateSource ↗
Terminal-Benchvariant: reasoning effort xhigh · v2.060accuracySource ↗
MCP Atlasvariant: reasoning effort xhigh57.7scoreSource ↗
Toolathlonvariant: reasoning effort xhigh42.9scoreSource ↗
τ²-Bench Telecomvariant: reasoning effort xhigh93.4accuracySource ↗
GPQA Diamondvariant: reasoning effort xhigh88accuracySource ↗
Humanity's Last Examvariant: with tools41.5accuracySource ↗
Humanity's Last Examvariant: without tools28.2accuracySource ↗
OSWorld-Verifiedvariant: reasoning effort xhigh72.1success rateSource ↗
MMMU Provariant: with Python78accuracySource ↗
MMMU Provariant: without tools76.6accuracySource ↗
OmniDocBenchvariant: reasoning effort none · v1.50.1263overall edit distanceSource ↗
OpenAI MRCRvariant: 8-needle, 64K-128K · vv247.7accuracySource ↗
OpenAI MRCRvariant: 8-needle, 128K-256K · vv233.6accuracySource ↗
Graphwalksvariant: BFS, 0-128K76.3accuracySource ↗
Graphwalksvariant: parents, 0-128K71.5accuracySource ↗

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

Related models

GPT Mini Latestsame series—GPT-Audio Minisame series—GPT-Realtime minisame series—GLM-5.3-Flashcheaper alternative$0.15 / $0.50DeepSeek V4.1 Flash 1017cheaper alternative$0.15 / $0.60GPT-5.6 Lunacheaper alternative$0.20 / $1.20MiniMax-M3cheaper alternative$0.30 / $1.20GPT-5.4 Image 2same lab—GPT-5.4 nanosame lab$0.20 / $1.25
Data partly from models.dev (MIT) · OpenAI official docs ↗