LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

GPT-5 Mini

openai·openai/gpt-5-mini·GA·Closed·gpt-mini series
Small GPT-5 for responsive agents, coding help, and everyday automation

Specs & pricing

Input / output per 1M tokens
Official price·OpenAI
$0.25 / $2.00
Blended $0.69 · Cache read $0.025
Lowest paid·QiHangGateway
$0.04 / $0.29
Blended $0.10 · 11.3× spread
1 more $0 channels
Context
400,000
Output limit
128,000
Knowledge cutoff
2024-05-30
Released / updated
2025-08-07 / 2025-08-07
Capabilities
✓ Reasoning✓ Tool use✓ Structured outputTemperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImagePDF

GPT-5 Mini by openai is offered by 42 providers on this page. Public prices are shown for 40 of them. Its official list price is $0.25 per 1M input tokens and $2.00 per 1M output tokens. The lowest paid channel is QiHang at $0.04 / $0.29 per 1M, about 6.7× 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 90 tokens per second, with 89.84s 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. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2024-05-30.

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

Intelligence—
Value—
Output speed90 tok/s
TTFT89.84 s

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

Available at 42 providers40 with public prices · 1 free

  • ProviderInput / Output
  • GitLab DuoCloud
    duo-chat-gpt-5-mini
    Free
    Context 400,000Output limit 128,000deprecated
  • QiHangGateway
    $0.04 / $0.29
    Context 200,000 ⚠Output limit 64,000
  • PoeGateway
    $0.23 / $1.82
    Cache read $0.023Context 400,000Output limit 128,000
  • Jiekou.AIGateway
    $0.24 / $1.90
    Cache read $0.024Context 400,000Output limit 128,000
  • OpenAIOfficialFirst-party
    $0.25 / $2.00
    Cache read $0.025Context 400,000Output limit 128,000
  • Perplexity AgentGateway
    $0.25 / $2.00
    Cache read $0.025Context 400,000Output limit 128,000deprecated
  • LLM GatewayGateway
    $0.25 / $2.00
    Cache read $0.025Context 400,000Output limit 128,000
  • LLM GatewayGateway
    $0.25 / $2.00
    Cache read $0.025Context 400,000Output limit 128,000
  • 302.AIGateway
    $0.25 / $2.00
    Cache read $0.025Context 400,000Output limit 128,000
  • DigitalOceanCloud
    openai-gpt-5-mini
    $0.25 / $2.00
    Cache read $0.025Context 400,000Output limit 128,000
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
GitLab Duo
duo-chat-gpt-5-mini
CloudFree——400,000128,000deprecated
QiHangGateway$0.04$0.29——200,000 ⚠64,000
PoeGateway$0.23$1.82$0.023—400,000128,000
Jiekou.AIGateway$0.24$1.90$0.024—400,000128,000
OpenAIOfficialFirst-party$0.25$2.00$0.025—400,000128,000
Perplexity AgentGateway$0.25$2.00$0.025—400,000128,000deprecated
LLM GatewayGateway$0.25$2.00$0.025—400,000128,000
LLM GatewayGateway$0.25$2.00$0.025—400,000128,000
302.AIGateway$0.25$2.00$0.025—400,000128,000
DigitalOcean
openai-gpt-5-mini
Cloud$0.25$2.00$0.025—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 = minimaleffort = loweffort = mediumeffort = higheffort = xhigheffort = maxeffort = none

Interleaved thinking (reasoning between tool calls) is declared by 1 of 42 providers.

2 / 42 providers expose no reasoning control (reasoning_options: []).

Experimental modes5 items

ModeProviderInputOutputCache readCache write
fastOpenAI$0.45$3.60$0.045—
flexOpenAI$0.13$1.00$0.013—
fastDatabricks$0.45$3.60$0.045—
fastVercel AI Gateway$0.45$3.60$0.045—
flexVercel AI Gateway$0.13$1.00$0.013—

Your usage cost

Common scenarios
1QiHang$22.50
2Poe$111.82
3Jiekou.AI$116.84
4OpenAI · Official$123.00
5Perplexity Agent$123.00
6LLM Gateway$123.00

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

Switch to QiHang to save $100.50/mo (82%)
Note: this is a gateway; verify availability and rate limits yourself.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$2.00$02026-08-052026-08-13
2026-08-13Input list $0.25Output list $2.00Min blended $0.10

Related models

GPT Mini Latestsame series—GPT-5.4 minisame series$0.75 / $4.50GPT-Audio Minisame series—GLM-5.3-Flashcheaper alternative$0.15 / $0.50DeepSeek V4.1 Flash 1017cheaper alternative$0.15 / $0.60Claude Haiku 5.5cheaper alternative$0.10 / $0.50Gemma 4 31B ITcheaper alternative$0 / $0GPT-5-Codexsame lab—GPT-5 Nanosame lab$0.05 / $0.40
Data partly from models.dev (MIT) · OpenAI official docs ↗