Models

gpt-5.4-mini

azure_ai ↗ · 400K ctx · 5 providers · updated 2026-08-05 00:15 UTC

Cheapest
$1.69 Official list · Azure AI
Avg price
$1.69 /1M
providers
5
Tokens (24h)
22B
Volume (24h)
$37.5K est.
(3 × $0.750 + $4.50) ÷ 4 = $1.69/1M — the $/1M figure blends input and output at 3:1 — that is the only way models with two different rates can be ranked on one axis. Your actual rate depends on your own input:output mix — input only $0.750, 3:1 $1.69, 1:1 $2.63, output only $4.50 per 1M.

The board shows this model's cheapest measured offer ($1.69/1M); the smaller figure under it is the mean of the 6 offers listed below ($1.69/1M). Add those up and divide — it matches. 24h token volume (22B) is sourced from OpenRouter public rankings — today's only public source of absolute per-model token counts (Vercel AI Gateway publishes share-of-traffic percentages); as more sources come online, the per-router breakdown will sum to this total here.

ProviderRouter / Source$ in /1M$ out /1MTTFTTPSUptimeEvidence
azure_ai Pricebook (LiteLLM) $0.750$4.50 Official list
azure Pricebook (LiteLLM) $0.750$4.50 Official list
openai Pricebook (LiteLLM) $0.750$4.50 Official list
openrouter-best OpenRouter $0.750$4.50 API-measured
requesty Requesty $0.750$4.50 API-measured
burncloud burncloud $0.750$4.50 API-measured

Volume trend

53B 30d d-29 · 35B tokensd-28 · 40B tokensd-27 · 40B tokensd-26 · 46B tokensd-25 · 34B tokensd-24 · 23B tokensd-23 · 23B tokensd-22 · 28B tokensd-21 · 30B tokensd-20 · 27B tokensd-19 · 25B tokensd-18 · 23B tokensd-17 · 20B tokensd-16 · 18B tokensd-15 · 23B tokensd-14 · 31B tokensd-13 · 27B tokensd-12 · 38B tokensd-11 · 34B tokensd-10 · 53B tokensd-9 · 0 tokensd-8 · 24B tokensd-7 · 29B tokensd-6 · 28B tokensd-5 · 0 tokensd-4 · 0 tokensd-3 · 17B tokensd-2 · 0 tokensd-1 · 0 tokensd-0 · 22B tokens

Last 30 days: 35B → 22B (-37%); range 0–53B tokens/day. Source: OpenRouter public rankings; refreshed hourly.

Data & method

Cheapest ranked by blended = (3×in + out) ÷ 4; performance columns show only when a source provides them, never estimated. “Official list” = LiteLLM open pricebook (MIT); “API-measured” = provider/aggregator public APIs. Machine-readable data: /api/v1/models/gpt-5.4-mini.json. Free reuse requires attribution to tkx.org.

About

GPT-5.4-mini is a language model served by multiple inference providers on AI model marketplaces, listed under the org tag "azure_ai". It is designed for natural language processing tasks, such as text generation and understanding.

AI-generated summary from public information — is this yours?

FAQ

How much does gpt-5.4-mini cost?

Cheapest measured offer right now: $0.75/1M input, $4.5/1M output via azure_ai — across 5 tracked providers, refreshed hourly.

Who serves gpt-5.4-mini?

5 providers currently serve it. The table above lists each with input/output price, TTFT, TPS, uptime and an evidence tier.

How heavily is gpt-5.4-mini used?

gpt-5.4-mini routed 22B tokens in the last 24h. The daily bars above show routed volume over recent days. Source: OpenRouter public rankings — one of the few routers publishing per-model usage; TKX refreshes hourly.

Related analysis

Back to rankings