Models

gpt-4o

azure ↗ · 131K ctx · 8 providers · updated 2026-08-05 00:15 UTC

Cheapest
$4.38 Official list · Azure
Avg price
$4.38 /1M
providers
8
(3 × $2.50 + $10.00) ÷ 4 = $4.38/1M — 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 $2.50, 3:1 $4.38, 1:1 $6.25, output only $10.00 per 1M.

The board shows this model's cheapest measured offer ($4.38/1M); the smaller figure under it is the mean of the 10 offers listed below ($4.38/1M). Add those up and divide — it matches.

ProviderRouter / Source$ in /1M$ out /1MTTFTTPSUptimeEvidence
azure Pricebook (LiteLLM) $2.50$10.00 Official list
gmi Pricebook (LiteLLM) $2.50$10.00 Official list
openai Pricebook (LiteLLM) $2.50$10.00 Official list
openrouter Pricebook (LiteLLM) $2.50$10.00 Official list
replicate Pricebook (LiteLLM) $2.50$10.00 Official list
vercel_ai_gateway Pricebook (LiteLLM) $2.50$10.00 Official list
requesty Requesty $2.50$10.00 API-measured
burncloud burncloud $2.50$10.00 API-measured
Azure OpenRouter $2.50$10.00 943ms 89 99.9% API-measured
OpenAI OpenRouter $2.50$10.00 523ms 70 100.0% API-measured

Who burns this model

Top apps routing traffic to this model over the last 30 days, via OpenRouter's public stats. Only apps that opted into tracking appear, and only the top few are published — this is not the full demand picture. These figures are a 30-day window and are NOT comparable with the cumulative totals on the Apps board.

AppTokens (30d)Requests
Replit 2B 392K
Medical CRM Vector Service 2B 286K
Hermes Agent 581M 54K
VirtualDMV-Review 320M 79K
G0DM0D3-pliny 307M 28K

Price trend

$4.375 $4.375 2026-07-06 → 2026-08-05 · 31d 2026-07-06 · O 4.375 H 4.375 L 4.375 C 4.375 $/1M2026-07-07 · O 4.375 H 4.375 L 4.375 C 4.375 $/1M2026-07-08 · O 4.375 H 4.375 L 4.375 C 4.375 $/1M2026-07-09 · O 4.375 H 4.375 L 4.375 C 4.375 $/1M2026-07-10 · O 4.375 H 4.375 L 4.375 C 4.375 $/1M2026-07-11 · O 4.375 H 4.375 L 4.375 C 4.375 $/1M2026-07-12 · O 4.375 H 4.375 L 4.375 C 4.375 $/1M2026-07-13 · O 4.375 H 4.375 L 4.375 C 4.375 $/1M2026-07-14 · O 4.375 H 4.375 L 4.375 C 4.375 $/1M2026-07-15 · O 4.375 H 4.375 L 4.375 C 4.375 $/1M2026-07-16 · O 4.375 H 4.375 L 4.375 C 4.375 $/1M2026-07-17 · O 4.375 H 4.375 L 4.375 C 4.375 $/1M2026-07-18 · O 4.375 H 4.375 L 4.375 C 4.375 $/1M2026-07-19 · O 4.375 H 4.375 L 4.375 C 4.375 $/1M2026-07-20 · O 4.375 H 4.375 L 4.375 C 4.375 $/1M2026-07-21 · O 4.375 H 4.375 L 4.375 C 4.375 $/1M2026-07-22 · O 4.375 H 4.375 L 4.375 C 4.375 $/1M2026-07-23 · O 4.375 H 4.375 L 4.375 C 4.375 $/1M2026-07-24 · O 4.375 H 4.375 L 4.375 C 4.375 $/1M2026-07-25 · O 4.375 H 4.375 L 4.375 C 4.375 $/1M2026-07-26 · O 4.375 H 4.375 L 4.375 C 4.375 $/1M2026-07-27 · O 4.375 H 4.375 L 4.375 C 4.375 $/1M2026-07-28 · O 4.375 H 4.375 L 4.375 C 4.375 $/1M2026-07-29 · O 4.375 H 4.375 L 4.375 C 4.375 $/1M2026-07-30 · O 4.375 H 4.375 L 4.375 C 4.375 $/1M2026-07-31 · O 4.375 H 4.375 L 4.375 C 4.375 $/1M2026-08-01 · O 4.375 H 4.375 L 4.375 C 4.375 $/1M2026-08-02 · O 4.375 H 4.375 L 4.375 C 4.375 $/1M2026-08-03 · O 4.375 H 4.375 L 4.375 C 4.375 $/1M2026-08-04 · O 4.375 H 4.375 L 4.375 C 4.375 $/1M2026-08-05 · O 4.375 H 4.375 L 4.375 C 4.375 $/1M

Cheapest blended price, last 31 days (USD/1M): $4.375 → $4.375 → $4.375 → $4.375 → $4.375 → $4.375 → $4.375 → $4.375 → $4.375 → $4.375 → $4.375 → $4.375 → $4.375 → $4.375 → $4.375 → $4.375 → $4.375 → $4.375 → $4.375 → $4.375 → $4.375 → $4.375 → $4.375 → $4.375 → $4.375 → $4.375 → $4.375 → $4.375 → $4.375 → $4.375 → $4.375

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-4o.json. Free reuse requires attribution to tkx.org.

About

GPT-4o is a large language model (LLM) designed for natural language processing tasks and served by multiple inference providers on AI model marketplaces. It is listed under the "azure" serving-platform tag, indicating its compatibility with Microsoft Azure's cloud services.

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

FAQ

How much does gpt-4o cost?

Cheapest measured offer right now: $2.5/1M input, $10/1M output via azure — across 8 tracked providers, refreshed hourly.

Who serves gpt-4o?

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

Is the price of gpt-4o going up or down?

The daily candles above track the cheapest blended price ($/1M, 3:1 in:out). TKX snapshots every hour, so drops and hikes show up the same day they happen.

Related analysis

Back to rankings