Models

gpt-5.5

azure_ai ↗ · 1050K ctx · 5 providers · updated 2026-08-04 22:15 UTC

Cheapest
$11.25 Official list · Azure AI
Avg price
$11.25 /1M · 1 outlier(s) excluded
providers
5
Tokens (24h)
23B
Volume (24h)
$256.9K est.
(3 × $5.00 + $30.00) ÷ 4 = $11.25/1M — 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 $5.00, 3:1 $11.25, 1:1 $17.50, output only $30.00 per 1M.

The board shows this model's cheapest measured offer ($11.25/1M); the smaller figure under it is the mean of the 5 offers listed below ($11.25/1M). Add those up and divide — it matches. 1 offer(s) above 10x the median were left out of the average and flagged ⚠ in the table below — they are still listed, and still compete for the cheapest price. 24h token volume (23B) 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) $5.00$30.00 Official list
azure Pricebook (LiteLLM) $5.00$30.00 Official list
openai Pricebook (LiteLLM) $5.00$30.00 Official list
openrouter-best OpenRouter $5.00$30.00 API-measured
requesty Requesty $5.00$30.00 API-measured
burncloud ⚠ outlier burncloud $75.00$450 API-measured

Volume trend

175B 30d d-29 · 134B tokensd-28 · 151B tokensd-27 · 175B tokensd-26 · 148B tokensd-25 · 142B tokensd-24 · 109B tokensd-23 · 81B tokensd-22 · 67B tokensd-21 · 114B tokensd-20 · 108B tokensd-19 · 100B tokensd-18 · 99B tokensd-17 · 99B tokensd-16 · 70B tokensd-15 · 68B tokensd-14 · 88B tokensd-13 · 76B tokensd-12 · 47B tokensd-11 · 35B tokensd-10 · 37B tokensd-9 · 23B tokensd-8 · 0 tokensd-7 · 26B tokensd-6 · 39B tokensd-5 · 33B tokensd-4 · 40B tokensd-3 · 25B tokensd-2 · 0 tokensd-1 · 0 tokensd-0 · 23B tokens

Last 30 days: 134B → 23B (-83%); range 0–175B 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-5.5.json. Free reuse requires attribution to tkx.org.

About

GPT-5.5 is a large language model served by multiple inference providers on AI model marketplaces, known for its capabilities in natural language processing tasks. It is listed under the "azure_ai" serving-platform tag, indicating its association with Azure's AI services.

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

FAQ

How much does gpt-5.5 cost?

Cheapest measured offer right now: $5/1M input, $30/1M output via azure_ai — across 5 tracked providers, refreshed hourly.

Who serves gpt-5.5?

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-5.5 used?

gpt-5.5 routed 23B 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