GPT-5.5 · Azure API pricing
OpenAI's GPT series — broad general capability, wide ecosystem, and the native models behind Codex CLI.
azure/gpt-5.5Call summary
Applies to request input ≤ 272,000 tokens · See pricing tiers
GPT-5.5 · Azure API endpoints
One API key — call this model through any of the 2 endpoints below.
GPT-5.5 · Azure pricing tiers
Pricing is tiered by total input length per request (cache included); once a threshold is crossed, the whole request is billed at that tier. All prices are per 1M tokens.
Production reliability
Privacy-safe aggregates from real Router One model calls, so you can assess stability and response latency before integrating.
96.85%
96.85%
0.00%
3.15%
—
tokens/s—
15.01 s
Includes production requests ending in 2xx, 429, or 5xx. Average latency uses successful requests; time to first token and TPS require complete observations from successful streams. Public thresholds are 100 requests and 5 independent principals.
Updated Nov 10, 2026, 3:54 PM UTC
More GPT models on Router One
21 other GPT models on the same gateway and API key — each page lists endpoints, posted price, and context window.
7 channel versions
GPT-5.5 · Azure at a glance
GPT-5.5 · Azure (model ID azure/gpt-5.5) is a GPT-series text model on Router One. GPT-5.5 · Azure is sold on the Azure sales channel: a separately priced product with an isolated routing pool — requests never fall back to the default channel, its rates and long-context tiers are its own, a plan quota covers it only when the live plan response lists the channel id, and the response model field and Dashboard → Logs carry the channel id. No Router One subscription plan includes GPT-5.5 · Azure today; every call bills the wallet at its posted rate. GPT-5.5 · Azure is priced in whole-request tiers. Request input ≤ 272,000 tokens: Input $3.75 / 1M tokens, Output $22.50 / 1M tokens, Cache write $3.75 / 1M tokens, Cached input $0.375 / 1M tokens; request input > 272,000 tokens: Input $7.50 / 1M tokens, Output $33.75 / 1M tokens, Cache write $7.50 / 1M tokens, Cached input $0.75 / 1M tokens. The total input tokens in each request select the tier; its rates apply to the whole request, not only tokens above the threshold. Context window: 1.05M tokens. Accepts text, image; returns text. Endpoints: POST /v1/chat/completions (OpenAI-compatible), POST /v1/responses (Responses API, the Codex CLI path).
GPT-5.5 · Azure FAQ
How much does GPT-5.5 · Azure cost on Router One?
GPT-5.5 · Azure is priced in whole-request tiers. Request input ≤ 272,000 tokens: Input $3.75 / 1M tokens, Output $22.50 / 1M tokens, Cache write $3.75 / 1M tokens, Cached input $0.375 / 1M tokens; request input > 272,000 tokens: Input $7.50 / 1M tokens, Output $33.75 / 1M tokens, Cache write $7.50 / 1M tokens, Cached input $0.75 / 1M tokens. The total input tokens in each request select the tier; its rates apply to the whole request, not only tokens above the threshold.
Is GPT-5.5 · Azure included in Router One subscriptions?
No Router One subscription plan includes GPT-5.5 · Azure today; every call bills the wallet at its posted rate.
Which endpoints serve GPT-5.5 · Azure?
GPT-5.5 · Azure is served on 2 endpoints — POST /v1/chat/completions (OpenAI-compatible), POST /v1/responses (Responses API, the Codex CLI path). The same Router One API key works on each.
What is GPT-5.5 · Azure's context window?
GPT-5.5 · Azure accepts up to 1.05M tokens of context per request on Router One.
What does the azure/ prefix in azure/gpt-5.5 mean?
azure/ selects the Azure sales channel on Router One: a separately priced product whose routing stays inside the Azure channel and never falls back to the default channel, with posted rates and tiers of its own, plan quota only when the live plan response lists the channel id, and the channel id echoed in the response and in every request trace. Router One publishes the channel label and the customer price, not the suppliers or regions behind it; the channel model ids guide on the blog states the full rules. No Router One subscription plan includes GPT-5.5 · Azure today; every call bills the wallet at its posted rate.
Start using GPT-5.5 · Azure
Create an API key and call GPT-5.5 · Azure at $3.75 in / $22.50 out per 1M tokens (request input ≤ 272,000 tokens) on Router One — pay as you go, with per-request cost and latency visibility.