gpt-5-nano
Microsoft Azure AI/🇺🇸 US/chat
GPT-5 Nano is our fastest, cheapest version of GPT-5. It's great for summarization and classification tasks.
Which id to call
azure/gpt-5-nanoThis exact deployment on Microsoft Azure AI, with no routing and no failover. Send it as the model field.
Input /1M
$0.05
$0.0050 cached
Output /1M
$0.40
8.0x input
Context
200K
100K output
Paid /1M
$0.10
measured, cache included
Capabilities 4/8
Provider rates
What gpt-5-nano costs
Provider prices per 1M tokens, updated September 5, 2026.moreless
These are the upstream provider rates. Pay as you go adds 5%, or 0% if you bring your own keys, and there is no per-request fee. Prompt caching and routing change what you pay against these rates, not the rates themselves.
Input /1M
$0.05
Output /1M
$0.40
Cache write /1M
-
Cache read /1M
$0.0050
What a workload costs
- 100K input + 10K output
- $0.0090
- 1M input + 100K output
- $0.0900
- 10M input + 1M output
- $0.90
At the rates above, before caching. A cache read costs $0.0050 per 1M, so repeated context lands under these figures.
model=
Which id to call
One base url, https://router.requesty.ai/v1, and one key for every id here.
azure/gpt-5-nanoThis exact deployment on Microsoft Azure AI, with no routing and no failover. Send it as the model field.
OpenAI compatible
Call it in three lines
Change the base url, use your Requesty key, set the model to any id on the left. Existing OpenAI SDK code needs no other edit.
123456789101112131415from openai import OpenAI client = OpenAI( api_key="YOUR_REQUESTY_API_KEY", base_url="https://router.requesty.ai/v1", ) response = client.chat.completions.create( model="azure/gpt-5-nano", messages=[ {"role": "user", "content": "Explain quantum computing in one paragraph."}, ], ) print(response.choices[0].message.content)
Live from production
Microsoft Azure AI on gpt-5-nano, measured
What this provider was measured doing on gpt-5-nano across Requesty traffic.moreless
Whole-window figures, because that is the grain published per provider. They cover Microsoft Azure AI serving this model in every region it serves it from, so a region-pinned deployment shares them with its siblings. A figure is absent where no qualifying sample exists.
First token
5.59s
median
p95 wait
28.72s
slowest 5%
Output speed
152/s
median tokens
Paid /1M
$0.10
blended, cache included
Cache hit
56.8%
of input tokens
Compare these against the other 2 providers serving gpt-5-nano.
Reference
Specs and data terms
What the catalog reports for this deployment, and what the provider does with the traffic.
Released 2025-08-07
Benchmark scores
Benchmarks measure the model, not this endpoint, so they are the same wherever these weights are served.
Graduate-level physics, chemistry & biology questions designed to resist Googling.
Artificial Analysis Intelligence Index: a composite of multiple evaluations measuring overall model capability.
Scores from official model cards, Artificial Analysis and public leaderboards. They measure specific skills and do not capture every aspect of model quality, so test on your own workload.
Same provider
More from Microsoft Azure AI
Newest first, on the same provider and the same key.
Reference
gpt-5-nano questions
How much does gpt-5-nano cost?
gpt-5-nano is priced at $0.05 per million input tokens and $0.40 per million output tokens when accessed via Requesty. Prompt caching is supported, which can cut effective input cost by up to 90% on repeated context. Those are the upstream provider rates: pay as you go adds 5% on top, or 0% if you bring your own provider keys.
What is the context window of gpt-5-nano?
gpt-5-nano has a context window of 200K tokens, with a maximum output of 100K tokens per response. That's roughly 267 words of input you can fit in a single prompt.
How does gpt-5-nano perform on benchmarks?
gpt-5-nano scores 83.7% on Math Index, 83.7% on AIME 2025, 78.9% on LiveCodeBench. See the full benchmark chart above for results across MMLU Pro, GPQA Diamond, SWE-Bench Verified, HumanEval, MATH, AIME, MMMU, and LiveBench.
What can gpt-5-nano do?
gpt-5-nano supports tool calling, extended reasoning, prompt caching, structured outputs (JSON schema). You can call it through any OpenAI-compatible client by pointing base_url to Requesty.
How do I use gpt-5-nano with the OpenAI SDK?
Install the OpenAI SDK, set base_url to "https://router.requesty.ai/v1", set your API key to your Requesty key, and set the model to "azure/gpt-5-nano". The Quickstart above shows Python, JavaScript and cURL snippets.
Can I run gpt-5-nano through Requesty?
Yes. gpt-5-nano runs through Requesty's OpenAI-compatible API, served from Microsoft Azure AI. You do not host the model yourself: point base_url at Requesty, set the model to "azure/gpt-5-nano", and requests are routed to the upstream provider with automatic failover. The same key gives you 600+ other models too.
Call gpt-5-nano through one endpoint
One key for this endpoint and 600+ other models. No markup on provider prices, automatic failover, caching built in.