Requesty
Sign in

identity

proprietary
OpenAI logo

gpt-5.6-terraOpenAI

from /1M in$1.00openai inc.
context1.1M128K out
best ttft875msmicrosoft azure ai
price spread2.2x10 endpoints
endpoints
10
regions
9
best tok/s
64
api
chat
released
July 2026
eu routing
available

capabilities 5/8

visionreasoningtoolscachingweb searchjson schemacomputer useimage gen

The same weights cost 2.2x more on microsoft azure ai than on openai inc.. That is what the endpoints table is for.

endpoints

10 / 9 regions
Providers serving gpt-5.6-terra, with pricing and measured performance. Best value in each column is coloured.
#flags
1OpenAI Inc.Global1.1M$1.00$6.00$0.101.36s53.0no-train
2OpenAI Inc.Global1.1M$2.00$12.00$0.201.36s53.0no-train
3Microsoft Azure AIeastus21.1M$2.00$12.00$0.20875ms48.0zdr
4Microsoft Azure AIfrancecentral1.1M$2.20$13.20$0.22875ms48.0zdr
5Microsoft Azure AIgermanywestcentral1.1M$2.20$13.20$0.22875ms48.0zdr
6Microsoft Azure AIswedencentral1.1M$2.20$13.20$0.22875ms48.0zdr
7Microsoft Azure AIwesteurope1.1M$2.20$13.20$0.22875ms48.0zdr
8AWS Bedrockus-east-11.1M$2.20$13.20$0.221.08s64.0zdr
9AWS Bedrockus-east-21.1M$2.20$13.20$0.221.08s64.0zdr
10AWS Bedrockus-west-21.1M$2.20$13.20$0.221.08s64.0zdr
provider price, no markupper 1M tokensblank where no qualifying sample

measured

through Sep 12
median
564ms1.40s2.23s07-0608-0309-071.61s1.16s738ms
hover the plot for weekly values
time to first token per provider: current value, window low and high, and change across the window
providernowlowhighchange
Microsoft Azure AI875ms710ms1.45s-43%
AWS Bedrock1.08s1.59s2.09s-23%
OpenAI Inc.1.36s703ms2.04s-32%

median wait before the first token lands. this is the number a user feels, and it moves with provider load through the day.

Lines are steps: each sample is one week of traffic held flat, not a slide from the week before. Click a name in the key to drop it from the plot. Measured through Sep 12.

benchmarks

artificial analysis
Benchmark scores, each normalised to 100
evalScore as a share of 100/100
GPQA Diamond92.5
τ²-Bench86.3
Coding Index76.7
Terminal-Bench Hard57.6
SciCode55.0
Humanity's Last Exam42.9
Intelligence Index42.3
7 evalsmean64.8

Scores from Artificial Analysis and public leaderboards, normalised to 100. Bar colour is the band, not the rank: green 80 and up, blue 55 and up, amber 30 and up. Benchmarks measure narrow skills, so test on your own workload before committing. Released 2026-07-09.

call it

model=
gpt-5.6-terra

requesty routes this id across every provider serving gpt-5.6-terra, picking on price and health and failing over automatically. the id stays valid when a provider changes underneath it

Base url is https://router.requesty.ai/v1 for every id here. One key reaches the whole catalog.

quickstart

openai compatible
main.py
from openai import OpenAI client = OpenAI(    api_key="YOUR_REQUESTY_API_KEY",    base_url="https://router.requesty.ai/v1",) response = client.chat.completions.create(    model="gpt-5.6-terra",    messages=[        {"role": "user", "content": "Explain quantum computing in one paragraph."},    ],) print(response.choices[0].message.content)

Change the base url, use your Requesty key, set the model to any id in the call pane. Existing OpenAI SDK code needs no other edit, and the same key reaches every other model in the catalog, so switching later is a one-parameter change. Browse all models

notes

reference

GPT-5.6 Terra is OpenAI's balanced frontier model for everyday production workloads, delivering near flagship reasoning, coding, and agentic performance at roughly half the cost of the previous generation. It features a 1M+ token context window with support for text and image inputs, server side tool calling, and prompt caching.

questions 7

Which providers serve gpt-5.6-terra?
gpt-5.6-terra is available from 3 providers through Requesty: OpenAI Inc., Microsoft Azure AI, AWS Bedrock. All endpoints share one OpenAI-compatible API and one key, and Requesty fails over between them automatically.
How much does gpt-5.6-terra cost?
Pricing starts at $1.00 per million input tokens and $6.00 per million output tokens on the cheapest provider. Prices vary by provider and region; the table above shows every endpoint. Requesty charges exactly what the upstream provider charges, with no markup.
Is gpt-5.6-terra open weights?
No. gpt-5.6-terra is a proprietary model from OpenAI, served through OpenAI's own API and licensed cloud platforms.
What is the context window of gpt-5.6-terra?
gpt-5.6-terra supports up to 1.1M tokens of context, with up to 128K output tokens per response. Some providers expose a smaller window; check the per-endpoint context column above.
Which provider is fastest for gpt-5.6-terra?
In recent production traffic through Requesty, Microsoft Azure AI had the lowest median time to first token (875ms) for gpt-5.6-terra. Latency shifts over time, so Requesty's latency-based routing picks the fastest healthy provider per request automatically.
How do I use gpt-5.6-terra 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 "gpt-5.6-terra" or any endpoint id from the table above. The quickstart section shows Python, JavaScript and cURL snippets.
Should I call gpt-5.6-terra by its managed id or a provider id?
Use the managed id, "gpt-5.6-terra". Requesty picks which of the 3 providers serves each request based on price and health, and fails over when one degrades, so the id keeps working while the routing changes underneath it. There is also an EU-only id, "gpt-5.6-terra@eu", which routes the same way but only through EU-hosted providers. Send a provider id like "openai/gpt-5.6-terra:flex" only when you need one specific deployment and want no failover.

more from openai 6

Other OpenAI models
modelcontextfrom /Mproviders
gpt-6-astra1.1M$5.002
gpt-5.6-luna1.1M$0.103
gpt-5.6-sol1.1M$2.503
gpt-5.5-pro1.1M$30.001
gpt-5.51.1M$2.503
gpt-5.4-nano400K$0.101

route gpt-5.6-terra through one endpoint

One key for 3 providers on this model and 600+ others. No markup on provider prices, automatic failover, caching built in. Weekly aggregates in the measured pane come from production traffic routed through Requesty, one line per provider on a shared axis. Methodology

gpt-5.6-terra3 providers10 endpointsfrom $1.00 /1M inctx 1.1Mttft 875msspread 2.2xupdated Sep 12