OpenAI Inc.
Leading AI research company behind GPT models and ChatGPT. Requesty routes to 47 OpenAI Inc. models starting at $0.02 per 1M input tokens with context windows up to 1.1M tokens. One API key, OpenAI-compatible SDK, no markup.
Flagship model
gpt-5.4MMLU Pro
91.2%
GPQA
86.5%
HumanEval
96.4%
SWE-Bench
82.1%
All OpenAI Inc. models
| Model | Context | Max Output | Input/1M | Output/1M | Capabilities | SWE-Bench |
|---|---|---|---|---|---|---|
gpt-5.5 | 1.1M | 128K | $5.00 | $30.00 | 👁🧠🔧⚡ | — |
gpt-5.5-pro | 1.1M | 128K | $30.00 | $180.00 | 👁🧠🔧 | — |
gpt-5.3-chat | 128K | 16K | $1.75 | $14.00 | 👁🧠🔧⚡ | — |
gpt-5.4-mini | 400K | 128K | $0.75 | $4.50 | 👁🧠🔧⚡ | — |
gpt-5.4-nano | 400K | 128K | $0.20 | $1.25 | 👁🧠🔧⚡ | — |
gpt-5.4-pro | 1.1M | 128K | $30.00 | $180.00 | 👁🧠🔧 | — |
gpt-5.4 | 1.1M | 128K | $2.50 | $15.00 | 👁🧠🔧⚡ | 82% |
gpt-5.2-chat | 128K | 16K | $1.75 | $14.00 | 👁🧠🔧⚡ | 80% |
gpt-5.2 | 400K | 128K | $1.75 | $14.00 | 👁🧠🔧⚡ | 80% |
gpt-5.1-chat | 128K | 16K | $1.25 | $10.00 | 👁🧠🔧⚡ | 77% |
gpt-5:priority | 400K | 128K | $2.50 | $20.00 | 👁🧠🔧⚡ | 75% |
gpt-5-chat | 128K | 16K | $1.25 | $10.00 | 👁🧠🔧⚡ | 75% |
gpt-5:flex | 400K | 128K | $0.63 | $5.00 | 👁🧠🔧⚡ | 75% |
gpt-5-mini:priority | 400K | 128K | $0.45 | $3.60 | 👁🧠🔧⚡ | — |
gpt-5.1 | 400K | 128K | $1.25 | $10.00 | 👁🧠🔧⚡ | 77% |
gpt-5 | 400K | 128K | $1.25 | $10.00 | 👁🧠🔧⚡ | 75% |
gpt-5-nano:flex | 400K | 128K | $0.02 | $0.20 | 👁🧠🔧⚡ | — |
gpt-5-nano | 400K | 128K | $0.05 | $0.40 | 👁🧠🔧⚡ | — |
gpt-5-mini | 400K | 128K | $0.25 | $2.00 | 👁🧠🔧⚡ | — |
gpt-5-mini:flex | 400K | 128K | $0.13 | $1.00 | 👁🧠🔧⚡ | — |
o3-deep-research | 100K | 200K | $10.00 | $40.00 | 👁🧠🔧⚡ | — |
o4-mini-deep-research | 100K | 200K | $2.00 | $8.00 | 👁🧠🔧⚡ | — |
o3:flex | 200K | 100K | $1.00 | $4.00 | 👁🧠🔧⚡ | 72% |
o3 | 200K | 100K | $2.00 | $8.00 | 👁🧠🔧⚡ | 72% |
o4-mini:high | 200K | 100K | $1.10 | $4.40 | 🧠🔧⚡ | — |
o4-mini:flex | 200K | 100K | $0.55 | $2.20 | 🧠🔧⚡ | — |
o4-mini:low | 200K | 100K | $1.10 | $4.40 | 🧠🔧⚡ | — |
o4-mini:medium | 200K | 100K | $1.10 | $4.40 | 🧠🔧⚡ | — |
o4-mini | 200K | 100K | $1.10 | $4.40 | 🧠🔧⚡ | — |
gpt-4.1 | 1.0M | 33K | $2.00 | $8.00 | 👁🔧⚡ | 68% |
gpt-4.1-mini | 1.0M | 33K | $0.40 | $1.60 | 👁🔧⚡ | 55% |
gpt-4.1-nano | 1.0M | 33K | $0.10 | $0.40 | 👁🔧⚡ | 43% |
o1-pro | 200K | 100K | $150.00 | $600.00 | 👁🧠🔧 | — |
o3-mini | 200K | 100K | $1.10 | $4.40 | 🧠🔧⚡ | 61% |
o3-mini:medium | 200K | 100K | $1.10 | $4.40 | 🧠🔧⚡ | 61% |
o3-mini:high | 200K | 100K | $1.10 | $4.40 | 🧠🔧⚡ | 61% |
o3-mini:low | 200K | 100K | $1.10 | $4.40 | 🧠🔧⚡ | 61% |
o1 | 200K | 100K | $15.00 | $60.00 | 👁🧠🔧⚡ | 49% |
o1:low | 200K | 100K | $15.00 | $60.00 | 👁🧠🔧⚡ | 49% |
o1:high | 200K | 100K | $15.00 | $60.00 | 👁🧠🔧⚡ | 49% |
o1:medium | 200K | 100K | $15.00 | $60.00 | 👁🧠🔧⚡ | 49% |
gpt-4o-2024-05-13 | 128K | 4K | $2.50 | $10.00 | 👁🔧⚡ | — |
gpt-4o-2024-11-20 | 128K | 16K | $2.50 | $10.00 | 👁🔧⚡ | — |
gpt-4o-2024-08-06 | 128K | 16K | $2.50 | $10.00 | 👁🔧⚡ | — |
gpt-4o | 128K | 16K | $2.50 | $10.00 | 👁🔧⚡ | 38% |
chatgpt-4o | 128K | 16K | $5.00 | $15.00 | 👁🔧⚡ | — |
gpt-4o-mini | 128K | 16K | $0.15 | $0.60 | 👁🔧⚡ | — |
About OpenAI Inc. on Requesty
How many OpenAI Inc. models are available through Requesty?
Requesty routes to 47 OpenAI Inc. models including regional variants, with pricing synced in real time to the upstream provider.
What is the cheapest OpenAI Inc. model?
The cheapest OpenAI Inc. model starts at $0.02 per million input tokens. See the pricing column in the table below for full per-model rates.
Does Requesty add markup on OpenAI Inc. pricing?
No. Requesty passes through exactly what OpenAI Inc. charges. You pay the same per-token rates as going direct — plus you get smart routing, caching, analytics, and one unified API for 400+ models.
Is my data used to train OpenAI Inc. models?
OpenAI Inc.'s terms state that API data is not used for training. See their privacy policy for the authoritative statement.
Where are OpenAI Inc. models hosted?
OpenAI Inc. models are hosted in 🇺🇸 US. Some models are available in additional regions through AWS Bedrock, Azure, or Google Vertex AI — filter by region on the OpenAI Inc. rows in the models explorer.