GPT-4o

GPT-4o is OpenAI's omni model of the GPT-4 generation, accepting text and image input with text output for general chat, analysis, and coding.

start building →
compare models

input · usd / 1m tok

$2.50

output · usd / 1m tok

$10.00

context window

128ktokens

modalities · in → out

takes text and image in, gives text out

pricing

base api ratesusd per 1m tokens

input
$2.50
output
$10.00
cache read
$1.25

providers

OpenAI hosts GPT-4o. Impossibl routes your request intelligently and handles failover automatically when a provider is down.

  • OpenAI

specifications

takes text and image in, gives text outopenai/gpt-4o

  • creatorOpenAI
  • model typeText generation
  • context window128,000 tokens
  • maximum outputnot published
  • input

    takes text and image in, gives text out

  • outputtext
  • tool callingnot verified
  • releasedmay 13, 2024
  • endpoint/v1/chat/completions

unknown means the public catalog does not establish that fact. a model's documented capabilities can differ from what a particular api supports. see the model documentation for integration details.

try it · your prompt, this model, live

# responses API
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["IMPOSSIBL_API_KEY"],
    base_url="https://api.impossibl.com/v1",
)

resp = client.responses.create(
    model="openai/gpt-4o",
    input="",
)
print(resp.output_text)

edit the prompt, then run

benchmarks

intelligence index

8.4#101 of 108 models on the gateway

  1. omniscience-10.5#52 of 84
  2. gpqa54.3%#75 of 80
  3. humanity’s last exam2.4%#87 of 87
  1. GPQA54.3%
  2. AA-LCR49.3%
  3. IFBench34.3%
  4. LiveCodeBench30.9%
  5. Tau225.1%
  6. Terminal-Bench Hard8.3%
  7. AIME 20256.0%
  8. Humanity’s Last Exam2.4%
  9. CritPt0.0%
  • Intelligence Index8.44
  • Omniscience Index-10.52
  • GDPval Elo-16.75
  • intelligence index (API)8.4

view source ↗all source data and breakdowns (json) ↗

each configuration is listed separately; these evaluations describe the tested model configuration, and performance and costs can differ on impossibl. unmeasured scores are omitted and api values keep their source units. last checked 2026-10-14.

compare GPT-4o with other models

frontier labs and open weights, best-ranked firstusd / 1m tok · in / out

impossibl models --all →

frequently asked questions

What is GPT-4o?

GPT-4o is OpenAI's omni model of the GPT-4 generation, accepting text and image input with text output for general chat, analysis, and coding. It matches the intelligence of GPT-4 Turbo while responding faster, and is the base for the smaller GPT-4o mini.

How much does GPT-4o cost?

GPT-4o costs $2.50 per million input tokens and $10.00 per million output tokens through the Impossibl API. Cache reads cost $1.25 per million tokens. All rates are in USD.

view the pricing table ↑

What is the context length of GPT-4o?

GPT-4o has a 128,000-token context window through the Impossibl API.

What inputs and outputs does GPT-4o support?

GPT-4o accepts text and image as input. GPT-4o returns text.

How do I use GPT-4o through an API?

GPT-4o is available through the Impossibl API. Use openai/gpt-4o as the model identifier with /v1/chat/completions. The quickstart explains how to create an API key and send your first request.

follow the api quickstart →

When was GPT-4o released?

OpenAI released GPT-4o on May 13, 2024.

this page describes GPT-4o as listed by the impossibl public api. prices and availability come from that catalog, refreshed here every five minutes. this is an impossibl offering, not a comparison of independent hosting-provider quotes. model descriptions and release dates, where available, use the creator sources linked under the answers above.

view the source catalog ↗model as markdown ↗report a correction →