This model was retired on 2026-02-27. The pricing below is the last-known rate, kept for migration reference.

GPT-4o (2024-08-06)Deprecated

OpenAIReleasedAug 6, 2024KnowledgeSep 2023
VisionTool usePrompt cachingStructured output
Context
128K
Max output
16K
Serving providers
2
Cheapest input
$2.50 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.

Benchmarks

independent evaluations · source: Artificial Analysis
Speed & latency
Output speed
57 t/s
tokens / second
Time to first token
7.18s
latency
Headline indices
Intelligence Index
9.6
of 100
Individual benchmarks · click a row for effort variants
BenchmarkBest scoreEffortCost / task
CritPt0%default
GPQA Diamond52%default
Humanity's Last Exam3%default
IFBench36%default
LiveCodeBench32%default
Long-Context Reasoning35%default
MMMU-Pro56%default
Omniscience-21.7default
SciCode33%default
TerminalBench Hard8%default
τ²-bench29%default

Pricing by serving provider

last-known · per 1M tokens · click a provider to expand
Serving providerInput /1MOutput /1MEndpoints
Azure$2.50$10.001
OpenAI$2.50$10.001

Price history

input + output $/1M since we started tracking
Input Output
$0.000$5.00$10.00Aug 6Oct 4Feb 1Jun 22$10.00$2.50

Cost calculator

estimate your monthly spend on this model
$1,300
estimated / month

Model IDs

copy the exact identifier for your platform
azure/global-standard/gpt-4o-2024-08-06gpt-4o-2024-08-06

Frequently asked questions

GPT-4o (2024-08-06) pricing, context and availability

Is GPT-4o (2024-08-06) still available?

GPT-4o (2024-08-06) was retired on 2026-02-27. The pricing on this page is the last-known rate, kept for migration reference.

How much did GPT-4o (2024-08-06) cost?

GPT-4o (2024-08-06)'s last-known pricing, before it was retired on 2026-02-27, was $2.50 per 1M input tokens and $10.00 per 1M output tokens.

What was the context window of GPT-4o (2024-08-06)?

GPT-4o (2024-08-06) had a 128K token context window and could return up to 16K output tokens.

What could GPT-4o (2024-08-06) do?

GPT-4o (2024-08-06) supported image input (vision), tool use, prompt caching and structured output.

Other OpenAI models

compare pricing across the OpenAI lineup
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI