Scheduled for retirement on Apr 14, 2027. Still available at the prices below until then.
Context
128K
Max output
16K
Serving providers
3
Cheapest input
$2.50 /1M
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Benchmarks
independent evaluations · source: Artificial AnalysisSpeed & latency
Output speed
145 t/s
tokens / second
Time to first token
0.90s
latency
Headline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| CritPt | 0% | default | — | |||||||||||||
| GPQA Diamond | 52% | default | — | |||||||||||||
| ||||||||||||||||
| Humanity's Last Exam | 2% | default | — | |||||||||||||
| IFBench | 36% | default | — | |||||||||||||
| LiveCodeBench | 32% | default | — | |||||||||||||
| Long-Context Reasoning | 41% | default | — | |||||||||||||
| MMMU-Pro | 56% | default | — | |||||||||||||
| Omniscience | -20.9 | default | — | |||||||||||||
| Omniscience Accuracy | 0.2 | default | — | |||||||||||||
| Omniscience Non Hallucination | 0.4 | default | — | |||||||||||||
| SciCodeArtificial Analysis did not report this score in its latest run on Oct 14, 2026 | 33% | — | — | |||||||||||||
| TerminalBench Hard | 8% | default | — | |||||||||||||
| τ²-bench | 29% | default | — | |||||||||||||
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expand| Serving provider | Input /1M | Output /1M | Endpoints | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Azure | $2.50 | $10.00 | 1 | |||||||||||||||||
Standardazure/global-standard/gpt-4o-2024-08-06
| ||||||||||||||||||||
| OpenAICheapest | $2.50 | $10.00 | 1 | |||||||||||||||||
Standardgpt-4o-2024-08-06
| ||||||||||||||||||||
| OpenRouter | $2.50 | $10.00 | 1 | |||||||||||||||||
Standardopenai/gpt-4o-2024-08-06
| ||||||||||||||||||||
Price history
listed seller prices, input and output per 1M tokens Input Output
Cost calculator
estimate your monthly spend on this model$1,300
estimated / month
Model IDs
copy the exact identifier for your platformgpt-4o-2024-08-06openai/gpt-4o-2024-08-06azure/global-standard/gpt-4o-2024-08-06
Frequently asked questions
GPT-4o (2024-08-06) pricing, context and availabilityIs GPT-4o (2024-08-06) still available?
Yes. GPT-4o (2024-08-06) is scheduled for retirement on 2027-04-14.
How much does GPT-4o (2024-08-06) cost?
GPT-4o (2024-08-06) costs $2.50 per 1M input tokens from OpenAI, and $10.00 per 1M output tokens from OpenAI.
What is the context window of GPT-4o (2024-08-06)?
GPT-4o (2024-08-06) accepts up to 128K tokens of context and can return up to 16K output tokens.
Which providers serve GPT-4o (2024-08-06)?
GPT-4o (2024-08-06) is available from 3 serving providers, each with its own pricing and model ID. OpenAI is currently the cheapest.
What can GPT-4o (2024-08-06) do?
GPT-4o (2024-08-06) supports image input (vision), tool use, prompt caching and structured output.
Other OpenAI models
compare pricing across the OpenAI lineup Listed prices from LiteLLM, OpenRouter and Vercel · last checked Oct 14, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI