As of August 20, 2026, GPT-4o API pricing is $2.50 per million input tokens and $10.00 per million output tokens. A typical 100K-in / 20K-out request costs $0.45. Source: https://developers.openai.com/api/docs/pricing
Source: OpenAI API pricing (https://developers.openai.com/api/docs/pricing)
Input $/M
$2.50
Output $/M
$10.00
Blended / 1M
$12.50
100K / 20K request
$0.45
| Context Window | 128K |
|---|---|
| Max Output | 16.4K tokens |
| Release Date | 2024-08-06 |
| Knowledge Cutoff | October 2023 |
| License | Proprietary |
| Throughput | 99 tok/s |
| HLE | 5.3% |
|---|---|
| GPQA | 70.1% |
| GPQA Diamond | 49.2% |
| SWE-bench Verified | 33.2% |
| SimpleQA | 38.2% |
| IFEval | 81% |
| tau-bench Retail | 60.3% |
| tau2-bench (Telecom) | 23.5% |
| MMMU-Pro | 59.9% |
| MMMLU | 81.4% |
| CharXiv-R | 58.8% |
| FinanceAgent v1.1 | 8.1% |
| FrontierMath | 0.3% |
| AIME 2025 | 6.4% |
| AIME 2024 | 13.1% |
| MATH 500 | 75.2% |
| Alder Polyglot | 30.7% |
| MMLU | 85.7% |
| MMMU | 72.2% |
| MATH | 53.3% |
| Activitynet | 61.9% |
| Ai2d | 94.2% |
| Aider Polyglot Edit | 18.2% |
| Chartqa | 85.7% |
| Charxiv D | 85.3% |
| Collie | 61% |
| Complexfuncbench | 66.5% |
| CorpFin v2 | 39.4% |
| Docvqa | 92.8% |
| Egoschema | 72.2% |
| ERQA | 35.2% |
| Graphwalks Bfs 128k | 41.7% |
| Graphwalks Parents 128k | 35.4% |
| LiveBench | 55.3% |
| MathVista | 61.4% |
| MedQA | 88.2% |
| MGSM | 90.7% |
| MMLU-Pro | 74.7% |
| Multi If | 60.9% |
| Multichallenge | 40.3% |
| Openai Mrcr 2 Needle 128k | 31.9% |
| SimpleBench | 17.8% |
| Swe Lancer | 32.6% |
| Swe Lancer Ic Diamond Subset | 12.4% |
| Tau Bench Airline | 42.8% |
| tau2-bench Airline | 45.5% |
| tau2-bench Retail | 63.4% |
| tau2-bench Telecom | 23.5% |
| Tax Eval v2 | 71.1% |
| Video-MME | 71.9% |
| VideoMMMU | 61.2% |
Same search as the hub. Pick any model, or jump into a priced matchup.
OpenAI
Anthropic
Google
xAI
DeepSeek
MiniMax
Qwen
As of August 20, 2026, GPT-4o OpenAI API pricing is $2.50 per million input tokens and $10.00 per million output tokens. Input tokens are the prompt you send; output tokens are the completion. Long answers therefore cost more than short ones even when the prompt stays the same. Source: https://developers.openai.com/api/docs/pricing
On this page the blended GPT-4o API cost is $12.50 for 1 million input tokens plus 1 million output tokens. That 1:1 mix is the comparison scale used across the LLM pricing table. A 3:1 mix (three million input tokens per one million output tokens), which some calculators use, would be about $17.50.
A typical GPT-4o API request with 100K input tokens and 20K output tokens costs about $0.45 at current rates as of August 20, 2026. Multiply that by daily or monthly volume to estimate spend. Caching, batch APIs, and volume discounts from OpenAI can bring the real invoice lower than the public list rate at https://developers.openai.com/api/docs/pricing.
GPT-4o supports a 128K token context window and can generate up to 16K output tokens per request. The context window is the total prompt plus conversation history the model can see in one call. Larger windows cost more when you fill them, because every input token is billed per million tokens.
No. GPT-4o is a proprietary model by OpenAI. The only public way to call it is OpenAI's API, billed per million input and output tokens. There is no self-host option for the weights.
GPT-4o currently reports HLE 5.3%, GPQA 70.1%, GPQA Diamond 49.2%. See the performance table for the full eval set. Use those scores with the token prices above when you are choosing between a cheaper LLM and a frontier model. GPQA, SWE-bench, and HLE are the evals people usually compare first.
GPT-4o scores 33.2% on SWE-bench Verified. Pair that score with OpenAI API pricing on this page: a slightly worse SWE-bench model can still win if it is much cheaper per million tokens. Open the SWE-bench or coding leaderboard from the sidebar for the full ranking, then jump into an LLM comparison against a coding specialist.
GPT-4o has a published knowledge cutoff of October 2023. Facts after that date are not guaranteed to be in the weights. For current events you still need retrieval or tools, which adds input tokens and therefore API cost per million tokens.
Use the Compare picker on this page to start an LLM comparison. Search by model or provider, pick a second model, and AnotherWrapper opens a dedicated GPT-4o vs page with per-million-token prices, blended 1M-in / 1M-out cost, context window, throughput, and benchmarks. You can also open any model from the sidebar, or go back to the LLM pricing table to sort the full index.
The cheapest LLM alternative depends on whether you optimize for blended token cost, coding evals, or context window. Start with the popular matchups on this page, then sort the LLM pricing table by blended cost to see which hosted APIs undercut GPT-4o. Open-weight models can be cheaper still if you self-host, but that is not the same as OpenAI API pricing on this page.
GPT-4o is called through OpenAI's API with an API key. Bill against input and output tokens separately; cache or shorten prompts if spend is high. If you are shipping a full product, AnotherWrapper includes pre-built API routes and templates for OpenAI and 5+ other providers with auth, payments, and deployment already configured.
This GPT-4o page tracks the latest published OpenAI API pricing from OpenAI, quoted per million tokens. List rates can differ from invoices because of prompt caching, batch discounts, committed-use tiers, and private contracts. Official rate sheet: https://developers.openai.com/api/docs/pricing. Benchmark scores come from official publications and independent evals, not from a private lab run by AnotherWrapper.
GPT-4o has a measured throughput of about 99 tokens per second (tok/s). Throughput is how fast completions stream once the model starts generating; time-to-first-token can still lag under load. Faster APIs matter when you are building chat or agents, even if the per-million-token price is the same.
GPT-4o is a proprietary model from OpenAI. Current API pricing is $2.50 per million input tokens and $10.00 per million output tokens, with a 128K token context window. A blended 1M-in / 1M-out workload costs $12.50.
Rank it on the LLM leaderboard, SWE-bench, and Humanity's Last Exam.
The index
281 models across 33 providers. Search or jump to a lab — every model page stays linked here.
Next step
Auth, billing, and the API layer are already decided. Fork 8 finished AI apps, or have us build the first version with you.
