Identity
- Status
- active
- Developer ID
gpt-4o-2024-08-06- Released
- Not reported
- Version
- GPT-4o
- License
- Unknown
GPT-4o is OpenAI's versatile multimodal GPT model for text and image inputs.
| Provider | Input / 1M | Output / 1M | Cache read / 1M | Cache write / 1M | Observed | Evidence |
|---|---|---|---|---|---|---|
OpenAIAvailable | $2.50 | $10.00 | $1.25 | — | Aug 29, 2026 | Provider-reported |
OpenrouterAvailable | $2.50 | $10.00 | $1.25 | — | Sep 2, 2026 | Provider-reported |
| GPT-4oOpenAI | Aider Polyglotpolyglot-225-5dc9490bb35f | 23.11 | — | 225 | diff; aider 0.70.1.devunknown | Recomputedwinner eligible | Third-party benchmark |
| GPT-4oOpenAI | LMArena Text Arenatext-2026-09-01-011508720696 | 1,282.33 | — | 45,499 | gpt-4o-2024-08-06; 95% CI [1278.14385443, 1286.52509361]; votes 45499; rank 250unknown | Original sourcewinner eligible | Third-party benchmark |
| GPT-4oOpenAI | LMArena Vision Arenavision-2026-08-27-011508720696 | 1,064.54 | — | 3,376 | gpt-4o-2024-08-06; 95% CI [1052.10281463, 1076.97369812]; votes 3376; rank 119unknown | Original sourcewinner eligible | Third-party benchmark |
| GPT-4oOpenAI | ToneBench2026-08-14-10-task | 57.17 | 1,184 | 50 | GPT-4oaverage per case | Original sourcewinner eligible | Third-party benchmark |
At a Glance
gpt-4o-2024-08-06This page represents one immutable developer model ID. Serving endpoints, pricing, regions, quantizations, and service tiers attach separately and never create duplicate model records.
Primary Evidence
Comparable Peers
| A | Pair | B | Context |
|---|---|---|---|
GPT-4oOpenAI | vs | GPT-4.1OpenAI | family variantsimage, text |
GPT-4oOpenAI | vs | GPT-4.1 MiniOpenAI | family variantsimage, text |
GPT-4oOpenAI | vs | GPT-4.1 NanoOpenAI | family variantsimage, text |
GPT-4oOpenAI | vs | GPT-5.6 LunaOpenAI | family variantsimage, text |
GPT-4oOpenAI | vs | cross-developer peersimage, text | |
GPT-4oOpenAI | vs | GLM-OCRZ.ai | cross-developer peersimage, text |
GPT-4oOpenAI | vs | Claude Haiku 4.5Anthropic | cross-developer peersimage, text |
GPT-4oOpenAI | vs | cross-developer peersimage, text | |
GPT-4oOpenAI | vs | Gemini 3.6 FlashGoogle DeepMind | cross-developer peerstext |
GPT-4oOpenAI | vs | SonarPerplexity | cross-developer peerstext |
GPT-4oOpenAI | vs | stable-diffusion-3.5-largeStability AI | cross-developer peersimage |
GPT-4oOpenAI | vs | stable-diffusion-3.5-mediumStability AI | cross-developer peersimage |
Questions
GPT-4o is OpenAI's versatile multimodal GPT model for text and image inputs. It is developed by OpenAI and its current sourced lifecycle status is active.
GPT-4o's current record lists Text and Image as input and Text as output.
The current record lists a 128,000-token context window and a maximum output of 16,384 tokens.
GPT-4o is marked as API-available. The directly sourced provider records currently include OpenAI and Openrouter.
The lowest directly sourced prices currently attached to GPT-4o are $2.50 per million input tokens through OpenAI and $10.00 per million output tokens through OpenAI. Prices are provider-specific and should be checked against each cited observation date.
GPT-4o's recorded capabilities are chat, generation, and tools. Its supported tasks are image and text.
GPT-4o is not marked as an open-weight model. Self-hosting is marked as unsupported, with no license recorded.
No predecessor is recorded. No successor is recorded. Recorded aliases are gpt-4o and gpt-4o-2024-08-06.
The current compatible peer set includes GPT-4.1, GPT-4.1 Mini, GPT-4.1 Nano, GPT-5.6 Luna, and granite-vision-4.1-4b. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons →
GPT-4o was last verified Aug 29, 2026 from OpenAI's primary source, “GPT-4o Model | OpenAI API.” The evidence is classified as official fact.