OpenAI / generation
GPT-4o family
GPT-4o variants retain their own model IDs, prices and rating coverage. API usage is separate from a ChatGPT subscription; Codex and Pro labels need endpoint-specific interpretation.
Family research reviewed · Official source notes below
- Standard models
- 6
- Independently rated
- 3 / 6
- Known token rates
- 6 / 6
- Global balanced frontier
- 0
This collection organises accepted catalogue identities. It does not certify equal weights, a shared licence, benchmark equivalence or current availability on every serving platform.
Compare exact catalogue rows
USD per 1M tokens. In / out are listed base rates; expand billing conditions before planning a request. LMArena scores measure the general preference board, not success on your engineering task. Unknown stays unknown.
Catalogue members
| Model | LMArena | Input / output $/M | Context / max output | Capabilities & conditions |
|---|---|---|---|---|
GPT-4o (2024-11-20)openai/gpt-4o-2024-11-20 | Unrated | $2.50 / $10.00Listed base ratesBilling details
Tool, media, cache-write and service-tier charges may add dimensions. Read the full model evidence. | 128,000Output 16,384 | text · image · fileTools yes · reasoning noClosed weightsReleased 2024-11-20 |
GPT-4o (2024-08-06)openai/gpt-4o-2024-08-06 | 1282.5±4.2 interval half-widthEffort: default | $2.50 / $10.00Listed base ratesBilling details
Tool, media, cache-write and service-tier charges may add dimensions. Read the full model evidence. | 128,000Output 16,384 | text · image · fileTools yes · reasoning noClosed weightsReleased 2024-08-06 |
GPT-4o-miniopenai/gpt-4o-mini | Unrated | $0.150 / $0.600Listed base ratesBilling details
Tool, media, cache-write and service-tier charges may add dimensions. Read the full model evidence. | 128,000Output 16,384 | text · image · fileTools yes · reasoning noClosed weightsReleased 2024-07-18 |
GPT-4o-mini (2024-07-18)openai/gpt-4o-mini-2024-07-18 | 1286.4±3.5 interval half-widthEffort: default | $0.150 / $0.600Listed base ratesBilling details
Tool, media, cache-write and service-tier charges may add dimensions. Read the full model evidence. | 128,000Output 16,384 | text · image · fileTools yes · reasoning noClosed weightsReleased 2024-07-18 |
GPT-4oopenai/gpt-4o | Unrated | $2.50 / $10.00Listed base ratesBilling details
Tool, media, cache-write and service-tier charges may add dimensions. Read the full model evidence. | 128,000Output 16,384 | text · image · fileTools yes · reasoning noClosed weightsReleased 2024-05-13 |
GPT-4o (2024-05-13)openai/gpt-4o-2024-05-13 | 1300.4±3.4 interval half-widthEffort: default | $5.00 / $15.00Listed base ratesBilling details
Tool, media, cache-write and service-tier charges may add dimensions. Read the full model evidence. | 128,000Output 4,096 | text · image · fileTools yes · reasoning noClosed weightsReleased 2024-05-13 |
Free and batch variants
These rows have different access or processing conditions. They are excluded from the standard-row counts above. A variant without a standard base remains a separately named variant.
- GPT-4o-mini (batch)batch · $0.075 in / $0.300 out per 1M
- GPT-4o (batch)batch · $1.25 in / $5.00 out per 1M
Sources and scope
- OpenAI model catalogue ↗
Exact named models on the vendor platform; not a promise about every reseller
Checked 2026-09-22 · official document opened and inspected
Source review does not refresh a price or transplant a benchmark score. Read the method and correction policy.
Questions this page answers
Are the GPT-4o family models interchangeable?
No. These are exact catalogue rows with separate capability, pricing and rating evidence. Compare the checkpoint, serving endpoint, reasoning settings and required input types. A family name does not establish equivalent behaviour.
How many OpenAI rows are compared here?
6 standard rows, of which 3 have an accepted LMArena general score and 6 have known input and output token rates. 2 related free or batch variants are listed separately.
What do the prices and frontier counts mean?
Prices below are listed US dollars per million input or output tokens, before request-specific context tiers and other billing dimensions. The frontier count comes from the global balanced view. Neither a family price range nor a benchmark difference proves your task will be cheaper or more successful.
How current are the official notes?
The linked family research was reviewed 2026-09-22. That date is separate from each accepted catalogue observation and each vendor’s effective date. An official note applies to its named platform, not automatically to every reseller.