GPT-4o (2024-11-20)

openai/gpt-4o

Maker: OpenAI, United States
Released: 2024-05-13
Knowledge cutoff: 2023-09
Family: gpt
Weights: closed
Tasks: text.chat, vision.understand, vision.extract
Cheapest offering: Azure OpenAI, about $0.0055 for a typical text.chat call

Try it in the sandbox Use it from the API

Offerings

Provider	Model id at the provider	Status	Price per 1M tokens	Per-unit prices	Limits	Capabilities (level)
Azure OpenAI	`gpt-4o`	deprecateddeprecated 2027-04-14	Input: $2.5 Output: $10 Cache read: $1.25 Since 2026-11-03 · models.dev, MIT	none	Context: 128,000 tokens Max output: 16,384 tokens	`input.text` claimed `input.image` claimed `input.pdf` claimed `output.text` claimed `tools` claimed `parallel_tools` claimed `tool_choice` claimed `structured_output` claimed `prompt_caching` claimed
OpenAI	`gpt-4o`	gadeprecated 2027-01-14retires 2027-01-14	Input: $2.5 Output: $10 Cache read: $1.25 Input, priority tier: $4.25 Output, priority tier: $17 Cache read, priority tier: $2.125 Since 2026-11-03 · models.dev, MIT	none	Context: 128,000 tokens Max output: 16,384 tokens	`input.text` claimed `input.image` claimed `input.pdf` claimed `output.text` claimed `tools` claimed `structured_output` claimed `parallel_tools` claimed `tool_choice` claimed `prompt_caching` claimed
OpenAI	`gpt-4o-2024-08-06`	gadeprecated 2027-01-14retires 2027-01-14	Input: $2.5 Output: $10 Cache read: $1.25 Since 2026-11-03 · models.dev, MIT	none	Context: 128,000 tokens Max output: 16,384 tokens	`input.text` claimed `input.image` claimed `input.pdf` claimed `output.text` claimed `tools` claimed `structured_output` claimed `parallel_tools` claimed `tool_choice` claimed `prompt_caching` claimed
OpenAI	`gpt-4o-2024-11-20`	gadeprecated 2027-01-14retires 2027-01-14	Input: $2.5 Output: $10 Cache read: $1.25 Since 2026-11-03 · models.dev, MIT	none	Context: 128,000 tokens Max output: 16,384 tokens	`input.text` claimed `input.image` claimed `input.pdf` claimed `output.text` claimed `tools` claimed `structured_output` claimed `parallel_tools` claimed `tool_choice` claimed `prompt_caching` claimed
OpenRouter	`openai/gpt-4o`	ga	Input: $2.5 Output: $10 Cache read: $1.25 Since 2026-11-03 · models.dev, MIT	none	Context: 128,000 tokens Max output: 16,384 tokens	`input.text` claimed `input.image` claimed `input.pdf` claimed `output.text` claimed `tools` claimed `structured_output` claimed
OpenRouter	`openai/gpt-4o-2024-05-13`	ga	Input: $5 Output: $15 Since 2026-11-03 · models.dev, MIT	none	Context: 128,000 tokens Max output: 4,096 tokens	`input.text` claimed `input.image` claimed `input.pdf` claimed `output.text` claimed `tools` claimed `structured_output` claimed
OpenRouter	`openai/gpt-4o-2024-08-06`	ga	Input: $2.5 Output: $10 Cache read: $1.25 Since 2026-11-03 · models.dev, MIT	none	Context: 128,000 tokens Max output: 16,384 tokens	`input.text` claimed `input.image` claimed `input.pdf` claimed `output.text` claimed `tools` claimed `structured_output` claimed
OpenRouter	`openai/gpt-4o-2024-11-20`	ga	Input: $2.5 Output: $10 Cache read: $1.25 Since 2026-11-03 · models.dev, MIT	none	Context: 128,000 tokens Max output: 16,384 tokens	`input.text` claimed `input.image` claimed `input.pdf` claimed `output.text` claimed `tools` claimed `structured_output` claimed

Quality scores

Basis	Score (0–1)	Raw	Measured	Source
`epoch:gpqa_diamond`	0.510	0.4921	2025-01-27	Epoch AI, CC-BY-4.0, normalized by Nanner Tech
`epoch:swe_bench_verified`	0.371	0.3099	2026-02-11	Epoch AI, CC-BY-4.0, normalized by Nanner Tech
`epoch:aider_polyglot`	0.263	0.2310	2024-12-30	Epoch AI, CC-BY-4.0, normalized by Nanner Tech
`epoch:hle`	0.050	0.0272	2024-11-20	Epoch AI, CC-BY-4.0, normalized by Nanner Tech
`epoch:frontiermath`	0.004	0.0035	2026-08-27	Epoch AI, CC-BY-4.0, normalized by Nanner Tech

Aliases

Other names the API accepts for this model.

gpt-4o
gpt-4o-2024-05-13
gpt-4o-2024-08-06
gpt-4o-2024-11-20
openai/gpt-4o-2024-05-13
openai/gpt-4o-2024-08-06
openai/gpt-4o-2024-11-20

Use it from the API

Look this model up, or ask for the best model for its task on the providers that offer it. See the quickstart and the API reference.

Look up this model

curl 'https://rhumbdata.com/v1/models/openai/gpt-4o' \
  -H "Authorization: Bearer $RHUMB_KEY"

Resolve text.chat on its providers

curl 'https://rhumbdata.com/v1/resolve?task=text.chat&providers=azure-openai,openai,openrouter' \
  -H "Authorization: Bearer $RHUMB_KEY"

Retired

Offerings no longer available; kept for reference.

Provider	Model id at the provider	Status	Price per 1M tokens	Per-unit prices	Limits	Capabilities (level)
OpenAI	`gpt-4o-2024-05-13`	retireddeprecated 2026-10-23retires 2026-10-23	Input: $5 Output: $15 Input, priority tier: $8.75 Output, priority tier: $26.25 Since 2026-11-03 · models.dev, MIT	none	Context: 128,000 tokens Max output: 4,096 tokens	`input.text` claimed `input.image` claimed `input.pdf` claimed `output.text` claimed `tools` claimed `structured_output` claimed `parallel_tools` claimed `tool_choice` claimed `prompt_caching` claimed

Built from catalog version 2026-11-04.3 of 2026-11-04. Prices are list prices per 1M tokens unless marked otherwise; every score shows its source's notice (see Attributions).