GPT-4o

Tool callingStructured outputImage inputFile input

Launch post Website Docs

Omni-era GPT for multimodal chat, practical coding, and general assistants

Context: 128K
Released: —
Input / 1M tokens: $2.50
Output / 1M tokens: $10.00
Cached input / 1M tokens: $1.25

Sources:models.devOpenRouter

Benchmarks

DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.

Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.

No benchmark results have been matched to this model yet.

Specifications

Developer: OpenAI
Model family: GPT
Type: Language model
Predecessor: —
Successor: —
Released: —
Model ID: openai/gpt-4o
Openness: Closed
License: —
Input modalities: text, image, file
Output modalities: text
Modality: text+image+file->text
Tokenizer: GPT
Max output tokens: 16K
Knowledge cutoff: 2023-09
Hugging Face: —
Source freshness: Metadata synced Oct 8, 2026, 10:17 PM UTC

Additional source evidence

Source model: openai/gpt-4o
Source family: gpt
Last updated: 2024-08-06
Knowledge cutoff: 2023-09
Model context: 128K
Model output limit: 16K
Open weights: No
File attachments: Yes
Reasoning: No
Tool calling: Yes
Structured output: Yes
Temperature control: Yes

Published benchmarks

Benchmark	Score	Evaluation details	Evidence
Aider Polyglot	23.1 · percent correct	2024-12-30	Source

Complete source record (JSON)

{
  "id": "openai/gpt-4o",
  "name": "GPT-4o",
  "description": "Omni-era GPT for multimodal chat, practical coding, and general assistants",
  "family": "gpt",
  "last_updated": "2024-08-06",
  "knowledge": "2023-09",
  "attachment": true,
  "reasoning": false,
  "tool_call": true,
  "structured_output": true,
  "temperature": true,
  "modalities": {
    "input": [
      "text",
      "image",
      "pdf"
    ],
    "output": [
      "text"
    ]
  },
  "limit": {
    "context": 128000,
    "output": 16384
  },
  "benchmarks": [
    {
      "name": "Aider Polyglot",
      "score": 23.1,
      "source": "https://aider.chat/docs/leaderboards/",
      "metric": "percent correct",
      "date": "2024-12-30"
    }
  ],
  "release_date": "2024-05-13",
  "open_weights": false
}

Infrastructure

Provider availability

All providers

Provider	Endpoint	Context	Input /M tokens	Output /M tokens	Cached input /M tokens	Cache write /M tokens	Uptime 1d	Data handling
Azure	azure	128K	$2.50	$10.00	—	—	100.00%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Azure	azureBatch pricing	128K	$2.50	$10.00	—	—	100.00%	ZDR: No Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
OpenAI	openai	128K	$2.50	$10.00	$1.25	—	100.00%	ZDR: No Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
OpenAI	openaiBatch pricing	128K	$2.50	$10.00	$1.25	—	100.00%	ZDR: No Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15

Provider data:OpenRouter

Text provenance

EU · product-scoped

OpenAI textGrain watermarking

In the EU, ChatGPT-generated text uses textGrain. OpenAI says API customers can opt in globally for select models, so watermarking depends on the product surface and configuration.

Official explanation