LLM Reference

GPT-4o

Released
2024-05-13
Last refreshed
2026-06-29
Status
Researched 57d ago
ProprietaryCommercial use: conditionalMultimodalCodingRAGAgentsLong contextVisionJSON / Tool use

GPT-4o is worth evaluating for coding, rag, and agents when its provider route and context window match the workload.

Use it for

  • Teams evaluating coding, rag, and agents
  • Workloads that can use a 128k context window
  • Buyers comparing 4 tracked provider routes

Do not use it for

  • Workloads where another current model has stronger sourced task evidence
Specifications
Family
GPT-4o
Released
2024-05-13
Context
128k
Max output
16,384
Architecture
Decoder Only
Knowledge cutoff
2023-10
Specialization
general
Openness
Proprietary
License
ProprietaryCommercial use: conditional
Weights
Not released
Code
Unknown
Training
Pretrained
Created by

Cutting-edge research and development.

San Francisco, California, United States
Founded 2015
Website
Pricing
Output / 1M
$10.00
Input / 1M
$2.50

Cheapest of 5 routes · OpenAI API · cache read $1.25

About

OpenAI GPT-4o: Flagship multimodal model with vision, function calling, and broad capability. $2.50/M input, $10/M output.

GPT-4o is a proprietary model. The structured metadata tracks a 128k-token context window, multimodal input, function calling, tool use, structured outputs, and code execution. This page tracks provider routes through Replicate API, OpenRouter, Azure OpenAI, and 2 more, with the cheapest tracked route listed at $2.5 input and $10 output per 1M tokens. Headline tracked benchmarks include Chatbot Arena 1315.0, Google-Proof Q&A 50.6, and Massive Multi-discipline Multimodal Understanding 69.1.

Top use-case fit: coding, agents, and build tasks

Coding

Included by capability and metadata signals in the decision map.

RAG

Included by capability and metadata signals in the decision map.

Agents

Included by capability and metadata signals in the decision map.

Provider price ladder

Compare all 5

Compare API pricing across 4 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MCacheRoute
OpenAI API$2.50$10.00read $1.25
Serverless
OpenRouter$2.50$10.00-
Serverless
Replicate API$2.50$10.00-
Serverless
Vercel AI Gateway$2.50$10.00read $1.25
Serverless

Available via routers & gateways(16)

Capabilities

VisionMultimodalFunction CallingTool UseStructured OutputsCode ExecutionPrompt CachingBatch APIFine-tuning

Benchmark peer barsfor Vision

Benchmark scores(4)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionSource
Chatbot Arena1315.0https://lmarena.ai
Google-Proof Q&A50.6diamondhttps://openai.com/index/learning-to-reason-with-llms/
Massive Multi-discipline Multimodal Understanding69.1https://mmmu-benchmark.github.io/
MMMU Pro64.7standard 4-option (original paper harness), 0513 checkpointhttps://arxiv.org/html/2409.02813v3

Migration checks

No linked migration route is available for this model yet.

Compare GPT-4o with other models

Frequently asked questions

What is the context window of GPT-4o?

GPT-4o has a context window of 128k tokens.

What is the max output of GPT-4o?

GPT-4o can generate up to 16,384 output tokens.

How much does GPT-4o cost?

GPT-4o is available at $2.5/1M input tokens through Replicate API.

When was GPT-4o released?

GPT-4o was released on 2024-05-13.

Which providers offer GPT-4o?

GPT-4o is available from 5 providers: Replicate API, OpenRouter, Azure OpenAI, OpenAI API, Vercel AI Gateway.

What benchmarks has GPT-4o been tested on?

GPT-4o has been evaluated on 4 benchmarks, including Chatbot Arena, Google-Proof Q&A, Massive Multi-discipline Multimodal Understanding, MMMU Pro.