GPT-4
gpt-4
Last refreshed 2026-05-11. Next refresh: weekly.
GPT-4 is a legacy integration reference; evaluate GPT-4.1 before starting new work.
Decision context: Coding task fit, 4 tracked provider routes, and research from 2026-05-10.
Use it for
- Teams maintaining an existing integration
- Workloads that can use a 8K context window
- Buyers comparing 3 tracked provider routes
Do not use it for
- New production launches
Cheapest output
$60.00
OpenAI API per 1M tokens
Provider routes
4
Tracked API hosts
Quality / dollar
Unknown
No task benchmark coverage yet
Freshness
2026-05-10
Researched 16d ago
This API model is marked deprecated. Use GPT-4.1 as the replacement candidate before sending new production traffic.
Top use-case fit
Coding
Included by capability and metadata signals in the decision map.
Agents
Included by capability and metadata signals in the decision map.
Vision
Included by capability and metadata signals in the decision map.
Provider price ladder
Compare all 4| Provider | Input / 1M | Output / 1M | Batch in / out | Route |
|---|---|---|---|---|
| OpenAI API | $30.00 | $60.00 | $15.00 / $30.00 | Serverless |
| OpenRouter | $30.00 | $60.00 | - | Serverless |
| Salesforce Einstein Generative AI | - | - | - | ServerlessPartial |
Benchmark peer barsfor Coding
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.
About
OpenAI's original GPT-4 model with strong reasoning and general knowledge. Foundation model for many applications.
GPT-4 has a 8K-token context window.
GPT-4 input tokens at $30/1M, output at $60/1M.
Capabilities
Benchmark Scores(1)
| Benchmark | Score | Version | Source |
|---|---|---|---|
| GAOKAO | 72.2 | zero-shot, objective-accuracy | https://github.com/OpenLMLab/GAOKAO-Bench |
API Versions
gpt-4-0314gpt-4-0613gpt-4