GPT-4 pricing, context window and limits
GPT-4 costs $30 per million input tokens and $60 per million output tokens at OpenAI list price. It accepts up to 8,192 tokens of context and returns up to 8,192 tokens.
- Model id
gpt-4 - Snapshot
What does GPT-4 cost?
| Input | $30 |
|---|---|
| Output | $60 |
| Cached input (read) | — |
| Cache write | — |
US dollars per million tokens. A dash means no price is published.
How much can GPT-4 read and write?
| Context window | 8,192 |
|---|---|
| Max output | 8,192 |
What can GPT-4 do?
| Vision (image input) | No |
|---|---|
| Tool calling | Yes |
| Structured output | No |
| Reasoning | No |
| Input | text |
| Output | text |
What does a request to GPT-4 cost?
| A typical request: 1,000 tokens in, 500 out | $0.06 |
|---|---|
| A long request: 10,000 tokens in, 1,000 out | $0.36 |
| 1,000 typical requests | $60 |
| 1 million tokens in and 1 million out | $90 |
Among 49 OpenAI models with a published price, GPT-4 is the 46th cheapest by input price. Its context window is the 45th largest of 48. List prices only; discounts, batch prices and prices above 200K tokens are not shown.
How do I call GPT-4 through DVARA?
Configure the openai provider in the DVARA LLM Gateway and send the model id gpt-4. DVARA, the AI governance platform, applies your policies, audit and cost attribution to the call. See LLM cost attribution and budgets.
In DVARA, if you haven't set your own price for a model, its calls are costed at the price in the catalogue that ships with your DVARA version. A price you set in Flightdeck always wins. You can switch catalogue prices off. Then a model with no price you set is counted as costing nothing. Every cost record says which price it used.
What should I check before relying on this data?
The weekly review marked this entry. A person saw each mark and kept the model listed.
- This provider bills prompt caching, but no cached-input price is listed.
Which other OpenAI models are there?
- GPT-3.5-turbo$0.5 in · $1.5 out · 16K context
- GPT-4 Turbo$10 in · $30 out · 128K context
- GPT-4.1$2 in · $8 out · 1.05M context
- GPT-4.1 mini$0.4 in · $1.6 out · 1.05M context
- GPT-4.1 nano$0.1 in · $0.4 out · 1.05M context
- GPT-4o$2.5 in · $10 out · 128K context
- GPT-4o (2024-05-13)$5 in · $15 out · 128K context
- GPT-4o (2024-08-06)$2.5 in · $10 out · 128K context
- GPT-4o (2024-11-20)$2.5 in · $10 out · 128K context
- GPT-4o mini$0.15 in · $0.6 out · 128K context
- GPT-5$1.25 in · $10 out · 400K context
- GPT-5 Mini$0.25 in · $2 out · 400K context
Which models from other providers are similar to GPT-4?
These are the closest in context window and input price, one per provider.
- Command A TranslateCohere · $2.5 in · $10 out · 8K context
- Gemini 3.5 Live Translate PreviewGoogle Gemini · $3.5 in · $21 out · 16K context
- Claude Opus 4.1Amazon Bedrock · $15 in · $75 out · 200K context
- Qwen Math PlusAlibaba Qwen · $0.574 in · $1.721 out · 4K context
- Mixtral 8x22BMistral AI · $2 in · $6 out · 64K context