GPT-4 Turbo
$10.00 per 1M input tokens and $30.00 per 1M output tokens · 128K context · vision, tools, JSON.
Prices checked Oct 21, 2026 · tracked by LLM Cost Index since Oct 21, 2026
Cheaper ways to run the same model: GPT-4 Turbo (batch) at $5.00 / $15.00 — same model, different service (e.g. batch processing with a delay).
What GPT-4 Turbo costs per month
Estimated monthly bill for typical workloads. Try your own numbers in the cost calculator.
| Workload | Per month |
|---|---|
| Customer chatbot 1,000 conversations a day, 8 turns each | $6,120 |
| Document Q&A (RAG) 500 questions a day over retrieved documents | $1,125 |
| Coding / tool-using agent 200 tasks a day, long tool-heavy contexts | $4,320 |
| Content generation 30 long articles a day | $94.50 |
| Classification / extraction 100,000 short items a day | $10,350 |
Price history
We started tracking GPT-4 Turbo on Oct 21, 2026; the chart appears as soon as there is a second data point. See all recent price changes.
Cheaper alternatives to GPT-4 Turbo
Models with the same tool calling, image input, structured output for at least 20% less (3:1 input/output mix), most capable first.
| Model | Input / 1M | Output / 1M | Context | Capabilities |
|---|---|---|---|---|
| Claude Opus 5.5 Anthropic | $4.00 | $20.00 | 1M | visiontoolsreasoningJSON |
| Claude Sonnet 5.5 Anthropic | $2.00 | $10.00 | 1M | visiontoolsreasoningJSON |
| Gemini 4 Argon | $2.00 | $10.00 | 1.05M | visionaudiotoolsreasoningJSON |
| GPT-6.1 Sol OpenAI | $2.00 | $10.00 | 1.05M | visiontoolsreasoningJSON |
| Claude Opus 5 Anthropic | $5.00 | $25.00 | 1M | visiontoolsreasoningJSON |
How to pay less for GPT-4 Turbo
For a customer chatbot (1,000 conversations a day, 8 turns each) that costs $6,120 a month at list price without caching:
| Option | Per month | You save |
|---|---|---|
| Move to Claude Opus 5.5 (similar capabilities) | $2,299 | $3,821 (62%) |
| Switch to GPT-4 Turbo (batch) | $3,060 | $3,060 (50%) |
Other workloads: cut-your-bill tool for GPT-4 Turbo.
Specifications
| Model ID | openai/gpt-4-turbo |
| Input | text, image |
| Output | text |
| Tool calling | Yes |
| Structured output | Yes |
| Reasoning mode | No |
| Open weights | No |
| Knowledge cutoff | 2023-12-31 |
| Released | Apr 9, 2024 |
FAQ
- How much does GPT-4 Turbo cost?
- $10.00 per million input tokens and $30.00 per million output tokens. Prices as of Oct 21, 2026.
- What is the context window of GPT-4 Turbo?
- 128K tokens, with up to 4K output tokens per response.
- Does GPT-4 Turbo support images, tools and structured output?
- Images as input: yes. Tool calling: yes. Structured (JSON) output: yes. Reasoning mode: no.
- What are cheaper alternatives to GPT-4 Turbo?
- Models with the same key capabilities for at least 20% less include Claude Opus 5.5 ($4.00 / $20.00), Claude Sonnet 5.5 ($2.00 / $10.00), Gemini 4 Argon ($2.00 / $10.00).
More from OpenAI: all OpenAI models · how we collect prices