OpenAI · language model
GPT-4 Turbo: pricing, context and benchmarks
GPT-4 Turbo is OpenAI's model released on April 9, 2024. It costs $10 per million input tokens and $30 per million output tokens, with a 128K-token context window. No independent score has been published for it so far.
What you need to know about GPT-4 Turbo
OpenAI, based in United States, put GPT-4 Turbo online on April 9, 2024. It accepts text and images as input and produces text. Its context window reaches 128,000 tokens, larger than 19 % of the models in the registry, and it can write up to 4,096 tokens in one go.
Released more than 2 years ago, it belongs to a generation most vendors have since superseded.
GPT-4 Turbo pricing
On OpenRouter, GPT-4 Turbo costs $10 per million input tokens and $30 per million output tokens. Counting three tokens read for every token written, its average price is $15 per million, more expensive than 96 % of paid models (19.7 times the median of $0.76).
A concrete example: a task that sends 2,000 tokens (about 1,500 words) and receives a 500-token answer costs $0.035. At 1,000 tasks a day, budget $1,050 a month. The price calculator redoes this with your own volumes.
With batch processing (delayed answers), the price drops to $5 input and $15 output.
Performance and benchmarks
Epoch AI does not yet publish a capabilities index for GPT-4 Turbo. We therefore show no made-up performance rating: only price, context and features count towards its score.
Scores published by Epoch AI on the benchmarks the site tracks:
| Benchmark | What it measures | Score | Date |
|---|---|---|---|
| GPQA Diamond | PhD-level science questions | 46.6 % | Apr 9, 2024 |
| FrontierMath | research-level maths problems (tiers 1-3) | 0.7 % | Apr 9, 2024 |
| OTIS Mock AIME | maths competition problems | 6.7 % | Apr 9, 2024 |
Features, privacy and local use
- It supports tool calling, so it can drive an AI agent, call APIs or MCP servers.
- It can answer in an enforced JSON format (structured outputs).
- Its knowledge stops at December 2023.
Its weights are not published: it can only be used through the OpenAI API or a broker such as OpenRouter, which means sending your data off your machines.
Other OpenAI models
| Model | Released | Avg. price | ECI |
|---|---|---|---|
| GPT-6.1 Sol | Sep 29, 2026 | $4 | 168.4 |
| GPT-6.1 Sol Pro | Sep 29, 2026 | $4 | — |
| GPT-6 Sol | Sep 22, 2026 | $4 | 163.7 |
| GPT-6 Luna | Sep 22, 2026 | $0.2 | 156.8 |
| GPT-6 Luna Pro | Sep 22, 2026 | $0.2 | — |
| GPT-6 Sol Pro | Sep 22, 2026 | $4 | — |
| GPT-6 Astra | Sep 4, 2026 | $20 | 168.8 |
| GPT-6 Astra Pro | Sep 4, 2026 | $20 | — |
Verdict
Computed score: 20/100, from public data (performance, price, context, features).
Strengths
- Agent-ready: tool calling and structured JSON output.
- Discounted batch pricing.
Limitations
- Expensive: costlier than 96 % of paid models.
- No independent score published: performance cannot be verified.
- Older generation, often replaced by a newer model from the same vendor.
Avoid if…
- you process large volumes on a tight budget;
- your data must not leave your servers.
Alternatives
Comparisons and tools
Learn more
Frequently asked questions
How much does GPT-4 Turbo cost?
$10 per million input tokens and $30 per million output tokens on OpenRouter (checked October 25, 2026). A task with 2,000 tokens read and 500 written costs $0.035.
How big is GPT-4 Turbo's context window?
128,000 tokens, roughly 96,000 words, with a maximum of 4,096 output tokens.
Can GPT-4 Turbo run locally?
No, OpenAI does not publish its weights: it is API-only.
Is GPT-4 Turbo suitable for an AI agent?
Technically yes: it supports tool calling and structured outputs. Then check its cost for your volume.
What are the alternatives to GPT-4 Turbo?
The closest models on price and performance are Claude Opus 4.5, Command R+ (08-2024), and Claude Opus 4.1.
Related articles
- Mistral AI: models, pricing and agentsOctober 25, 2026
- LLM benchmarks: how to read model rankingsOctober 24, 2026
- Running a local LLM: hardware, software, and limitationsOctober 24, 2026
- Open-source or closed models for your AI agents?October 5, 2026
Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score