openai
GPT-4 vs GPT-6 Astra
82.2 overall · $20.00 / 1M
// openai
GPT-4
openai/gpt-4
tool calling
GPT-4 costs $30.00 per 1M input tokens and $60.00 per 1M output tokens with a 8K-token context window.
A tool-calling model from openai, released May 28, 2023. LiveBench hasn't published a run for it, so this page carries measured price and specs only — no benchmark numbers.
- Input / 1M
- $30.00
- Output / 1M
- $60.00
- Context
- 8K
- LiveBench overall
- Not evaluated
Specs and pricing
| Input price USD per 1M prompt tokens | $30.00 |
|---|---|
| Output price USD per 1M completion tokens, reasoning included | $60.00 |
| Blended price 3:1 input:output — #6 most expensive of 343 listed models | $37.50 |
| Cached input read Blank means not priced separately — not free | — |
| Cache write | — |
| Context window | 8,191 tokens |
| Max output | 4,096 tokens |
| Input modalities | text |
| Tool calling | Yes |
| Extended reasoning | No |
| Knowledge cutoff | 2021-09-30 |
| Listed | May 28, 2023 |
What GPT-4 costs to run
Monthly list cost across five workload shapes, using the published cached-input rate where there is one. A floor, not a quote — batch discounts and cache writes aren't included.
| Workload | Per month |
|---|---|
| Support chatbot 1.2K in / 400 out × 200K requests | $12,000/mo |
| RAG assistant 8K in / 600 out × 100K requests | $27,600/mo |
| Coding agent 40K in / 4K out × 20K requests | $28,800/mo |
| Document extraction 20K in / 1.5K out × 50K requests | $34,500/mo |
| Bulk classification 500 in / 20 out × 5M requests | $81,000/mo |
Compare GPT-4 with
Benchmarked models at a similar price.
GPT-4 FAQ
How much does GPT-4 cost?
GPT-4 lists at $30.00 per 1M input tokens and $60.00 per 1M output tokens. A RAG assistant handling 100K requests a month (8K tokens in, 600 out) comes to about $27,600 at list price.
What is the context window of GPT-4?
GPT-4 accepts up to 8,191 tokens of context and can return up to 4,096 output tokens per response.
Does GPT-4 support tool calling?
Yes — GPT-4 supports tool (function) calling. It accepts text input.
How does GPT-4 score on benchmarks?
LiveBench has not published a run for GPT-4 yet. Until it does, compare it on price and specs, or run your own evaluation on your own tasks.
What is the API model ID for GPT-4?
On OpenRouter the model ID is "openai/gpt-4". It was listed on May 28, 2023.
More from openai
How these numbers are produced
- Price and specs — provider list data from OpenRouter, refreshed every 15 minutes. “Blended” is a 3:1 input:output mix.
- Scores and ranks — LiveBench release 2026-06-25. Ranks count only models that have a published run; a blank means “not evaluated”, never “bad”.
- Cost per point — the measured dollars LiveBench spent on the run, divided by the score it earned.
Published benchmarks rank models on someone else's tasks. Before committing, see LLM & agent evaluation for building an eval on your own.