One agent session
1M input tokens and 100K output tokens, no caching.
- Input1M x $30 = $30.00
- Output0.1M x $60 = $6.00
$36.00per session
OpenAI - Closed weights
GPT-4 pricing and specs
GPT-4 is a closed-weights model from OpenAI that costs $30 per 1M input tokens and $60 per 1M output tokens on the first-party API, with a 8K-token context window.
Last verified from developers.openai.com. All sources
- Input / 1M
- $30
- Output / 1M
- $60
- Context
- 8K tokens
- Weights
- Closed
Pricing per 1M tokens
| Item | Price / 1M tokens |
|---|---|
| Input | $30 |
| Output | $60 |
| Batch inputBatch requests | $15 |
| Batch outputBatch requests | $30 |
Note: Legacy model, priced on the pricing page as gpt-4-0613 (the default snapshot). Text only. release date blank: the API changelog has no launch entry for GPT-4. Not found in the Vercel AI Gateway model list.
Specs
- Context window
- 8,192 tokens
- Max output
- 8,192 tokens
- Provider
- OpenAI
- API model id
gpt-4- Weights
- Closed weights
What GPT-4 costs in practice
Worked from the standard list rates above, with the math shown so you can swap in your own token counts.
A chat app
10,000 requests a day at 2K input and 500 output tokens each.
- Input20M x $30 = $600.00
- Output5M x $60 = $300.00
$900.00per day
$27,000.00 per 30-day month
Compare with
| Model | Input / 1M | Output / 1M |
|---|---|---|
| GPT-4 (this page) | $30 | $60 |
| o1OpenAI | $15 | $60 |
| Claude Fable 5Anthropic | $10 | $50 |
| Claude Fable 5.1Anthropic | $10 | $50 |
| Claude Mythos 5Anthropic | $10 | $50 |
| GPT-6 AstraOpenAI | $10 | $50 |
| GPT-5.6 CyberOpenAI | $12.50 | $75 |
| o3-proOpenAI | $20 | $80 |
| Chat LatestOpenAI | $5 | $30 |
| GPT-4 TurboOpenAI | $10 | $30 |
Related reading
- Codex CLI 0.163: Instant Steering Is Now the DefaultCodex CLI 0.163.0 makes mid-response steering the default and adds searchable /config and a leader key. What changed and what to check before upgrading.
- Tool Calling Under the Hood: Claude Messages vs OpenAI ResponsesHow tool calling works on the wire: JSON schema tools, parallel calls, tool_choice, strict mode and streaming deltas in Claude Messages vs OpenAI Responses.
- Codex 'gpt-5.5 Model Is Not Supported' Error: The FixCodex says gpt-5.5 is not supported with a ChatGPT account because OpenAI retired it from ChatGPT sign-in on October 14. The fix and what still works.
- Codex CLI Background Daemon: How to Turn It OffCodex CLI starts a persistent, self-updating background daemon since 0.157.0. What it does, why it hit Hacker News and the reported workaround to turn it off.
- Codex CLI 0.162: Managed Worktrees and Pinned TasksCodex CLI 0.162 lets the agent create and list its own Git worktrees, adds pinned tasks and custom provider capability overrides. What to change this week.
- ChatGPT Free vs Go vs Plus After GPT-6: Which Model You GetFree and Go ($8) both get GPT-6 Luna in Chat. Plus ($20) is the cheapest plan with GPT-6 Sol and full Codex. What each ChatGPT plan buys now.
FAQ
How much does GPT-4 cost per million tokens?
GPT-4 costs $30 per 1M input tokens and $60 per 1M output tokens on OpenAI's first-party API, per developers.openai.com on October 17, 2026. Per 1M tokens, the batch rate is $15 input and $30 output.
What is GPT-4's context window?
GPT-4 has a 8,192-token context window and returns up to 8,192 output tokens per response.
Are GPT-4's weights open?
No. GPT-4 is a closed-weights model. You call it through OpenAI's API as gpt-4.
Sources
Last verified from developers.openai.com.
Newsletter
Get model price changes as they ship
One email per week. New model releases, price cuts and what they mean for your bill.