GPT-4 Turbo API pricing
Standard tier, blended at 3:1 input to output: $15.00 per million tokens.
OpenAI charges $10.00 per million input tokens and $30.00 per million output tokens for GPT-4 Turbo. It is sold in 4 forms, from $7.50 to $15.00 blended; the table below shows what each costs against standard. 8 of the models nearest it in price are cheaper on a blended basis.
Every tier of GPT-4 Turbo
Blended at 3:1 input to output. The last column compares each against the standard tier.
| Source | ||||||||
|---|---|---|---|---|---|---|---|---|
| Standard Standard | gpt-4-turbo | OpenAI | $10.00 | $30.00 | Not listed | $15.00 | Standard | ↗ |
| Standard | gpt-4-turbo | OpenRouter | $10.00 | $30.00 | Not listed | $15.00 | Same | ↗ |
| Dated snapshot | gpt-4-turbo-2024-04-09 | OpenAI | $10.00 | $30.00 | Not listed | $15.00 | Same | ↗ |
| Batch | gpt-4-turbo:batch | OpenRouter | $5.00 | $15.00 | Not listed | $7.50 | −50% | ↗ |
Prices last checked: . Methodology
Which tier to use
What each costs against standard in our data, and the job it is for.
Batch
The batch tier (gpt-4-turbo:batch) is 50% cheaper than standard. Batch requests are queued and answered asynchronously, typically within 24 hours, so it suits work nobody is waiting on: evaluations, back-fills, bulk classification and tagging. Anything a user is waiting on belongs on the standard tier.
Dated snapshots
One dated snapshot (gpt-4-turbo-2024-04-09) is listed at the same price as standard. A snapshot pins the model to one release, while the undated name moves to newer releases when the vendor updates it. Pin a snapshot in production when your prompts depend on exact output; use the undated name to pick up improvements automatically.
Direct or through a reseller
Through OpenRouter, gpt-4-turbo is the same price as buying direct. A reseller is worth it for one bill across vendors and automatic fallback; buy direct for the vendor's own batch, caching and rate-limit terms.
Against the models nearest in price
Standard tiers, blended at a 3:1 input to output ratio.
| Source | ||||||
|---|---|---|---|---|---|---|
| GPT-4 Turbo This model | OpenAI | $10.00 | $30.00 | 128,000 | $15.00 | ↗ |
| GPT-5.5 | OpenAI | $5.00 | $30.00 | 1,050,000 | $11.25 | ↗ |
| Claude Opus 4.5 | Anthropic | $5.00 | $25.00 | 200,000 | $10.00 | ↗ |
| Claude Opus 4.6 | Anthropic | $5.00 | $25.00 | 1,000,000 | $10.00 | ↗ |
| Claude Opus 4.7 | Anthropic | $5.00 | $25.00 | 1,000,000 | $10.00 | ↗ |
| Claude Opus 4.8 | Anthropic | $5.00 | $25.00 | 1,000,000 | $10.00 | ↗ |
| Claude Opus 5 | Anthropic | $5.00 | $25.00 | 1,000,000 | $10.00 | ↗ |
| Claude Opus 5.5 | Anthropic | $4.00 | $20.00 | 1,000,000 | $8.00 | ↗ |
| GPT-5.6 Sol | OpenAI | $4.00 | $20.00 | 922,000 | $8.00 | ↗ |
Prices last checked: . Methodology
Questions
How much does GPT-4 Turbo cost per million tokens?
$10.00 per million input tokens and $30.00 per million output tokens. At a 3:1 input to output mix that blends to $15.00. Checked 28 Oct 2026.
How much cheaper is GPT-4 Turbo through the Batch API?
gpt-4-turbo:batch costs $5.00 in and $15.00 out per million tokens, 50% cheaper than standard, in exchange for asynchronous delivery.
What would GPT-4 Turbo cost for a real workload?
A thousand requests a day at 2,000 input and 600 output tokens each comes to $1,140.00 a month on the standard tier, or $570.00 through batch.
What is the context window for GPT-4 Turbo?
128,000 tokens of input, with up to 4,096 tokens of output.
GPT-5.5 · Claude Opus 4.5 · Claude Opus 4.6 · Claude Opus 4.7 · Claude Opus 4.8 · All OpenAI models · Cost calculator