Historical model (deprecated). The rates below are the last recorded rates, not a recommendation for a new deployment.
OpenAI shut down this API model on 2026-10-23.
Current price verification is unresolved or overdue. These are the last recorded rates; check the official source before budgeting. We do not relabel an old check with today's build date.
gpt-4o-2024-05-13 API Pricing
OpenAI shut down this API model on 2026-10-23. No directly comparable current token quote is available. These rates were last verified on .
Moving off gpt-4o-2024-05-13?
Same token usage, 3:1 input:output, standard list rates · excludes cache, batch and fast mode. Not a quality or compatibility claim. Full calculator →
OpenAI general text pricing history
USD · units shown per rate- GPT-6 CyberFirst seen 2026-11-10Input: $20.00 / 1M tokensOutput: $100.00 / 1M tokensRate first observedLatestVerified 2026-11-09
- Input: $1.00 / 1M tokensOutput: $5.00 / 1M tokensRate first observedLatestVerified 2026-11-12
- Input: $2.00 / 1M tokensOutput: $10.00 / 1M tokensRate first observedAvailable · older versionVerified 2026-11-12
- Input: $2.00 / 1M tokensOutput: $10.00 / 1M tokensRate first observedAvailable · older versionVerified 2026-11-12
- Input: $10.00 / 1M tokensOutput: $50.00 / 1M tokensRate first observedAvailable · older versionVerified 2026-11-12
- gpt-3.5-turboFirst seen 2026-08-18Input: $0.50 / 1M tokensOutput: $1.50 / 1M tokensRate first observedShut downVerified 2026-11-12
- gpt-3.5-turbo-1106First seen 2026-08-18Input: $1.00 / 1M tokensOutput: $2.00 / 1M tokensRate first observedShut downVerified 2026-10-20
- gpt-3.5-turbo-instructFirst seen 2026-08-18Input: $1.50 / 1M tokensOutput: $2.00 / 1M tokensRate first observedShut downVerified 2026-11-12
- gpt-4-0613First seen 2026-08-18Input: $30.00 / 1M tokensOutput: $60.00 / 1M tokensRate first observedShut downVerified 2026-11-02
- gpt-4-turbo-2024-04-09First seen 2026-08-18Input: $10.00 / 1M tokensOutput: $30.00 / 1M tokensRate first observedShut downVerified 2026-11-02
- gpt-4o-2024-05-13First seen 2026-08-18Input: $5.00 / 1M tokensOutput: $15.00 / 1M tokensRate first observedShut downVerified 2026-11-02
- GPT-5.5 CyberFirst seen 2026-08-11Input: $12.50 / 1M tokensOutput: $75.00 / 1M tokensRate first observedStatus unverifiedVerified 2026-11-09
- GPT-5.6 CyberFirst seen 2026-08-11Input: $12.50 / 1M tokensOutput: $75.00 / 1M tokensRate first observedLatestVerified 2026-11-09
- Input: $4.00 / 1M tokensOutput: $20.00 / 1M tokensRate first observedAvailable · older versionVerified 2026-11-12
1 recorded price changes
- Input: $4.00 / 1M tokens · Output: $20.00 / 1M tokens — observed Aug 22, 2026
- Input: $5.00 / 1M tokens · Output: $30.00 / 1M tokens — observed Jun 28, 2026 (first recorded)
- Input: $2.00 / 1M tokensOutput: $12.00 / 1M tokensRate first observedAvailable · older versionVerified 2026-11-12
1 recorded price changes
- Input: $2.00 / 1M tokens · Output: $12.00 / 1M tokens — observed Jul 31, 2026
- Input: $2.50 / 1M tokens · Output: $15.00 / 1M tokens — observed Jun 28, 2026 (first recorded)
- GPT-5.2 ProFirst seen 2026-05-16Input: $21.00 / 1M tokensOutput: $168.00 / 1M tokensRate first observedLatestVerified 2026-11-12
- Input: $5.00 / 1M tokensOutput: $30.00 / 1M tokensRate first observedAvailable · older versionVerified 2026-11-12
- Input: $30.00 / 1M tokensOutput: $180.00 / 1M tokensRate first observedAvailable · older versionVerified 2026-11-12
- Input: $2.50 / 1M tokensOutput: $15.00 / 1M tokensRate first observedAvailable · older versionVerified 2026-11-12
- Input: $30.00 / 1M tokensOutput: $180.00 / 1M tokensRate first observedAvailable · older versionVerified 2026-11-12
- Input: $1.75 / 1M tokensOutput: $14.00 / 1M tokensRate first observedAvailable · older versionVerified 2026-11-12
- Input: $1.25 / 1M tokensOutput: $10.00 / 1M tokensRate first observedDeprecated · 2027-04-01Verified 2026-11-12
- Input: $15.00 / 1M tokensOutput: $120.00 / 1M tokensRate first observedDeprecated · 2026-12-11Verified 2026-11-12
- Input: $1.25 / 1M tokensOutput: $10.00 / 1M tokensRate first observedDeprecated · 2026-12-11Verified 2026-11-12
- Input: $2.00 / 1M tokensOutput: $8.00 / 1M tokensRate first observedDeprecated · 2027-01-14Verified 2026-11-12
- Input: $2.50 / 1M tokensOutput: $10.00 / 1M tokensRate first observedDeprecated · 2027-01-14Verified 2026-11-12
- Input: $0.50 / 1M tokensOutput: $1.50 / 1M tokensRate first observedShut downVerified 2026-11-02
Newest first. Release dates describe the model, not when today's rates took effect. Observations show when we recorded rates, not launch pricing. Image and text token meters are separate; no fixed image-token savings mix is assumed. How we verify
OpenAI shut down this API model on 2026-10-23.
Published rates and billing units
| Billing dimension | USD list price |
|---|
Verified 2026-11-02 · Official source · Pricing methodology. Taxes, optional services and account-specific discounts are not included.
Cost examples
These examples use published list prices only. They exclude taxes, enterprise discounts, minimum charges, retries, batch discounts, and provider-specific billing rules.
1M input + 1M output
—
A direct per-million comparison against every other text model.
100K input + 25K output
—
A compact chat, summarization, or analysis workload.
10M input + 2M output
—
A monthly production estimate for heavier RAG or agent traffic.
75% cached input + 250K output
Not listed
OpenAI does not publish a cached-input rate for this model in our dataset.
Calculator for gpt-4o-2024-05-13
Enter your own input, output, and cached-token assumptions. This calculator is preloaded with only gpt-4o-2024-05-13, so the result stays focused on this model.
OpenAI shut down this API model on 2026-10-23. Token-only calculation unavailable.
Price history
No list-price movement across 86 daily snapshots from 2026-08-18 to 2026-11-11.
When to use gpt-4o-2024-05-13
Good fit
- OpenAI workloads where this price tier and API surface fit your existing stack
Be careful with
- production launches until the provider restores availability
- decisions that depend on unpublished context-window limits without checking the provider docs first