GPT-4
openai The API that serves this model and sets the prices shown here. gpt-4 The model identifier to send in API requests. LLM Generates text from a prompt, so it can be compared with other LLMs on price and capability. Large The most capable general-purpose tier of a model family. Retired Oct 23, 2026 This model has been retired and can no longer be relied on.Provider: openai
Knowledge cutoff: November 2023
Model deprecated and scheduled for shutdown on October 23, 2026. Substitute: gpt-5.6-sol. Source: https://platform.openai.com/docs/deprecations
Sticker prices & cost-per-token
List rates as published by openai, before any volume or enterprise discounts.
$30.00
$60.00
8,192 tokens
8,192
tokens per response (includes reasoning tokens)
Closed weights
Get this data free
Want to stay updated on price changes on this model? Pull this data free (no API key required) here:
curl "https://coolhandlabs.com/api/v2/inference_apis?q%5Bmodel_eq%5D=gpt-4&q%5Bsource_api_eq%5D=openai"Pricing History
| Effective | Price |
|---|---|
| Aug 16, 2026 – present | Input cost: $30.00 / 1M, Output cost: $60.00 / 1M, Cached input cost: $0.00 / 1M, Cache creation cost: $0.00 / 1M, 5-minute cache write cost: $0.00 / 1M, 1-hour cache write cost: $0.00 / 1M, Reasoning output cost: $0.00 / 1M, Cache storage cost: $0.00 / 1M/hr |
History
Last change detected September 7, 2026 (about 2 months ago) by an automated scan.
| Date | Changed by | What changed |
|---|---|---|
| Aug 16, 2026 | Unknown | Initial record created |
Source
https://models.dev/api.json (models.dev provider 'openai', bulk import 2026-08-13)Comparable models
No comparable models identified yet.
Reliability
No reliability incidents recorded in the last 90 days.
Frequently asked questions
GPT-4 (openai) costs $30.00 per 1M input tokens and $60.00 per 1M output tokens, as last published by openai.
GPT-4 has a context window of 8,192 tokens (the maximum combined input and output it can handle in a single request).
GPT-4 sits in the large size tier. Size tiers run from micro (small enough to run on a device) through small, medium and large to extra large (frontier flagships), and are assigned from the model's family, naming and limits rather than its price.
GPT-4 can generate up to 8,192 tokens in a single response. Reasoning (thinking) tokens count toward this limit.
GPT-4's training data runs through November 2023, so it may not know about later events. Coolhand records the cutoff at month precision, since providers often publish only the month.
GPT-4 accepts text as input and produces text as output, as recorded in the Coolhand catalog.
No — the weights of GPT-4 have not been released, so it is only available through hosted APIs.
Yes — openai deprecated GPT-4 on October 23, 2026. Model deprecated and scheduled for shutdown on October 23, 2026. Substitute: gpt-5.6-sol. Source: https://platform.openai.com/docs/deprecations
openai retired GPT-4 on October 23, 2026.
Since GPT-4 is deprecated, openai customers are moving to GPT-4, GPT-Image-2, and o1 Mini.
Call GET https://coolhandlabs.com/api/v2/inference_apis?q[source_api_eq]=openai&q[model_eq]=gpt-4 — free, no API key required, and scoped to just this model since source_api and model together are unique. See https://coolhandlabs.com/docs for the full REST API reference.
Coolhand also tracks GPT-3.5 Turbo 0125, GPT-3.5 Turbo 1106, GPT-3.5 Turbo Instruct, GPT-4 Turbo Vision, GPT-4, and GPT-Image-2 from openai. Some may already be deprecated, so check each model's status alongside its current pricing.
| Model | Input cost | Output cost | Context window | Max output tokens | Status |
|---|---|---|---|---|---|
| GPT-3.5 Turbo 0125 via Azure | $0.50/1M $0.0000005000 | $1.50/1M $0.0000015000 | 16,384 | 16,384 |
Deprecated Aug 13, 2026
|
| GPT-3.5 Turbo 1106 via Azure | $1.00/1M $0.0000010000 | $2.00/1M $0.0000020000 | 16,384 | 16,384 |
Deprecated Aug 13, 2026
|
| GPT-3.5 Turbo Instruct via Azure | $1.50/1M $0.0000015000 | $2.00/1M $0.0000020000 | 4,096 | 4,096 |
Deprecated Aug 13, 2026
|
| GPT-4 Turbo Vision via Azure | $10.00/1M $0.0000100000 | $30.00/1M $0.0000300000 | 128,000 | 4,096 |
Deprecated Aug 13, 2026
|
| GPT-4 via Azure | $30.00/1M $0.0000300000 | $60.00/1M $0.0000600000 | — | — | Active |
| GPT-Image-2 via Azure | $5.00/1M $0.0000050000 | $30.00/1M $0.0000300000 | — | — | Active |
Track LLM pricing and deprecations automatically.
Start free