GPT-4 API Pricing
Retired October 23, 2026: OpenAI shut gpt-4 down on that date, and calls to it now fail; OpenAI names GPT-5.6 Sol as the substitute. This archive preserves the $30/$60 launch-era price ceiling. $30/M input, $60/M output. Use it as the baseline for tracking how far frontier OpenAI API pricing compressed after 2023.
GPT-4 API cost calculator.
Archive calculator pre-loaded with the last GPT-4 rates OpenAI published. Tweak spend, output mix, or cache hit rate to compare legacy bills with current replacements.
GPT-4 cost on real workloads.
Repo-wide bug fix
Reading 100-page contracts
Support agent ticket triage
Research planning turn
This is a chars-per-token approximation, not a real tokenizer. Actual tokens vary by language, code density, and tool-call overhead — counts are typically ±10–20% off for English prose, more for code or non-Latin scripts. For exact billing, use the vendor's official tokenizer.
| Model | Input /M | Output /M | Effective blended | Context | Best for |
|---|---|---|---|---|---|
| GPT-4 Current | $30.00 | $60.00 | $32.40 agentic 92/8 | 8K | OpenAI archive comparisons |
| GPT-5.5 | $5.00 cache $0.50 | $30.00 | $3.61 −9.0× | 1M | Current OpenAI flagship |
| GPT-5.4 | $2.50 cache $0.25 | $15.00 | $1.80 −18× | 1.05M | Current OpenAI daily driver |
| GPT-5.4 mini | $0.75 cache $0.075 | $4.50 | $0.541 −60× | 400K | Current cheap OpenAI workloads |
| Claude Sonnet 5.5 | $2.00 cache $0.10 | $10.00 | $1.29 −25× | 1M | Anthropic's current Sonnet |
| Gemini 3.8 Flash | $0.75 cache $0.075 | $3.75 | $0.481 −67× · promo | 1M | Gemini long-context work |
| DeepSeek V4 Pro | $1.32 cache $0.044 | $3.96 | $0.569 −57× | 1M | Low-cost reasoning and coding |
By replacement
GPT-4 API pricing FAQ.
Short answers for teams checking GPT-4 pricing, status, and migration choices.
Q · 01 Can I still use GPT-4? +
gpt-4 would be shut down on October 23, 2026, and its deprecations page now says access was shut down on that date. The substitute OpenAI names is GPT-5.6 Sol. OpenAI's pricing page still prints this model's rates in its legacy table, but they no longer buy anything; the figures here are the last OpenAI published, kept for old invoices and migration math.