ARCHIVE PRICEDEPRECATED MODEL128KTEXT + VISIONPROMPT CACHING
GPT-4o API Pricing
GPT-4o is deprecated in the API but still a high-demand pricing archive. $5/M input, $15/M output, and $2.5/M cached input. Use this page for historical GPT-4o bills and migration checks toward GPT-5.5.
Archived input - per 1M tokens
$5.00/M
Source OpenAI deprecated
Archived output - per 1M tokens
$15.00/M
Use for invoice checks deprecated
Cached input
$2.50/M
Cache hit price discounted
Effective - agentic blend
$3.91/M
92/8 split - 82% cache
§ 01 / TERMINAL
Run the numbers.
Archive calculator pre-loaded with GPT-4o rates. Tweak spend, output mix, or cache hit rate to compare legacy bills with current replacements.
$ /mo
Workload split
Prompt cache hit rate
Tokens you can process
—
Words equivalent (English)
—
Effective rate
—
§ 02 / SCENARIOS
Real-world presets.
CODING AGENT ARCHIVE
Repo-wide bug fix
$0.344/task
LONG DOC ANALYSIS
Reading 100-page contracts
$0.636/doc
RAG SUPPORT
Support agent ticket triage
$0.027/ticket
ASSISTANT TURN
Research planning turn
$0.065/turn
§ 03 / TAPE
Price history.
Input · $5/M
Output · $15/M
Cached · $2.5/M
MAY 13 Launch-era API price at $5/M input and $15/M outputMAY 18 Deprecated; shutdown listed for October 23, 2026 with GPT-5.5 as replacement
§ 04 / TOKENIZER
Paste text. See tokens. See cost.
Estimate · tiktoken-cl100k_base · ≈4 chars/token Auto-counts as you type
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.
Characters —
Words —
Tokens (estimated) —
Cost as input · uncached —
Cost as output · uncached —
Cost as cached input —
| Model | Input /M | Output /M | Effective blended | Context | Best for |
|---|---|---|---|---|---|
| GPT-4o | $5.00 cache $2.50 | $15.00 | $3.91 current page | 128K | Legacy multimodal OpenAI apps |
| GPT-5.5 | $5.00 cache $0.50 | $30.00 | $3.60 cheaper | 1M | Current replacement workloads |
| GPT-5.4 | $2.50 cache $0.25 | $15.00 | $1.80 cheaper | 1.05M | Current replacement workloads |
| GPT-5.4 mini | $0.75 cache $0.07 | $4.50 | $0.54 cheaper | 400K | Current replacement workloads |
| Claude Sonnet 4.6 | $3.00 cache $0.30 | $15.00 | $1.92 cheaper | 1M | Legacy Claude production baselines |
| Gemini 2.5 Pro | $1.25 cache $0.13 | $10.00 | $1.10 cheaper | 2M | Gemini long-context work |
| DeepSeek V4 Pro | $0.43 cache $0.00 | $0.87 | $0.14 cheaper | 1M | Low-cost reasoning and coding |
Frequently asked.
Short answers for teams checking GPT-4o pricing, status, and migration choices.
Q · 01 Is GPT-4o still available? +
It is deprecated. Use this archive for old workloads and migrate before the listed shutdown date.
Q · 02 How much did GPT-4o cost? +
GPT-4o is listed here at $5/M input and $15/M output.
Q · 03 Is cached-input pricing included? +
Yes. Cached input is shown at $2.5/M.
Q · 04 What should teams use instead? +
For new work, compare against
gpt-5-5 and other current rows in the shelf.Q · 05 Why keep this archive page? +
Archive pages preserve old price baselines, help explain invoice history, and capture migration search demand without implying the model is the best current choice.