ARCHIVE PRICELEGACY MODEL1MTEXT + VISIONPROMPT CACHING
GPT-4.1 API Pricing
GPT-4.1 is a legacy long-context OpenAI model at $2/$8 per million tokens. $2/M input, $8/M output, and $0.5/M cached input. It introduced a 1M context window to the GPT-4 family and a 75% cached-input discount.
Archived input - per 1M tokens
$2.00/M
Source OpenAI legacy
Archived output - per 1M tokens
$8.00/M
Use for invoice checks legacy
Cached input
$0.50/M
Cache hit price discounted
Effective - agentic blend
$1.35/M
92/8 split - 82% cache
§ 01 / TERMINAL
Run the numbers.
Archive calculator pre-loaded with GPT-4.1 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
$0.118/task
LONG DOC ANALYSIS
Reading 100-page contracts
$0.199/doc
RAG SUPPORT
Support agent ticket triage
$0.011/ticket
ASSISTANT TURN
Research planning turn
$0.025/turn
§ 03 / TAPE
Price history.
Input · $2/M
Output · $8/M
Cached · $0.50/M
APR 14 Launch at $2/M input, $0.50/M cached input, and $8/M outputMAY 18 Legacy row; recommended replacement is GPT-5.5
§ 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-4.1 | $2.00 cache $0.50 | $8.00 | $1.35 current page | 1M | OpenAI archive comparisons |
| GPT-5.5 | $5.00 cache $0.50 | $30.00 | $3.60 pricier | 1M | Current OpenAI flagship |
| GPT-5.4 | $2.50 cache $0.25 | $15.00 | $1.80 pricier | 1.05M | Current OpenAI daily driver |
| GPT-5.4 mini | $0.75 cache $0.07 | $4.50 | $0.54 cheaper | 400K | Current cheap OpenAI workloads |
| Claude Sonnet 4.6 | $3.00 cache $0.30 | $15.00 | $1.92 pricier | 1M | Current Claude agents |
| 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-4.1 pricing, status, and migration choices.
Q · 01 Is GPT-4.1 still available? +
GPT-4.1 is a legacy model. It is useful for old baselines, but new projects should compare current GPT-5-family rows first.
Q · 02 How much did GPT-4.1 cost? +
GPT-4.1 is archived at $2/M input and $8/M output.
Q · 03 Is cached-input pricing included? +
Yes. Cached input is shown at $0.5/M.
Q · 04 What replaced it? +
The snapshot replacement is
gpt-5-5; use the shelf to compare current options.Q · 05 Why keep this archive page? +
Archive pages preserve old price baselines, help explain invoice history, and capture migration search demand without treating old models as current recommendations.