OpenRouter
GPT-5.4 Mini (OpenRouter) token cost
OpenAI GPT-5.4 Mini routed on OpenRouter — compare with first-party OpenAI rates.
Published list rates
Input
$0.75
per 1M tokens
Output
$4.50
per 1M tokens
Cached input
$0.075
per 1M tokens
Context window
400,000
tokens
Pricing source: OpenRouter model pricing
Estimate cost
Estimate from text
Calculate from a token total
Project monthly volume
Daily requests × tokens per request × 30 days.
Estimated cost
- Estimated tokens
- —
- Characters
- —
- Words
- —
- Input tokens
- —
- Output tokens
- —
- Input cost
- —
- Output cost
- —
- Total cost
- —
- Combined price per 1M tokens
- —
- Estimated monthly cost
- —
- Estimated daily cost
- —
Cost as volume grows
GPT-5.4 Mini (OpenRouter) at rising volume: prompt-only, reply-only, and a mixed chat (70% in, 30% out).
| Tokens | Input only | Output only | Mix (70% in / 30% out) |
|---|---|---|---|
| 1 | $0.00000075 | $0.000005 | $0.000002 |
| 10 | $0.000008 | $0.000045 | $0.000019 |
| 100 | $0.000075 | $0.00045 | $0.000188 |
| 200 | $0.00015 | $0.0009 | $0.000375 |
| 300 | $0.000225 | $0.00135 | $0.000563 |
| 400 | $0.0003 | $0.0018 | $0.00075 |
| 500 | $0.000375 | $0.00225 | $0.000938 |
| 1,000 | $0.00075 | $0.0045 | $0.001875 |
| 2,000 | $0.0015 | $0.009 | $0.00375 |
| 5,000 | $0.00375 | $0.0225 | $0.009375 |
| 10,000 | $0.0075 | $0.045 | $0.01875 |
| 25,000 | $0.01875 | $0.1125 | $0.04688 |
| 50,000 | $0.0375 | $0.225 | $0.09375 |
| 100,000 | $0.075 | $0.45 | $0.1875 |
| 250,000 | $0.1875 | $1.125 | $0.46875 |
| 500,000 | $0.375 | $2.25 | $0.9375 |
| 1,000,000 | $0.75 | $4.50 | $1.875 |
| 5,000,000 | $3.75 | $22.50 | $9.375 |
| 10,000,000 | $7.50 | $45.00 | $18.75 |
| 50,000,000 | $37.50 | $225.00 | $93.75 |
| 100,000,000 | $75.00 | $450.00 | $187.50 |
| 500,000,000 | $375.00 | $2,250.00 | $937.50 |
| 1,000,000,000 | $750.00 | $4,500.00 | $1,875.00 |
| 10,000,000,000 | $7,500.00 | $45,000.00 | $18,750.00 |
| 100,000,000,000 | $75,000.00 | $450,000.00 | $187,500.00 |
Tokens for a fixed budget
Tokens GPT-5.4 Mini (OpenRouter) can process for a set budget — send-only, reply-only, and a 70/30 mix.
| Budget | Input tokens | Output tokens | Mixed tokens (70/30) |
|---|---|---|---|
| $0.01 | 13,333 | 2,222 | 5,333 |
| $0.1 | 133,333 | 22,222 | 53,333 |
| $0.5 | 666,667 | 111,111 | 266,667 |
| $1.00 | 1.33M | 222,222 | 533,333 |
| $5.00 | 6.67M | 1.11M | 2.67M |
| $10.00 | 13.3M | 2.22M | 5.33M |
| $20.00 | 26.7M | 4.44M | 10.7M |
| $25.00 | 33.3M | 5.56M | 13.3M |
| $30.00 | 40M | 6.67M | 16M |
| $50.00 | 66.7M | 11.1M | 26.7M |
| $100.00 | 133.3M | 22.2M | 53.3M |
| $250.00 | 333.3M | 55.6M | 133.3M |
| $500.00 | 666.7M | 111.1M | 266.7M |
| $1,000.00 | 1.33B | 222.2M | 533.3M |
| $5,000.00 | 6.67B | 1.11B | 2.67B |
| $10,000.00 | 13.3B | 2.22B | 5.33B |
At these rates
- A workload with 70% input and 30% output costs $1.875 per 1 million total tokens and $187.50 per 100 million.
- At the same token count, output costs 6 times the input rate. Response length therefore deserves its own budget limit.
- Filling the 400,000-token context window with input alone would cost about $0.3, before any output.
- Cached input is $0.075 per million, 90% below standard input when the workload meets the provider’s cache rules.
OpenRouter prices reflect the top provider route and can change with routing. Confirm the live model page before budgeting.
These figures use public list prices. Cache eligibility, batch or priority modes, long-context surcharges, discounts, and regional billing can change the invoice.