OpenAI GPT-5.4 Mini API Pricing and Speed
OpenAI GPT-5.4 Mini API pricing: $0.75 per 1M tokens for input and $4.50 per 1M tokens for output, from the official API price list of OpenAI. Official rate checked (source); OpenRouter is a separate channel below. Our measured latency and output speed are shown by route and country below. Published OpenRouter: Last checked · Source (data) · Methodology
OpenRouter: Amount worked out from the source page: $0.75 per 1M tokens, in USD · as shown in the United States on 9 Nov 2026 · the page does not say whether tax is included; we do not assume it is excluded · no price change seen since 16 Oct 2026.
Quality on your task: not measured by Measured Lab yet. On our data, GPT-5.4 mini fits 6 of 6 common tasks by published prices, context window and terms, with calculated monthly costs.
What can I use it for?
Six common tasks cost a month at list prices
- Calculated Answer customer messages: $17.25 for 5,000 customer messages a month
- Calculated Pull data from invoices and documents with strict JSON and page images: $6.60 for 2,000 documents a month
- Calculated Summarize documents and meetings: $7.73 for 1,000 documents or meetings a month
- Calculated Translate content: $14.40 for 3,000 pages a month
- Calculated Chat assistant on your website: $163.12 for 10,000 conversations a month
- Calculated Write and review code with tool calls: $45.56 for 500 coding tasks a month
What our data confirms
- Observed Strict JSON output: accepted in our test call on 17 Oct 2026
- Published Calls your tools, in OpenAI documentation, read 17 Oct 2026
- Published Reads images; OpenRouter listing, 9 Nov 2026
Example to try
“Draft a reply to this refund request from our returns policy, and hand it to a person if the order is over $500.” Run it on your own data before you choose.
What we measured
- Observed Speed on a short test request: first token 0.7 s, 156 tokens/s (median of 120 test requests on 23 dates, short request)
Before you choose
- Published Training on your data, per OpenAI API data controls: no — API data is not used for training unless you explicitly opt in to share it, read 9 Nov 2026
- Unknown Where requests are processed: Unknown
Prices USD per 1M tokens, as listed
- $0.75Input per 1M tokens, from OpenAI Published
- $4.50Output per 1M tokens, from OpenAI Published
All prices by channel
| Price per 1M tokens | OpenAI direct | Through OpenRouter | Previous prices by channel |
|---|---|---|---|
| Input | $0.75 Published | $0.75 Published | — |
| Output | $4.50 Published | $4.50 Published | — |
| Cached input · read | UnknownUnknown | $0.075 Published | — |
| Batch · input / output | — | $0.375 / $2.25 Published | — |
Input price from OpenAI, 24 Oct 2026 – 9 Nov 2026
24 Oct 2026$0.75 throughout9 Nov 2026
Input price through OpenRouter, 16 Oct 2026 – 9 Nov 2026
16 Oct 2026$0.75 throughout9 Nov 2026
OpenRouter providers who serves this model through OpenRouter, at what price
OpenRouter sends a call without a pinned provider to one of these endpoints, and each endpoint has its own price. Prices are USD per 1M tokens, input / output.
Pinned min: $0.375 / $2.25 · OpenAI (openai/flex)
Unpinned range: input $0.375–$1.50, output $2.25–$9.00 across 5 endpoints of 2 providers (listing shows $0.75 / $4.50).
Models with the widest provider price spread on OpenRouter
Request fragment that pins OpenAI (openai/flex):
{"provider": {"order": ["openai/flex"], "allow_fallbacks": false}}With fallbacks turned off, OpenRouter does not move the call to another provider. A full endpoint tag pins that endpoint; the provider name alone covers all of its endpoints (OpenRouter provider routing).
All endpoints (5), by input price
| Provider | Endpoint tag | Precision | Input | Output | Context, tokens |
|---|---|---|---|---|---|
| OpenAI | openai/flex | Not stated | $0.375 | $2.25 | 400,000 |
| Azure | azure | Not stated | $0.75 | $4.50 | 400,000 |
| OpenAI | openai | Not stated | $0.75 | $4.50 | 400,000 |
| Azure | azure/us | Not stated | $0.825 | $4.95 | 400,000 |
| OpenAI | openai/fast | Not stated | $1.50 | $9.00 | 400,000 |
Sorted by input price, then output price. Precision is the quantization field of the endpoints list.
Measured by us our own short test request: about 380 tokens in, a short JSON answer out · medians from answers on two dates or more
United States
| Route | First answer token | Output speed | Cost per request | Hidden reasoning |
|---|---|---|---|---|
| Direct API · OpenAIreasoning: off120 answers on 23 dates · 100 % answered | 663 msrange 0.32–30.57 s · slow 10 %: 1.41 s Observed | 156 tokens/srange 47.6–265 · slowest 10 %: 123 tokens/s | $0.000557range $0.000556–$0.000559 Calculated | 0for 64 visible |
United Kingdom
| Route | First answer token | Output speed | Cost per request | Hidden reasoning |
|---|---|---|---|---|
| Direct API · OpenAIreasoning: off105 answers on 21 dates · 100 % answered | 674 msrange 0.46–1.39 s · slow 10 %: 984 ms Observed | 152 tokens/srange 69.7–262 · slowest 10 %: 112 tokens/s | $0.000557range $0.000556–$0.000559 Calculated | 0for 64 visible |
Germany
| Route | First answer token | Output speed | Cost per request | Hidden reasoning |
|---|---|---|---|---|
| Direct API · OpenAIreasoning: off105 answers on 21 dates · 100 % answered | 678 msrange 0.46–30.92 s · slow 10 %: 1.12 s Observed | 168 tokens/srange 64.1–303 · slowest 10 %: 120 tokens/s | $0.000557range $0.000556–$0.000559 Calculated | 0for 64 visible |
Canada
| Route | First answer token | Output speed | Cost per request | Hidden reasoning |
|---|---|---|---|---|
| Direct API · OpenAIreasoning: off105 answers on 21 dates · 100 % answered | 594 msrange 0.36–1.49 s · slow 10 %: 939 ms Observed | 168 tokens/srange 85.5–243 · slowest 10 %: 135 tokens/s | $0.000557range $0.000556–$0.000559 Calculated | 0for 64 visible |
Australia
| Route | First answer token | Output speed | Cost per request | Hidden reasoning |
|---|---|---|---|---|
| Direct API · OpenAIreasoning: off105 answers on 21 dates · 100 % answered | 900 msrange 0.56–1.70 s · slow 10 %: 1.27 s Observed | 168 tokens/srange 76.8–278 · slowest 10 %: 128 tokens/s | $0.000557range $0.000556–$0.000559 Calculated | 0for 64 visible |
- Hidden reasoning tokens are billed as output, at the output price, even though they are not part of the answer.
How the test works and what each number means: methodology. The figures are also in our open data.
Quality signals public test results, each with its source and date
| Signal | Result | Source |
|---|---|---|
| Instruction followingIFEval, 50 prompts · reasoning: off | 92 % Observedof 50 prompts with every instruction followed | Our run of a fixed IFEval subset, checked by code92 % on 22 Oct 2026 · 88 % on 17 Oct 2026 · instruction level 94 % |
- Your own task: quality on it is not measured here. These are public test sets; a short trial on a few of your own examples is the check that fits your work.
- Other public leaderboards, without figures copied here: human preference votes on open-ended answers: Arena (LMArena) text leaderboard; long tasks in coding, data analysis and research: LiveBench.
What each signal covers and how our run is scored: methodology.
How we got this number
- What we read: the published price on openrouter.ai/api/v1/models
- Checked: ; tracked since 16 Oct 2026
- Shown in: the United States
- Checks so far: 25 checks since 16 Oct 2026
- What changed: no price change since 16 Oct 2026
- Page updated:
Other measured facts
| Question | Answer | Checked | Status |
|---|---|---|---|
| How much does GPT-5.4 Mini cost per 1M input tokens directly from OpenAI (official API price)? | $0.75 per 1M tokens | Published | |
| How much does GPT-5.4 Mini cost per 1M output tokens directly from OpenAI (official API price)? | $4.50 per 1M tokens | Published | |
| How much does OpenAI GPT-5.4 Mini cost per 1M cache-read tokens (cache hits) on OpenRouter? | $0.08 per 1M tokens | Published | |
| How much does OpenAI GPT-5.4 Mini cost per 1M output tokens on OpenRouter? | $4.50 per 1M tokens | Published | |
| What is the context window of OpenAI GPT-5.4 Mini on OpenRouter, in tokens? | 400,000 tokens | Published | |
| What is the maximum output length of OpenAI GPT-5.4 Mini on OpenRouter, in tokens? | 128,000 tokens | Published |
History
Same price in all 25 checks since 16 Oct 2026.
- — First check: $0.75 per 1M tokens
The source record lists $0.00000075 per token ($0.75 per 1M tokens), fetched on 9 Nov 2026.
The source record, as published
"prompt":"0.00000075"
Latest briefings each price change recalculated as a task cost
- DeepSeek V4 Pro 0813: price rise input $0.115 → $0.111 per 1M tokens (-3 %), output $4.00 → $4.44 per 1M tokens (+11 %)
- DeepSeek V4.1 Flash 1017: price cut input $0.300 → $0.0060 per 1M tokens (-98 %), output $1.20 → $0.500 per 1M tokens (-58 %)
- MoonshotAI Kimi K2.5: price rise input $0.500 → $0.532 per 1M tokens (+6 %), output $2.50 → $3.33 per 1M tokens (+33 %)
Record history — 147 records for 7 questions
- Last record
- Shown in
- the United States
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | $0.75 per 1M tokens | Published |
| 8 Nov 2026 | $0.75 per 1M tokens | Published |
| 7 Nov 2026 | $0.75 per 1M tokens | Published |
| 6 Nov 2026 | $0.75 per 1M tokens | Published |
| 5 Nov 2026 | $0.75 per 1M tokens | Published |
| 4 Nov 2026 | $0.75 per 1M tokens | Published |
| 3 Nov 2026 | $0.75 per 1M tokens | Published |
| 2 Nov 2026 | $0.75 per 1M tokens | Published |
| 1 Nov 2026 | $0.75 per 1M tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | $0.75 per 1M tokens | Published |
| 8 Nov 2026 | $0.75 per 1M tokens | Published |
| 7 Nov 2026 | $0.75 per 1M tokens | Published |
| 6 Nov 2026 | $0.75 per 1M tokens | Published |
| 5 Nov 2026 | $0.75 per 1M tokens | Published |
| 4 Nov 2026 | $0.75 per 1M tokens | Published |
| 3 Nov 2026 | $0.75 per 1M tokens | Published |
| 2 Nov 2026 | $0.75 per 1M tokens | Published |
| 1 Nov 2026 | $0.75 per 1M tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | $4.50 per 1M tokens | Published |
| 8 Nov 2026 | $4.50 per 1M tokens | Published |
| 7 Nov 2026 | $4.50 per 1M tokens | Published |
| 6 Nov 2026 | $4.50 per 1M tokens | Published |
| 5 Nov 2026 | $4.50 per 1M tokens | Published |
| 4 Nov 2026 | $4.50 per 1M tokens | Published |
| 3 Nov 2026 | $4.50 per 1M tokens | Published |
| 2 Nov 2026 | $4.50 per 1M tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | $0.08 per 1M tokens | Published |
| 8 Nov 2026 | $0.08 per 1M tokens | Published |
| 7 Nov 2026 | $0.08 per 1M tokens | Published |
| 6 Nov 2026 | $0.08 per 1M tokens | Published |
| 5 Nov 2026 | $0.08 per 1M tokens | Published |
| 4 Nov 2026 | $0.08 per 1M tokens | Published |
| 3 Nov 2026 | $0.08 per 1M tokens | Published |
| 2 Nov 2026 | $0.08 per 1M tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | $4.50 per 1M tokens | Published |
| 8 Nov 2026 | $4.50 per 1M tokens | Published |
| 7 Nov 2026 | $4.50 per 1M tokens | Published |
| 6 Nov 2026 | $4.50 per 1M tokens | Published |
| 5 Nov 2026 | $4.50 per 1M tokens | Published |
| 4 Nov 2026 | $4.50 per 1M tokens | Published |
| 3 Nov 2026 | $4.50 per 1M tokens | Published |
| 2 Nov 2026 | $4.50 per 1M tokens | Published |
| 1 Nov 2026 | $4.50 per 1M tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | 400,000 tokens | Published |
| 8 Nov 2026 | 400,000 tokens | Published |
| 7 Nov 2026 | 400,000 tokens | Published |
| 6 Nov 2026 | 400,000 tokens | Published |
| 5 Nov 2026 | 400,000 tokens | Published |
| 4 Nov 2026 | 400,000 tokens | Published |
| 3 Nov 2026 | 400,000 tokens | Published |
| 2 Nov 2026 | 400,000 tokens | Published |
| 1 Nov 2026 | 400,000 tokens | Published |
| Time | Value | Status |
|---|---|---|
| 9 Nov 2026 | 128,000 tokens | Published |
| 8 Nov 2026 | 128,000 tokens | Published |
| 7 Nov 2026 | 128,000 tokens | Published |
| 6 Nov 2026 | 128,000 tokens | Published |
| 5 Nov 2026 | 128,000 tokens | Published |
| 4 Nov 2026 | 128,000 tokens | Published |
| 3 Nov 2026 | 128,000 tokens | Published |
| 2 Nov 2026 | 128,000 tokens | Published |
Showing the latest 60 of 147 records; the full history is in data.json and data.csv.