GPT-5.4 pro vs Qwen3.8-Max
Qwen3.8-Max is the cheaper of the 2: for the same tokens, 3 read for each 1 written, GPT-5.4 pro costs 23 times as much. Below are both price lists, what 8 everyday jobs cost a month on each, and how many tokens the same text takes on each, which can change the answer.
- For the same tokens
- Qwen3.8-Max is cheaper; GPT-5.4 pro costs 23 times as much
- Cheaper to read
- Qwen3.8-Max, $2 against $30
- Cheaper to write
- Qwen3.8-Max, $6 against $180
- Scores higher
- Neither, 159 and 157 are within the range of doubt
- Larger window
- Not listed for Qwen3.8-Max
Price per million tokens, side by side
In US dollars, as each maker prints them. The better figure in each row is green.
| GPT-5.4 proOpenAI · earlier model | Qwen3.8-MaxAlibaba | |
|---|---|---|
| InputTokens the model reads | $30 | $2 |
| Cached inputRead again from the cache | Not listed | $0.25 |
| Cache writePutting text in the cache | Not listed | Not listed |
| OutputTokens it writes, thinking included | $180 | $6 |
| Blend 3:13 tokens read for each 1 written | $67.50 | $3 |
| Batch inputAnswers collected later | $15 | Not listed |
| Batch output | $90 | Not listed |
| Long prompt inputAbove 272K on GPT-5.4 pro | $60 | $2 |
| Long prompt outputThe standard price where there is no long-prompt price | $270 | $6 |
| Context windowTokens it holds at once | 1.05M | Not listed |
| Capability scoreEpoch Capabilities Index; GPT-5 is 150 | 159 | 157 |
| Longest answerTokens it writes in 1 reply | 128K | Not listed |
The same text, counted by each maker
A price per token means little until you know how many tokens your text is. Here is our lesson How AI writes, about 1,700 words of English, counted the way each maker counts it, and what it costs to send it once.
GPT-5.4 pro
about 2,100 tokens
Sent once: 6.2 cents at $30 per million
GPT-5.6 is counted with o200k_base, the tokenizer OpenAI publishes for it, so its count is exact. OpenAI has not published the tokenizer of GPT-6, so its count is the same o200k_base figure, marked as about.
Qwen3.8-Max
about 2,100 tokens
Sent once: 0.43 cents at $2 per million
Counted with the tokenizer Alibaba publishes with its open Qwen3.8 models. Alibaba does not say its API models use the same one, so the count is marked as about.
What 8 everyday jobs cost a month on each
Each job at its usual number of runs a day, for 30 days, at the standard price. The cheaper of the 2 is green; open any job in the calculator to change it.
| Job | GPT-5.4 pro | Qwen3.8-Max | Difference |
|---|---|---|---|
| A chat question300 in, 500 out, 100 a day | $2979.9 cents a run | $10.800.36 cents a run | 27 times |
| A hard question, with thinking300 in, 1,400 out, 100 a day | $78326 cents a run | $27.000.9 cents a run | 29 times |
| A long report, summarised60,000 in, 2,000 out, 20 a day | $1,296$2.16 a run | $79.2013 cents a run | 16 times |
| A 40-turn agent task2,800,000 in, 40,000 out, 10 a day | $27,360$91.20 a run | $429$1.43 a run | 64 times |
| A support bot's reply4,000 in, 300 out, 2,000 a day | $10,44017 cents a run | $3780.63 cents a run | 28 times |
| Sort a message into a category250 in, 5 out, 50,000 a day | $12,6000.84 cents a run | $7950.053 cents a run | 16 times |
| Read an invoice into fields1,500 in, 250 out, 1,000 a day | $2,7009 cents a run | $1350.45 cents a run | 20 times |
| Review a pull request25,000 in, 4,500 out, 50 a day | $2,340$1.56 a run | $1167.7 cents a run | 20 times |
Your own job on both
Start from a job, then set its size, how often it runs and whether the answers can wait. Both bills follow every change.
A short question and a few paragraphs back.
about 230 words
Instructions or documents the model has read before cost far less the second time.
about 380 words
A month of this job
- GPT-5.4 pro$297
9.9 cents a run
- Qwen3.8-Max$10.80
0.36 cents a run
Qwen3.8-Max saves $286 a month; GPT-5.4 pro costs 27 times as much.
This job on every modelWhy the price per token is only the start
Every maker prints 2 main prices: one for the tokens a model reads (input) and one for the tokens it writes (output). On most current models writing costs 3 to 5 times as much as reading, so which model is cheaper can depend on the job. A job that reads a long document and writes a line pays mostly the input price; a chat that writes paragraphs pays mostly the output price. That is why each comparison prices 8 jobs and not one figure.
The same text is not the same number of tokens on every model. Each maker cuts text its own way, and Anthropic says its models from Claude 4.7 on produce about 30 percent more tokens for the same text than earlier ones. A model with the lower price per token can still send the larger bill, so each comparison counts one of our lessons the way both makers count it.
Discounts change the order too. Work that can wait costs half on a batch at the makers that offer one, and text read again from a cache costs a quarter of the input price or less on every current model here. The price table on each comparison shows who offers what.
Thinking is billed as output, and models differ in how much they think and how long they answer. A price list cannot show that. Before you switch, run the same 10 tasks on both models and compare the bills.
Questions
- Which is cheaper, GPT-5.4 pro or Qwen3.8-Max?
- Qwen3.8-Max is cheaper: $2 per million tokens read and $6 per million written, against $30 and $180 on GPT-5.4 pro. On a mix of 3 tokens read for each 1 written, GPT-5.4 pro costs 23 times as much.
- Which is better, GPT-5.4 pro or Qwen3.8-Max?
- They cannot be told apart on the Epoch Capabilities Index, an independent score from Epoch AI that combines over 50 benchmarks: GPT-5.4 pro scores 159 and Qwen3.8-Max 157, within the range of doubt around each (GPT-5 is 150). So choose on price and on 10 tasks of your own.
- What does a support bot cost a month on GPT-5.4 pro and Qwen3.8-Max?
- At 2,000 replies a day, each reading 4,000 tokens (50 percent of them from cache) and writing 300, it costs $10,440 a month on GPT-5.4 pro and $378 on Qwen3.8-Max: GPT-5.4 pro costs 28 times as much for this job.
- What does an AI agent task cost on GPT-5.4 pro and Qwen3.8-Max?
- One 40-turn task that reads 2,800,000 tokens in all, 90 percent of them from cache, and writes 40,000, costs $91.20 on GPT-5.4 pro and $1.43 on Qwen3.8-Max. At 10 tasks a day that is $27,360 and $429 a month.
- Does the same text take the same number of tokens on GPT-5.4 pro and Qwen3.8-Max?
- No. Our lesson "How AI writes", 1,700 words long, is about 2,100 tokens on GPT-5.4 pro and about 2,100 on Qwen3.8-Max. Each maker cuts text its own way, and every extra token is paid for at the model's price.
- Can I pay less on GPT-5.4 pro and Qwen3.8-Max for work that can wait?
- On GPT-5.4 pro only: with a batch, where you collect the answers later, it costs $15 per million tokens read and $90 written. Alibaba's price page lists no batch price for Qwen3.8-Max.
Sources