Claude Sonnet 4.5 vs GPT-4o
GPT-4o is the cheaper of the 2: for the same tokens, 3 read for each 1 written, Claude Sonnet 4.5 costs 1.4 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
- GPT-4o is cheaper; Claude Sonnet 4.5 costs 1.4 times as much
- Cheaper to read
- GPT-4o, $2.50 against $3
- Cheaper to write
- GPT-4o, $10 against $15
- Scores higher
- Not known, GPT-4o has no independent score yet
- Larger window
- Claude Sonnet 4.5, 200K against 128K tokens
Price per million tokens, side by side
In US dollars, as each maker prints them. The better figure in each row is green.
| Claude Sonnet 4.5Anthropic · earlier model | GPT-4oOpenAI · earlier model | |
|---|---|---|
| InputTokens the model reads | $3 | $2.50 |
| Cached inputRead again from the cache | $0.30 | $1.25 |
| Cache writePutting text in the cache | $3.75 | Not listed |
| OutputTokens it writes, thinking included | $15 | $10 |
| Blend 3:13 tokens read for each 1 written | $6 | $4.375 |
| Batch inputAnswers collected later | $1.50 | $1.25 |
| Batch output | $7.50 | $5 |
| Context windowTokens it holds at once | 200K | 128K |
| Capability scoreEpoch Capabilities Index; GPT-5 is 150 | 147 | Not listed |
| Longest answerTokens it writes in 1 reply | 64K | 16K |
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.
Claude Sonnet 4.5
about 2,100 to 3,600 tokens
Sent once: 0.62 cents to 1.1 cents at $3 per million
Anthropic does not publish its tokenizer. It says Claude 4.7 and later produce about 30 percent more tokens for the same text than earlier models, and an independent test counted TypeScript at 1.73 times OpenAI's figure. The range runs from OpenAI's count to 1.75 times it.
GPT-4o
about 2,100 tokens
Sent once: 0.51 cents at $2.50 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.
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. Sizes are in tokens, and Claude Sonnet 4.5 can need up to 1.8 times as many as GPT-4o for the same words, so its bill for the same work can be up to that much higher.
| Job | Claude Sonnet 4.5 | GPT-4o | Difference |
|---|---|---|---|
| A chat question300 in, 500 out, 100 a day | $25.200.84 cents a run | $17.250.57 cents a run | 1.5 times |
| A hard question, with thinking300 in, 1,400 out, 100 a day | $65.702.2 cents a run | $44.251.5 cents a run | 1.5 times |
| A long report, summarised60,000 in, 2,000 out, 20 a day | $12621 cents a run | $10217 cents a run | 1.2 times |
| A 40-turn agent task2,800,000 in, 40,000 out, 10 a day | $659$2.20 a run | Too long for its window$4.25 a run | |
| A support bot's reply4,000 in, 300 out, 2,000 a day | $6661.1 cents a run | $6301 cents a run | 1.1 times |
| Sort a message into a category250 in, 5 out, 50,000 a day | $1,2380.083 cents a run | $1,0130.068 cents a run | 1.2 times |
| Read an invoice into fields1,500 in, 250 out, 1,000 a day | $2480.83 cents a run | $1880.63 cents a run | 1.3 times |
| Review a pull request25,000 in, 4,500 out, 50 a day | $21414 cents a run | $16111 cents a run | 1.3 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
- Claude Sonnet 4.5$25.20
0.84 cents a run
- GPT-4o$17.25
0.57 cents a run
GPT-4o saves $7.95 a month; Claude Sonnet 4.5 costs 1.5 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, Claude Sonnet 4.5 or GPT-4o?
- GPT-4o is cheaper: $2.50 per million tokens read and $10 per million written, against $3 and $15 on Claude Sonnet 4.5. On a mix of 3 tokens read for each 1 written, Claude Sonnet 4.5 costs 1.4 times as much.
- Which is better, Claude Sonnet 4.5 or GPT-4o?
- Claude Sonnet 4.5 scores 147 on the Epoch Capabilities Index, an independent score from Epoch AI that combines over 50 benchmarks (GPT-5 is 150). GPT-4o has no independent score yet, so the only fair test is to run the same 10 tasks on both.
- What does a support bot cost a month on Claude Sonnet 4.5 and GPT-4o?
- At 2,000 replies a day, each reading 4,000 tokens (50 percent of them from cache) and writing 300, it costs $666 a month on Claude Sonnet 4.5 and $630 on GPT-4o: Claude Sonnet 4.5 costs 1.1 times as much for this job.
- Which has the larger context window, Claude Sonnet 4.5 or GPT-4o?
- Claude Sonnet 4.5, with 200K tokens against 128K on GPT-4o. The window holds your instructions, the files you attach, the conversation so far and the answer, all at once.
- Does the same text take the same number of tokens on Claude Sonnet 4.5 and GPT-4o?
- No. Our lesson "How AI writes", 1,700 words long, is about 2,100 to 3,600 tokens on Claude Sonnet 4.5 and about 2,100 on GPT-4o. Each maker cuts text its own way, and every extra token is paid for at the model's price.
- Can I pay less on Claude Sonnet 4.5 and GPT-4o for work that can wait?
- Yes, on both. With a batch, where you collect the answers later instead of at once, Claude Sonnet 4.5 costs $1.50 per million tokens read and $7.50 written, and GPT-4o $1.25 and $5.
Sources