Claude Haiku 5.5 vs Gemini 3.8 Flash
Claude Haiku 5.5 is the cheaper of the 2: for the same tokens, 3 read for each 1 written, Gemini 3.8 Flash costs 7.5 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
- Claude Haiku 5.5 is cheaper; Gemini 3.8 Flash costs 7.5 times as much
- Cheaper to read
- Claude Haiku 5.5, $0.10 against $0.75
- Cheaper to write
- Claude Haiku 5.5, $0.50 against $3.75
- Scores higher
- Neither, 159 and 157 are within the range of doubt
- Larger window
- Gemini 3.8 Flash, 1.05M against 1M 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 Haiku 5.5Anthropic | Gemini 3.8 FlashGoogle | |
|---|---|---|
| InputTokens the model reads | $0.10 | $0.75 |
| Cached inputRead again from the cache | $0.01 | $0.075 |
| Cache writePutting text in the cache | $0.125 | Not listed |
| OutputTokens it writes, thinking included | $0.50 | $3.75 |
| Blend 3:13 tokens read for each 1 written | $0.20 | $1.50 |
| Batch inputAnswers collected later | $0.05 | Not listed |
| Batch output | $0.25 | Not listed |
| Long prompt inputAbove 100K on Claude Haiku 5.5 | $0.50 | $0.75 |
| Long prompt outputThe standard price where there is no long-prompt price | $2.50 | $3.75 |
| Context windowTokens it holds at once | 1M | 1.05M |
| Capability scoreEpoch Capabilities Index; GPT-5 is 150 | 159 | 157 |
| Longest answerTokens it writes in 1 reply | 128K | 66K |
Read before you choose
- Gemini 3.8 Flash: Until 31 December 2026. From 1 January 2027 it is $1.50 in, $7.50 out and $0.15 cached.
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 Haiku 5.5
about 2,100 to 3,600 tokens
Sent once: 0.021 cents to 0.036 cents at $0.10 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.
Gemini 3.8 Flash
about 2,200 tokens
Sent once: 0.16 cents at $0.75 per million
Google does not publish the Gemini tokenizer. Its rule is that a token is about 4 characters, so the count is the characters divided by 4.
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 Haiku 5.5 can need up to 1.6 times as many as Gemini 3.8 Flash for the same words, so its bill for the same work can be up to that much higher.
| Job | Claude Haiku 5.5 | Gemini 3.8 Flash | Difference |
|---|---|---|---|
| A chat question300 in, 500 out, 100 a day | 84 cents0.028 cents a run | $6.300.21 cents a run | 7.5 times |
| A hard question, with thinking300 in, 1,400 out, 100 a day | $2.190.073 cents a run | $16.430.55 cents a run | 7.5 times |
| A long report, summarised60,000 in, 2,000 out, 20 a day | $4.200.7 cents a run | $31.505.3 cents a run | 7.5 times |
| A 40-turn agent task2,800,000 in, 40,000 out, 10 a day | $21.967.3 cents a run | $16555 cents a run | 7.5 times |
| A support bot's reply4,000 in, 300 out, 2,000 a day | $22.200.037 cents a run | $1660.28 cents a run | 7.5 times |
| Sort a message into a category250 in, 5 out, 50,000 a day | $41.250.0028 cents a run | $3090.021 cents a run | 7.5 times |
| Read an invoice into fields1,500 in, 250 out, 1,000 a day | $8.250.027 cents a run | $61.880.21 cents a run | 7.5 times |
| Review a pull request25,000 in, 4,500 out, 50 a day | $7.130.48 cents a run | $53.443.6 cents a run | 7.5 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 Haiku 5.584 cents
0.028 cents a run
- Gemini 3.8 Flash$6.30
0.21 cents a run
Claude Haiku 5.5 saves $5.46 a month; Gemini 3.8 Flash costs 7.5 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 Haiku 5.5 or Gemini 3.8 Flash?
- Claude Haiku 5.5 is cheaper: $0.10 per million tokens read and $0.50 per million written, against $0.75 and $3.75 on Gemini 3.8 Flash. On a mix of 3 tokens read for each 1 written, Gemini 3.8 Flash costs 7.5 times as much.
- Which is better, Claude Haiku 5.5 or Gemini 3.8 Flash?
- They cannot be told apart on the Epoch Capabilities Index, an independent score from Epoch AI that combines over 50 benchmarks: Claude Haiku 5.5 scores 159 and Gemini 3.8 Flash 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 Claude Haiku 5.5 and Gemini 3.8 Flash?
- At 2,000 replies a day, each reading 4,000 tokens (50 percent of them from cache) and writing 300, it costs $22.20 a month on Claude Haiku 5.5 and $166 on Gemini 3.8 Flash: Gemini 3.8 Flash costs 7.5 times as much for this job.
- What does an AI agent task cost on Claude Haiku 5.5 and Gemini 3.8 Flash?
- One 40-turn task that reads 2,800,000 tokens in all, 90 percent of them from cache, and writes 40,000, costs 7.3 cents on Claude Haiku 5.5 and 55 cents on Gemini 3.8 Flash. At 10 tasks a day that is $21.96 and $165 a month.
- Which has the larger context window, Claude Haiku 5.5 or Gemini 3.8 Flash?
- Gemini 3.8 Flash, with 1.05M tokens against 1M on Claude Haiku 5.5. 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 Haiku 5.5 and Gemini 3.8 Flash?
- No. Our lesson "How AI writes", 1,700 words long, is about 2,100 to 3,600 tokens on Claude Haiku 5.5 and about 2,200 on Gemini 3.8 Flash. 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 Haiku 5.5 and Gemini 3.8 Flash for work that can wait?
- On Claude Haiku 5.5 only: with a batch, where you collect the answers later, it costs $0.05 per million tokens read and $0.25 written. Google's price page lists no batch price for Gemini 3.8 Flash.
Sources