Comparison · Anthropic and Google
Claude Sonnet 5.5 vs Gemini 3.8 Flash
Listed API prices of Claude Sonnet 5.5 and Gemini 3.8 Flash turned into the cost of the same three standard tasks, with speed from our own test requests in the United States and what each provider’s API documentation says about features that break on a switch. Output quality and answer length are not compared.
Calculated impact cost per task and per month
For an L2 task (deep analysis over a 50,000-token document, 3 steps), Claude Sonnet 5.5 costs $0.348 and Gemini 3.8 Flash $0.131 at the prices listed in the United States on , so Claude Sonnet 5.5 is 166.7 % more than Gemini 3.8 Flash, counting visible output only, without cache discounts or hidden reasoning.
| Task | Claude Sonnet 5.5, per task | Gemini 3.8 Flash, per task | Claude Sonnet 5.5, per month | Gemini 3.8 Flash, per month | Claude Sonnet 5.5 vs Gemini 3.8 Flash, per task |
|---|---|---|---|---|---|
| L1Micro-task (classification or strict JSON extraction) | $0.0050per L1 task | $0.0019per L1 task | $73.00per month | $27.38per month | +166.7 % |
| L2Deep analysis over a 50,000-token document | $0.348per L2 task | $0.131per L2 task | $5,080.80per month | $1,905.30per month | +166.7 % |
| L3Agentic coding loop, 15 steps | $2.72per L3 task | $1.02per L3 task | $39,726.60per month | $14,897.47per month | +166.7 % |
Calculated Per month: 20 tasks an hour around the clock, 730 hours.
Prices USD per 1M tokens
| Price | Claude Sonnet 5.5 | Gemini 3.8 Flash |
|---|---|---|
| Input, per 1M tokens | $2.00 | $0.750 |
| Output, per 1M tokens | $10.00 | $3.75 |
| Price from | Provider's price list · source page Published | Provider's price list · source page Published |
| Read | · the United States | · the United States |
| Context window | 1,000,000 tokens | 1,048,576 tokens |
What can I use it for? six common tasks, our data checks
Quality on your task: not measured by Measured Lab yet.
| Task | Claude Sonnet 5.5 | Gemini 3.8 Flash |
|---|---|---|
| Answer customer messages | Fits on price and context | Fits on price and context |
| Pull data from invoices and documents with strict JSON and page images | Fits on price and context | Fits on price and context |
| Summarize documents and meetings | Fits on price and context | Fits on price and context |
| Translate content | Fits on price and context | Fits on price and context |
| Chat assistant on your website | Fits on price and context | Fits on price and context |
| Write and review code with tool calls | Fits on price and context | Fits on price and context |
| Tasks it fits | 6 of 6 | 6 of 6 |
Checks of our data for six common tasks: a published price, a context window and answer length for the task and, where the task needs them, strict JSON output, page images and tool calls; prices, cost a month and terms for each model on its model card. Compare models for your own task in the model picker.
Speed in the US Observed our test requests
In our test requests from the United States, the median time to the first answer token was 961 ms for Claude Sonnet 5.5 (Direct API · Anthropic) and 6,955 ms for Gemini 3.8 Flash (Direct API · Google).
| Model and route | Time to first answer token, median | Output speed, median | Answers |
|---|---|---|---|
| Claude Sonnet 5.5Direct API · Anthropic | 961 ms range 363 ms–8,537 ms | 115 tokens/s range 67.7 tokens/s–244 tokens/s | 115 answers on 23 dates |
| Gemini 3.8 FlashDirect API · Google | 6,955 ms range 1,021 ms–10,510 ms | 200 tokens/s range 103 tokens/s–365 tokens/s | 95 answers on 19 dates |
The same short request to every model, sent from a measurement point in the United States; medians of successful answers on at least 2 different dates, latest on . How we measure
What breaks when you switch Published provider documentation
Moving from Anthropic to Google, 1 of the 5 features may not carry over, by each provider’s documentation:
- Cache covers tool definitions — Anthropic: yes; Google: not stated. Where the cache does not cover tool definitions, a long tool list is paid as fresh input on every request.
Moving from Google to Anthropic: every feature that Google’s documentation lists as supported is also listed as supported by Anthropic.
| Feature of the API | Anthropic | |
|---|---|---|
| Strict JSON schemas | Yes | Yes |
| Parallel tool calls | Yes | Yes |
| Streamed tool arguments | Yes | Yes |
| Reasoning with tools | Yes | Yes |
| Cache covers tool definitions | Yes | Not stated |
What each provider’s own API documentation says, read ; “not stated” is not the same as “no”. Quotes and sources: what breaks when you switch AI APIs.