Claude Opus 5.5
- Input / 1M tokens
- $4.00
- Output / 1M tokens
- $20.00
- Providers
- 5
- Uptime, 24 h
- 100%
API models · Side by side
Claude Opus 5.5 vs Gemini 3.1 Pro Preview
Opus 5.5 and Gemini 3.1 Pro Preview make different trade-offs. Gemini is cheaper for ordinary text requests and accepts audio and video. Opus offers a larger reply allowance and different long-document pricing.
Gemini 3.1 Pro Preview
- Input / 1M tokens
- $2.00
- Output / 1M tokens
- $12.00
- Providers
- 2
- Uptime, 24 h
- 100%
The short answer
Consider Gemini when direct audio or video input is required or its lower base rates suit a text workload. Consider Opus when you need its response behaviour, larger output allowance or long-prompt billing arrangement. Neither a larger budget nor a longer context window proves better answers.
Estimate your monthly bill
Enter your own usage. We apply each model's current rates, including long-prompt pricing, for a 30-day month.
Try:
Claude Opus 5.5$540.00per month
Gemini 3.1 Pro Preview$300.00per month
A token is roughly three-quarters of an English word. Cached input, reasoning tokens, tools and media are not included.
Compare the details
Compare context, supported inputs and usage costs. Highlighted rows show a difference.
| Feature | Claude Opus 5.5 | Gemini 3.1 Pro Preview |
|---|---|---|
| Input formats | file, image, text | audio, file, image, text, video |
| Output formats | text | text |
| Context / position limit | 1,000,000 | 1,048,576 |
| Endpoint output limit (tokens) | 128,000 | 65,536 |
| Developer features | Reasoning output, Completion limit, Output limit, Reasoning controls, Thinking effort, Response format, Stop sequences, Structured output, Tool selection, Tool calling, Response length | Reasoning output, Output limit, Reasoning controls, Thinking effort, Response format, Seed, Stop sequences, Structured output, Temperature, Tool selection, Tool calling, Sampling controls |
| Cached input / 1M tokens | $0.20 | $0.20 |
| Cache write / 1M tokens | $5.00 | $0.38 |
| USD input / 1M tokens | $4.00 | $2.00 |
| USD output / 1M tokens | $20.00 | $12.00 |
| Available API providers | 5 | 2 |
| Best provider uptime, last 24 h | 100% | 100% |
| Model identifier | anthropic/claude-opus-5.5 | google/gemini-3.1-pro-preview |
API pricing
Prices are in USD per million tokens. Input is what you send; output is what the model generates. Chat subscriptions and API usage are billed separately.
Gemini 3.1 Pro Preview: long-prompt rates
- Long-prompt threshold: 200,000 prompt tokens. Input: $4.00 / 1M. Output: $18.00 / 1M.
Tools, images and additional reasoning can add charges. The examples below cover input and output tokens only.
Compare local modelsWhat those prices mean in practice
Each example uses the same token budget for both models. These are calculations, not measured workloads. Cache discounts, media, tools and extra reasoning are excluded.
| Workload | Claude Opus 5.5 | Gemini 3.1 Pro Preview |
|---|---|---|
| 1,000 short requestsPer request: 2,000 input + 500 output tokens | $18.00 | $10.00 |
| 100 document summariesPer request: 20,000 input + 1,000 output tokens | $10.00 | $5.20 |
| 10 long-document requestsPer request: 300,000 input + 2,000 output tokens | $12.40 | $12.36 |
Estimate = requests × (input tokens × input price + output tokens × output price) ÷ 1,000,000. Long-prompt rates are applied where the pricing data provides them. Real requests can use different amounts of output.
Beyond the price tag
Small requests favour Gemini on token cost
Opus costs $4 per million input tokens and $20 per million output tokens. Gemini’s base rates are $2 and $12. At 1,000 requests with 2,000 input tokens and 500 output tokens each, the totals are $18 for Opus and $10 for Gemini. Use that difference as a budget question: what improvement would justify spending the additional amount on your actual workload?
Very long prompts change the comparison
Gemini moves to $4 input and $18 output per million tokens at its 200,000-token prompt threshold. Opus has no equivalent long-prompt tier in the current rates. The input-price gap therefore disappears at that Gemini tier, while the output rates remain different. A large archive and a short chat should not share the same cost assumption.
Choose inputs before choosing a model tier
Gemini accepts audio and video directly. Opus accepts text, images and files in this comparison. For a video review, sending a written transcript to Opus is a different workflow from supplying the recording to Gemini. Decide whether the job needs the original media before comparing results, because different evidence can explain a difference in the answer.
Long outputs bring their own work
Opus has a 128,000-token output allowance; Gemini has 65,536. That can matter for a large generated artifact, but a generous maximum is not a recommendation to use it. A report that long is costly to inspect and difficult to correct as one unit. Give the model a clear structure and consider producing sections that can be checked separately.
Keep the decision tied to a real task
For a document workflow, compare the same files and ask for the same deliverable. Record factual errors, missing requirements and the amount of editing each answer needs. For Gemini, include the implications of using a preview endpoint. For Opus, decide whether the result justifies the higher small-request bill. Avoid declaring an overall winner from a task that covers only one part of your application.
Common questions
Which costs less for a 300,000-token prompt?
With a 2,000-token reply, Opus costs $1.24 and Gemini costs $1.236 using its long-prompt tier. The difference is tiny for that example; additional reasoning, tools and media are excluded.
Can I use either with private business documents?
Check the terms and data controls of the actual service endpoint you use. The model name alone does not establish retention, regional processing or access arrangements for your account.