Claude Sonnet 4.6
$1,740.00 / month- Input cost
- $1,365.00
- Output cost
- $375.00
- Per 1,000 calls
- $174.00
- Pricing profile
- standard
Source-tracked model comparison
How do Claude Sonnet 4.6 and Gemini 2.5 Pro costs compare for long documents?
Compare verified pricing and model limits for long-document analysis. The cost example uses a document summarization workload and does not assume equal model quality.
Direct cost answer: Claude Sonnet 4.6 is estimated at $1,740.00 per month and Gemini 2.5 Pro at $818.75 for 50,000 input tokens, 2,500 output tokens, and 10,000 monthly requests. Gemini 2.5 Pro is $921.25 lower under these assumptions. This does not identify a quality winner.
Tracked facts
Pricing and model limits
Prices are USD per 1M tokens under each model's verified default profile.
| Field | Claude Sonnet 4.6 | Gemini 2.5 Pro |
|---|---|---|
| Provider | Anthropic | |
| API model ID | claude-sonnet-4-6 | gemini-2.5-pro |
| Input / 1M | $3.00 | $1.25 |
| Cached input / 1M | $0.30 | $0.125 |
| Output / 1M | $15.00 | $10.00 |
| Context window | 1,000,000 tokens | 1,048,576 tokens |
| Maximum output | 128,000 tokens | 65,536 tokens |
| Accepted input | text, image | text, image, video, audio, pdf |
Example workload
Document summarization cost scenario
50,000 input and 2,500 output tokens per request, 10,000 monthly requests, and 10% cached input.
Gemini 2.5 Pro
$818.75 / month- Input cost
- $568.75
- Output cost
- $250.00
- Per 1,000 calls
- $81.88
- Pricing profile
- standard / short context
Cost result: Gemini 2.5 Pro is $921.25 lower per month for these assumptions. This is a price comparison, not a model-quality ranking.
Questions to answer before choosing
- Which model preserves the facts required by the summary?
- Does prompt size trigger a higher tracked pricing tier?
- How much output is needed for the intended document type?
What this estimate leaves out
OCR, file ingestion, multimodal document processing, and multi-pass summarization are not included.
Latency, reliability, output quality, retries, regional processing, and provider-specific tool charges can change the practical decision.
Related active comparisons
Continue with a nearby model decision
These comparisons share a model or provider decision with this page.
same family
Gemini 2.5 Pro vs Gemini 2.5 Flash
How much does Gemini 2.5 Pro cost compared with Gemini 2.5 Flash for RAG?
Compare API cost provider switchGPT-4o vs Claude Sonnet 4.6
How do GPT-4o and Claude Sonnet 4.6 costs compare for developer assistance?
Compare API cost contextGPT-4o vs Gemini 2.5 Pro
How do GPT-4o and Gemini 2.5 Pro costs compare for document workloads?
Compare API cost