Primary use stated or inferred cautiously from official documentation.
A
ANTHROPIC / claude-sonnet-4-5
Claude Sonnet 4.5
Previous Sonnet generation for code, agents, and interface automation, with official computer use results.
01 / SUMMARY
The essential
Maximum input capacity when published by the source.
Documented maximum generation limit.
Verified availability channels.
Primary functional family and verified specialties.
Declared terms for API access, model weights, or self-hosting.
02 / TECHNICAL SHEET
Limits and integration
| API ID | claude-sonnet-4-5 |
|---|---|
| Model type | Code · Text and reasoning |
| Access model | Paid proprietary |
| License | Proprietary |
| Deployment | Hosted API |
| Release | 29 SEP 2025 |
| Knowledge cutoff | Not published |
| Entrance | Text · Image |
| Exit | Text |
| Context window | 200.000 tokens |
| maximum output | Not published |
| Reasoning | Extended thinking |
| Published tools | Use of tools · Computer use |
| Structured Outings | Not applicable or not published |
| Batch processing | Not published |
| Prompt cache | Not published |
| Fine-tuning | Not published |
| Verified platforms | Claude API · Amazon Bedrock · Google Cloud · Microsoft Foundry |
Compatibility with agent workflows built on Claude 4.5.
It is an earlier generation; validate cost and behavior against Sonnet 5.
03 / CAPABILITIES
What it can do
Orientation
Compatibility with agent workflows built on Claude 4.5.
Context
200,000 tokens · Not published
Tools and integration
Tool use · Computer use
Access
Claude API and associated clouds
Input modalities
TextImage
04 / PRICES
Documented cost
| Concept | Worth | Unit/condition |
|---|---|---|
| Standard input | Not published | Standard API rate |
| Cached input | Not published | Reading reused prefixes |
| Cache write or storage | Not published | The condition varies by provider |
| Standard output | Not published | May include reasoning tokens |
| Batch input | Not published | Asynchronous processing |
| Batch output | Not published | Asynchronous processing |
Consult the primary source: the billing unit depends on the model type and access channel.
i Prices change and may depend on level, region or context length. Check the source before making a decision.
05 / EVALUATIONS
How to read the results
“
A public benchmark provides guidance, but does not replace an evaluation with your data, tools, budget, and error tolerance.
| Benchmark | Result | Metric | Source |
|---|---|---|---|
| OSWorld | 61,4 % | Computer tasks solved | View source ↗ |
Inferama only highlights a “best result” when the metric, test set, configuration, and date allow for an equivalent comparison. The supplier's figures are presented as claims from its own source.
06 / VERSIONS
Chronology
Claude Sonnet 4.5
Version added to Inferama's verified catalog.
ANALYSIS
Related analysis
Claude Sonnet 4.5 with tools: calculate the cost of a task, not just a call
A template for estimating tool-workflow costs by round, separating input and output tokens from additional charges, and checking the calculation against usage logs.
28 Sep 2026 ↗
Claude Sonnet 4.5 in the life sciences: what its results show and how to revalidate them
Sonnet 4.5’s scores on biological research tasks justify internal evaluation, not a conclusion about its experimental reliability. What Protocol QA, LAB-Bench, and BixBench measure, what they do not, and how to design a controlled retrospective test.
23 Sep 2026 ↗
Claude Opus 4.5 vs Claude Sonnet 4.5: when to pay more to fix code issues—and when not to
The useful comparison between Claude Opus 4.5 and Claude Sonnet 4.5 is not a general verdict on capability. It is an operational decision: which one lowers the total cost per correctly resolved, reviewed, and accepted issue in a specific repository. This guide proposes a reproducible protocol for measuring that outcome with frozen tickets, tests, blind human review, and complete costs.
22 Sep 2026 ↗07 / SOURCES