Claude Sonnet 4.5
anthropic/claude-sonnet-4.5The default serious coding model, million-token context, dependable agent loops, production temperament.
Model overview
Context window
1M
tokens
Input price
—
quoted on request
Output price
—
quoted on request
Weekly volume
—
tokens / week
Open weights
No
API only
Capabilities
6
of 11 tags
Description
Claude Sonnet 4.5 is a coding model from Anthropic. Webparam does not stock this model yet and can source it on request — tell us what you need it for and we will come back with availability and a price. Anthropic’s stated focus is frontier models with a safety-first identity. The weights are not published, so it is API-only.
Capabilities
- Tool calling
- Calls functions you define and returns their arguments as structured data, the basis of agents.
- JSON mode
- Constrains the response to valid JSON matching a schema you supply.
- Streaming
- Emits tokens as they are generated, so answers appear progressively rather than all at once.
- Caching
- Reuses already-processed prompt prefixes across requests, cutting input cost for repeated context.
- Vision input
- Accepts images alongside text in the prompt.
- Long context
- Built for inputs well beyond the mainstream window, whole repositories, archives or corpora.
Strengths & weaknesses
Strengths
- Best-in-catalogue agentic coding (SWE-bench 77)
- 1M context fits entire repositories
- Caching cuts effective input cost sharply
Weaknesses
- Premium pricing versus open peers
- Closed weights
Pricing
Free| Rate | Price | Unit |
|---|---|---|
| Input | $0.00 | per 1M tokens |
| Output | — not charged | — |
Prompt caching is supported, so repeated prefixes bill below the listed input rate. Free at the point of use; fair-use rate limits apply to the free tier. Illustrative placeholder pricing.
Context window
1Mtokens
covers prompt and response together, so a long input leaves less room for the answer.
Supported features
| Feature | Support |
|---|---|
| Tool calling | Supported |
| JSON mode | Supported |
| Streaming | Supported |
| Vision input | Supported |
| Audio input | Not supported |
| Long context | Supported |
| Open weights | Not supported |
| Reasoning | Not supported |
| Fine-tunable | Not supported |
| Batch | Not supported |
| Caching | Supported |
Example use cases
Coding agents
Best-in-catalogue agentic coding (SWE-bench 77)
Repository-scale work
1M context fits entire repositories
Production assistants
Caching cuts effective input cost sharply
Example prompt
Review this diff for correctness and side effects, then propose a safer refactor with tests.Comparison
| Attribute | Claude Sonnet 4.5 | Qwen3 Coder | Claude Opus 4.5 |
|---|---|---|---|
| Context window | 1M | 256K | 200K |
| Input price | $0.00 | $0.00 | $0.00 |
| Output price | — not charged | — not charged | — not charged |
| Tool calling | Supported | Supported | Supported |
| JSON mode | Supported | Supported | Supported |
| Vision input | Supported | Not supported | Supported |
| Open weights | Not supported | Supported | Not supported |
| Prompt caching | Supported | Not supported | Supported |
Best value in each row is highlighted. Illustrative placeholder data.
Provider information
View Anthropic →Anthropic · San Francisco, United States · est. 2021
Founded by former OpenAI researchers, Anthropic pairs frontier capability with an explicit safety research agenda. 5's million-token context a favourite for repository-scale tasks.
Recent releases
Documentation
Frequently asked questions
Input is billed at $0.00 per 1M tokens, and there is no separate output charge. Prompt caching bills repeated prefixes below the listed input rate. Every figure on this page is an illustrative placeholder.