import requests r = requests.post( "https://api.aimlapi.com/v1/chat/completions", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "anthropic/claude-sonnet-4.5", "messages": [ { "role": "user", "content": "Hello!" } ] }, ) print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", { method: "POST", headers: { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "model": "anthropic/claude-sonnet-4.5", "messages": [ { "role": "user", "content": "Hello!" } ] }), }); console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"anthropic/claude-sonnet-4.5","messages":[{"role":"user","content":"Hello!"}]}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Cached input |
| Benchmark | Score | What it measures | Source | Retrieved |
|---|---|---|---|---|
| Intelligence | 21.2 | Composite score across standardised reasoning, knowledge and problem-solving evaluations, measured independently by Artificial Analysis | Source | September 12, 2026 |
| Coding | 52.1 | Composite score across standardised coding evaluations, measured independently by Artificial Analysis | Source | September 12, 2026 |
| Math | 88 | Composite score across standardised mathematics evaluations, measured independently by Artificial Analysis | Source | September 12, 2026 |
| SWE-bench Verified | 77.2% | Resolving verified real GitHub issues | Source | September 22, 2026 |
| OSWorld | 61.4% | Computer-use across real desktop applications | Source | September 22, 2026 |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Claude 4.5 Sonnet Thinking This page | Chat + assistants | |||
| Reasoning + agents | ||||
| Balanced coding + agents | ||||
| Long-context, multimodal & agentic workflows | ||||
| Reasoning + agents |
Claude 4.5 Sonnet Thinking has a 200,000 tokens context window and can return up to 64,000 tokens.
Claude 4.5 Sonnet Thinking takes text as input and returns text.
Use anthropic/claude-sonnet-4.5 as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.
Claude 4.5 Sonnet Thinking is priced at input $4.1262 / 1M tokens, output $19.5 / 1M tokens, cached input $0.41262 / 1M tokens.
Yes, Claude 4.5 Sonnet Thinking can stream responses as they are generated.
Claude 4.5 Sonnet Thinking was built by Anthropic.
Its name includes 'Thinking,' indicating it is built for extended reasoning tasks.