Anthropic

llm

Claude Sonnet 4.5

Claude Sonnet 4.5

Claude Sonnet 4.5

Anthropic's most capable model, built for complex reasoning, coding, and long-context tasks.

Anthropic's most capable model, built for complex reasoning, coding, and long-context tasks.

All models

chat, vision, reasoning

REQUEST

llm

curl -X POST https://api.apiarium.dev/llm -H "Authorization: Bearer YOUR_KEY" -H "Content-Type: application/json" -d '{"model":"claude-sonnet","messages":[{"role":"user","content":"Hello"}]}'

curl -X POST https://api.apiarium.dev/llm -H "Authorization: Bearer YOUR_KEY" -H "Content-Type: application/json" -d '{"model":"claude-sonnet","messages":[{"role":"user","content":"Hello"}]}'

Context window

200K

200K

Max output

8.2K

8.2K

Credits

16.875 credits / 1K input tokens, 101.25 credits / 1K output tokens

USD equivalent

$3.00 / $15.00 per 1M tokens (input/output)

MODEL NOTES

Claude Sonnet 4.5 is Anthropic's most capable model, built for complex reasoning, coding, and long-context work. It's the model to reach for when a task genuinely requires multi-step thinking — debugging logic, working through an ambiguous spec, or writing code that needs to actually be correct, not just plausible-looking.

The 200,000 token context window means it can hold an entire codebase, a long document, or an extended conversation in memory without losing track of earlier details.

This is Apiarium's most expensive per-token model, reflecting its real capability gap over faster models — it's not meant to be your default, it's meant to be the option you switch to for the requests that actually need it.

‹ Claude Haiku 4.5

Gemini 3.5 Flash ›