anthropic/claude-sonnet-4-5
Balanced Claude model for coding, analysis, agent workflows, and cost control
This model's cache
This model page returns the exact headers below. The page and /api/models/anthropic--claude-sonnet-4-5 share the model:anthropic--claude-sonnet-4-5 tag, so invalidation stays scoped to this model.
/models/anthropic--claude-sonnet-4-5public, max-age=300, stale-while-revalidate=3600catalogmodel:anthropic--claude-sonnet-4-5Workers Cache derives the key from this path/query, plus the Worker entrypoint and current Worker version.
export const Route = createFileRoute('/models/$modelSlug')({
headers: () => ({
'Cache-Control': 'public, max-age=300, stale-while-revalidate=3600',
'Cache-Tag': 'catalog,model:anthropic--claude-sonnet-4-5',
}),
})Invalidate this cache tag
await ctx.cache.purge({ tags: ['model:anthropic--claude-sonnet-4-5'] })Use this when one model changes and you do not want to evict the whole catalog.
- Released
- Sep 29, 2025
- Last updated
- Sep 29, 2025
- Context window
- 200K tokens
- Max output
- 64K tokens
- Open weights
- No
- Family
- Claude Sonnet
Starts at
$3
per 1M input tokens
Output
$15
Sellers
6
No cart or checkout in this MVP — pick a provider below and open their docs when you're ready to use it.
Sorted by lowest input price
| Provider | Input / 1M | Output / 1M | Context | |
|---|---|---|---|---|
Requesty anthropic/claude-sonnet-4-5 | $3 | $15 | 1M | Docs |
NEAR AI Cloud anthropic/claude-sonnet-4-5 | $3 | $15.5 | 200K | Docs |
Cloudflare AI Gateway anthropic/claude-sonnet-4-5 | $3 | $15 | 200K | Docs |
Anthropic claude-sonnet-4-5 | $3 | $15 | 1M | Docs |
Perplexity Agent anthropic/claude-sonnet-4-5 | $3 | $15 | 200K | Docs |
AnyAPI anthropic/claude-sonnet-4-5 | Quote | Quote | 200K | Docs |
anthropic/claude-sonnet-5
Claude Sonnet 5
Everyday Claude agent model for coding, planning, browsing, and general work
anthropic/claude-fable-5
Claude Fable 5
Claude model for creative writing, analysis, and controlled agent workflows
anthropic/claude-opus-4-8
Claude Opus 4.8
Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents