Model intelligence
Claude Sonnet 4.6
Anthropic's current Sonnet model. Documented by Anthropic as the best combination of speed and intelligence.
- Snapshot date
- Data not yet verified.
- Context window
- 1,000,000 tokenssrc
- Max output
- 64,000 tokenssrc
- Modality
- text-in, image-in, text-outsrc
Data freshness: last checked 9 d ago · updated 2026-05-20
Verification
8 of 10 tracked fields verified against a primary source.
- API identifiersverified
- Release / snapshot datenot yet verified
- Context windowverified
- Max output tokensverified
- Modalityverified
- Knowledge cutoffverified
- Featuresverified
- Lifecycleverified
- Pricingverified
- Benchmarksnot yet verified
Data freshness: last checked 9 d ago · updated 2026-05-20
Verification checklist
8 of 10 tracked fields verified against a primary source
Each row reflects the actual state on the record — no checkmark is asserted without isVerified() returning true.
- Verified
API identifiers (canonical / alias)
- Verified
Context window
- Verified
Max output tokens
- Verified
Modality channels
- Verified
Knowledge cutoff
- Verified
Features (extended thinking / tool use / vision …)
- Verified
Lifecycle (active / deprecated / retired)
- Missing
Release date
- Missing
Snapshot date
- Verified
Pricing rows
7 pricing rows sourced
Data gaps
Fields not yet verified
These fields are intentionally null until verified against a primary source. They are not estimated.
Benchmark scores
No third-party benchmark scores have been verified for any model on this site — see the benchmark-limitations guide for why.
Infrastructure (regions / latency / uptime)
Infrastructure fields are intentionally null until a durable measurement source is wired. See the inference-infrastructure guide.
How a value moves from this list to a verified row — see source verification methodology.
Reference
API identifiers
Pinned snapshot IDs as listed by the provider.
- Canonical
- claude-sonnet-4-6
- Alias
- claude-sonnet-4-6
- AWS Bedrock
- anthropic.claude-sonnet-4-6
- Vertex AI
- claude-sonnet-4-6
API pricing
First-party API pricing references
Per-unit rates published by Anthropic for its own first-party API. Each row is a source-backed reference, not a live quote. Where Anthropic does not run a paid first-party API for this model, the table renders the unverified-data label and any hosted-provider rates appear below.
Pricing is volatile and may change after retrieval. Treat prices as source-backed references, not live quotes.
Capability
Benchmarks
Benchmark scores are only published once verified against a primary source. WebmasterID Models does not republish provider-reported scores without an independent reference.
Infrastructure
Inference infrastructure
Regions, latency, and uptime where independently verified.
Regions
Data not yet verified.
Avg latency (ms)
Data not yet verified.
Uptime (%)
Data not yet verified.
Compare
Related comparisons
Continue
Related models
Other models in the catalogue — same provider first, then the rest of the graph.
Entity graph
Provider context
- Provider page: /providers/anthropic
- Pricing rows for this provider: /pricing?provider=anthropic
- Sources for this provider: /sources?provider=anthropic
- Vendor-status observation API: /api/status/anthropic
Documentation example
Calling Claude Sonnet 4.6 via the Anthropic Messages API
Shape of a minimal Messages API request using the verified canonical model ID. See the source for the full request schema, headers, streaming, and tool-use details.
curl
curl https://api.anthropic.com/v1/messages \
-H "x-api-key: $ANTHROPIC_API_KEY" \
-H "anthropic-version: 2023-06-01" \
-H "content-type: application/json" \
-d '{
"model": "claude-sonnet-4-6",
"max_tokens": 1024,
"messages": [
{ "role": "user", "content": "Hello, Claude Sonnet 4.6." }
]
}'TypeScript (@anthropic-ai/sdk)
import Anthropic from "@anthropic-ai/sdk";
const client = new Anthropic();
const response = await client.messages.create({
model: "claude-sonnet-4-6",
max_tokens: 1024,
messages: [{ role: "user", content: "Hello, Claude Sonnet 4.6." }],
});Shown for reference — not a performance recommendation. Refer to the provider's documentation for current request shape, headers, and limits.
Sources
- Official docsRetrieved 2026-05-20FreshAnthropic — Models overview
Anthropic's models overview page (legacy section), including the Claude Opus 4 row.
- Official pricingRetrieved 2026-05-20FreshAnthropic — Pricing
Anthropic's pricing reference (model pricing, prompt caching multipliers, batch API pricing).
Verification queue
Next review for this entity targets re-checking pricing against official provider documentation and confirming lifecycle state. Cadence per field type lives in /docs.