Anthropic: Claude Sonnet 4.6, Anthropic — route, pricing & source
Anthropic Sonnet model focused on speed, intelligence, coding, and cost balance.
Claude APIhighLast checked: May 13, 2026
Input
$3.00 / 1M
/ 1M tokens
Output
$15.00 / 1M
/ 1M tokens
Cached input
$0.3000 / 1M
/ 1M tokens
Cache write
$3.75 / 1M
/ 1M tokens
Context and limits
Context window
1M
Max output
Unknown
Input modalities
text, image
Output modalities
text
Weight access
Closed
Availability
Official API
Capability flags
VisionToolsReasoningLong context
From source metadata + verification fields — confirm provider docs before production.
Benchmarks
- LMArena Text Arenaoverall · official_benchmark_api1,466Independent
Rank: 23 | Votes: 17127 | 95% CI: 1460.8-1471.0 | Published: 2026-05-07 | Model license label in dataset: Proprietary
- LMArena WebDev Arenaoverall · official_benchmark_api1,524Independent
Rank: 6 | Votes: 9434 | 95% CI: 1516.6-1531.8 | Published: 2026-05-07 | Model license label in dataset: Proprietary
- LMArena Vision Arenaoverall · official_benchmark_api1,272Independent
Rank: 12 | Votes: 6642 | 95% CI: 1262.9-1280.4 | Published: 2026-05-07 | Model license label in dataset: Proprietary
Access and license
Official API
Yes
Open weights
No
Self-hostable
No
License
Closed · API onlyNo public weights: use through a vendor’s cloud API or product. “Proprietary” means the creator does not distribute the trained model weights for self-hosting.
Example costs
Scenario: 1K input + 300 output tokens / request
10,000 requests
$75.00
100,000 requests
$750.00
1,000,000 requests
$7,500.00
Cheaper alternatives
Lower-cost models for the same scenario
Source
Source
Anthropic public model and pricing docs
Confidence
high
Route
Claude API
Last checked
May 13, 2026
Source notes
- Official sources found Claude Sonnet 4.6, not Claude Sonnet 4.7.
- Sonnet 4.6 has 1M context support according to Anthropic public docs.
- Includes Hugging Face benchmark data only when the dataset is public, ungated, allowlisted, and matched by reviewed aliases.
