Claude Sonnet 4 6

Chat

Built by Anthropic · United States · anthropic.com

Anthropic chat model.

How to use

model: "anthropic/claude-sonnet-4-6"

Cap quality here and save

Hard questions go to this model, easy ones drop to something cheaper. Set a savings target (0–0.8) and the router tunes itself until realized savings converge on it.

{
  "model": "celon/auto",
  "celon": {
    "anchor": "anthropic/claude-sonnet-4-6",
    "savings_target": 0.4
  }
}

Naming a model directly gets you that model — savings controls don't apply.

Context

—

Max output

—

Input $/1M

$3.00

Output $/1M

$15.00

Features

Tool callingJSON

Serving providers

DeepInfra

Providers

Price, latency, and uptime per provider serving this model. Celon routes each request to the fastest and cheapest of them. Click a row for regions and data policies.

Loading provider metrics…

Performance

Benchmark quality scores, and measured speed per provider.

Quality

Epoch Capabilities IndexComposite over 50+ benchmarks

153.2

GPQA DiamondPhD-level science questions

87.4%

AIMECompetition mathematics

85.8%

FrontierMathResearch-level mathematics

32.4%

SWE-bench VerifiedReal GitHub issue resolution

75.2%

Terminal-BenchAgentic terminal tasks

53.4%

SciCodeScientific code generation

46.8%

ARC-AGI-2Abstract reasoning

60.4%

SimpleQA VerifiedFactual accuracy

29.0%

At each model's best reasoning effort. Benchmarks it wasn't run on are omitted.

Speed

Loading provider metrics…