Celon

Claude Haiku 4.5

ChatInput: TextInput: ImageInput: FileReleased Oct 15, 2025

Built by Anthropic · United States · anthropic.com

Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...

How to use

model: "anthropic/claude-haiku-4.5"

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-haiku-4.5",
    "savings_target": 0.4
  }
}

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

Context

200K

Max output

64K

Input $/1M

$1.00

Output $/1M

$5.00

Features

Image inputTool callingJSON

Serving providers

Anthropic

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
142.9
GPQA DiamondPhD-level science questions
71.2%
AIMECompetition mathematics
66.7%
FrontierMathResearch-level mathematics
5.9%
Terminal-BenchAgentic terminal tasks
35.5%
SciCodeScientific code generation
43.3%
ARC-AGI-2Abstract reasoning
4.0%
SimpleQA VerifiedFactual accuracy
5.9%

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

Speed

Loading provider metrics…