Models Model details

Anthropic

Anthropic: Claude Haiku 4.5 (batch)

anthropic/claude-haiku-4.5:batch

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 across reasoning, coding, and computer-use tasks, Haiku 4.5 brings frontier-level capability to real-time and high-volume applications. It introduces extended thinking to the Haiku line; enabling controllable reasoning depth, summarized or interleaved thought output, and tool-assisted workflows with full support for coding, bash, web search, and computer-use tools. Scoring >73% on SWE-bench Verified, Haiku 4.5 ranks among the world’s best coding models while maintaining exceptional responsiveness for sub-agents, parallelized execution, and scaled deployment.

Input
$0.5

/ 1M tokens

Output
$2.5

/ 1M tokens

Context window
200K

tokens

Limits

Context

200,000

tokens

Max output

64,000

32% of the context window

Model facts

Author

Anthropic

Tokenizer

Claude

Modality

Text + Image + File -> Text

Created

Oct 15, 2025

Publication status

Hugging Face: unavailableLicense: not publishedParameter count: not published

Modalities

Input · TextInput · ImageInput · FileOutput · Text

Generation controls

Include reasoningMax tokensReasoningResponse formatStopStructured outputsTemperatureTool choiceToolsTop kTop p

Capability scores

8
Agentic index

Better than 32% of models compared

43.9
Coding index

Better than 40% of models compared

16.9
Intelligence index

Better than 43% of models compared

Creative tasks

Category performance

ASCII art
Top 74%

1142 Elo

49.3% win

Data visualization
Top 78%

1124 Elo

45.6% win

Websites
Top 74%

1124 Elo

45.1% win

Code
Top 77%

1116 Elo

44.9% win

Games
Top 73%

1100 Elo

44.7% win

UI components
Top 76%

1099 Elo

42.6% win

3D
Top 77%

1073 Elo

41.1% win

SVG
Top 90%

1025 Elo

39.1% win