Claude Haiku 4.5
Claude Haiku 4.5Alternatives?
CheaperClaude Haiku 5.5max×10.4-23%$0.21Remove sampling parameters+5
BetterGPT-5.6 Lunamedium+36%-94%$0.016
OpenGLM 5.3 Flashmax×8.4same$0.28Defaults to max · Self-hosted+4
CheaperMuse Glimmer 30BhighOpen×3.3-79%$0.058Context: 200K → 131K
CheaperMiMo v2.6 ProthinkingOpen×3-52%$0.13Pass back reasoning_content+3Claude Haiku 5.5max×10.4-23%$0.21Remove sampling parameters+5Muse Glimmer 30BhighOpen×3.3-79%$0.058Context: 200K → 131KGPT-5.6 Lunamax×3.2-36%$0.18MiMo v2.6 ProthinkingOpen×3-52%$0.13Pass back reasoning_content+3GPT-6 Lunamax×2.6-75%$0.068Function calling only with none · Chat Completions+3GPT-5.6 Lunamedium+36%-94%$0.016MiMo v2.5 ProthinkingOpen+55%-80%$0.054No image inputMuse Glimmer 30BhighOpen×3.3-79%$0.058Context: 200K → 131KGPT-6 Lunamax×2.6-75%$0.068Function calling only with none · Chat Completions+3MiMo v2.6 ProthinkingOpen×3-52%$0.13Pass back reasoning_content+3GLM 5.3 FlashmaxOpen×8.4same$0.28Defaults to max · Self-hosted+4GLM 5.3maxOpen×7.9+625%$2.01No image input+4
Kimi K3maxOpen×6.3+623%$2.00Sampling parameters are fixed+3
Qwen3.8 27BxhighOpen×3.5+264%$1.01max_tokens range · QwenCloud+4Muse Glimmer 30BhighOpen×3.3-79%$0.058Context: 200K → 131KClaude Sonnet 5.5max×12.3+1,873%$5.46No forced tool use+5Claude Fable 5.1max×11.6+2,656%$7.63Replace forced tool_choice+5Claude Opus 5.5max×10.9+2,061%$5.98No forced tool use+5Claude Fable 5max×10.5+3,059%$8.75Claude Haiku 5.5max×10.4-23%$0.21Remove sampling parameters+5Claude Opus 5medium×9.2+691%$2.19Claude Sonnet 5max×9+1,739%$5.09Claude Opus 4.8max×7.5+1,374%$4.08All Anthropic models →History
3 versionsBenchmarks
in Chat & KnowledgeFAQ
How much does Claude Haiku 4.5 cost?›
$1 per 1M input tokens and $5 per 1M output tokens; cached input $0.10 per 1M. A typical benchmark task costs about $0.28 at default effort.
Is Claude Haiku 4.5 free to use?›
There is no free API; the cheapest paid price is $1 per 1M input tokens.
How good is Claude Haiku 4.5, and what is it best at?›
#185 of 334 in Chat & Knowledge, #75 of 132 in Coding, #90 of 133 in Agents & Tool Use, #80 of 195 in Writing & Language, #98 of 124 in Vision & Documents.
Is Claude Haiku 4.5 better than K2 Horizon 375B A23B?›
On MLCR-AA, Claude Haiku 4.5 scores 6.1 vs 6.7 — about the same.
How can I use Claude Haiku 4.5?›
Through the API of Amazon Bedrock, Anthropic, Azure, DeepInfra, Google.
What is the context window of Claude Haiku 4.5?›
200K tokens, with up to 64K output tokens.
When was Claude Haiku 4.5 released? Is there a newer version?›
Released 2025-10-15. It has been superseded by Claude Haiku 5.5.
Is Claude Haiku 4.5 open source?›
No, Claude Haiku 4.5 is a closed model available through an API. The closest open-weights option here is GLM 5.3 Flash.
Can Claude Haiku 4.5 read images?›
It accepts text and images, PDF files as input.
What is Claude Haiku 4.5?›
Claude Haiku 4.5 is a closed language model from Anthropic, released Oct 2025.
What are the best alternatives to Claude Haiku 4.5?›
Claude Haiku 5.5 (cheaper), GPT-5.6 Luna (better), GLM 5.3 Flash (open weights).