Claude Haiku 4.5
Claude Haiku 4.5Alternatives?
CheaperGemini 3.8 Flashunstated+7%-25%*$0.75 / $3.75Sampling parameters are ignored+1BetterClaude Sonnet 4.5thinking+3%+142%$0.56
OpenKimi K3unstated+6%+200%$3 / $15Sampling parameters are fixed+3CheaperGemini 3 Flash Previewunstated+7%-44%$0.50 / $3CheaperGemini 3.6 Flashunstated+7%-25%*$0.75 / $3.75Gemini 3.8 Flashunstated+7%-25%*$0.75 / $3.75Sampling parameters are ignored+1Gemini 3 Flash Previewunstated+7%-44%$0.50 / $3Gemini 3.6 Flashunstated+7%-25%*$0.75 / $3.75
MiniMax M3unstatedOpen+5%-74%$0.30 / $1.20No strict JSON+1
Qwen 3.5 Plusunstated+5%-87%$0.12 / $0.69Claude Sonnet 4.5thinking+3%+142%$0.56Claude Fable 5unstated+9%+900%$10 / $50Claude Fable 5.1unstated+9%+900%$10 / $50Replace forced tool_choice+5Gemini 4 Argonunstated+9%+100%*$2 / $10Synchronous output stops at 65,536+2Gemini 3.1 Pro Previewunstated+8%+125%$2 / $12Cannot use both thinking controlsKimi K3unstatedOpen+6%+200%$3 / $15Sampling parameters are fixed+3MiniMax M3unstatedOpen+5%-74%$0.30 / $1.20No strict JSON+1
GLM 5.3unstatedOpen+4%+7%$1.40 / $4.40No image input+4Kimi K2.6unstatedOpen+4%-14%$0.95 / $4GLM 5.1unstatedOpen+4%+7%$1.40 / $4.40No image inputClaude Fable 5unstated+9%—$10 / $50Claude Fable 5.1unstated+9%—$10 / $50Replace forced tool_choice+5Claude Opus 5unstated+7%—$5 / $25Claude Opus 4.6thinking+5%—$5 / $25Claude Opus 4.7unstated+5%—$5 / $25Claude Opus 4.5thinking+4%—$5 / $25Claude Sonnet 4.5thinking+3%+142%$0.56Claude Sonnet 5unstated+3%—$2 / $10All Anthropic models →Benchmarks
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 $0.23 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?›
#187 of 336 in Chat & Knowledge, #77 of 134 in Coding, #92 of 135 in Agents & Tool Use, #85 of 197 in Writing & Language, #99 of 125 in Vision & Documents.
Is Claude Haiku 4.5 better than Kimi K2 0711?›
On Vals LegalBench, Claude Haiku 4.5 scores 81.2 vs 81.5 — 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 It has been superseded by Claude Haiku 5.5.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 Kimi K3.
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?›
Gemini 3.8 Flash (cheaper), Claude Sonnet 4.5 (better), Kimi K3 (open weights).