Claude Haiku 4.5

by Anthropic · anthropic/claude-haiku-4.5

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...

Input / 1M tokens
$1.00
Output / 1M tokens
$5.00
Context
200K

Specs

Input price$1.00 / 1M tokens
Output price$5.00 / 1M tokens
Cached input$0.10 / 1M tokens
Context window200K tokens
Max output64K tokens
Readstext, image, file
Writestext
Tool callingYes
ReasoningYes
ListedOct 15, 2025

List prices in USD, updated Oct 30, 2026. Providers may charge differently.

Providers

8 providers serve this model, as of Oct 30, 2026, 18:12 UTC.

Providers serving this model, sorted by price
ProviderContextMax outputInput / 1MOutput / 1MCache read / 1MUptime (30 min)Latency (median)Throughput (median)SupportsStatus
Amazon Bedrock200K64K$1.00$5.00$0.10100%737 ms88 tok/sNormal
Anthropic200K64K$1.00$5.00$0.10100%453 ms80 tok/sNormal
Azure200K64K$1.00$5.00$0.10100%544 ms67 tok/sNormal
Google200K64K$1.00$5.00$0.10100%667 ms85 tok/sNormal
Amazon Bedrock200K64K$1.10$5.50$0.11—527 ms91 tok/sNormal
Amazon Bedrock200K64K$1.10$5.50$0.11100%477 ms125 tok/sNormal
GoogleFastest200K64K$1.10$5.50$0.11—394 ms190 tok/sNormal
Google200K64K$1.10$5.50$0.11—298 ms95 tok/sNormal

"Cheapest" is the lowest input plus output price; "Fastest" the highest median throughput. Columns empty for every provider are not shown.