chooseaimodel
← All models

Claude 3 Haiku vs Claude Haiku 4.5

List-price comparison · Claude 3 Haiku details · Claude Haiku 4.5 details

For a typical workload (100,000 requests / mo), Claude 3 Haiku costs 75% less $80.00/mo vs $320.00/mo.

 Claude 3 HaikuClaude Haiku 4.5
Input / 1M tokens$0.250$1.00
Output / 1M tokens$1.25$5.00
Typical request (1,200 in + 400 out)$0.0008$0.0032
Context window200k tokens200k tokens
Max output4,096 tokens64k tokens
TierBalancedFlash
ProviderAnthropicAnthropic

Projected monthly cost

Rows open both models in the calculator — adjust volume and token counts there.

Claude 3 Haiku

Auto-synced from OpenRouter — no editorial write-up yet.

Claude Haiku 4.5

Very low latency for high-volume, simple tasks — classification, short summaries, and lightweight chat where response time matters more than depth.

Noticeably weaker on multi-step reasoning and long-context synthesis; pairing with a larger model for escalation is common.

More comparisons

Vendor list rates · per-request examples assume 1,200 input + 400 output tokens.