Claude Haiku 4 5
Provider: vertex ai-anthropic models ·
vertex_ai/claude-haiku-4-5 Pricing per million tokens
| Component | USD per 1M tokens |
|---|---|
| Input | $1.00 |
| Output | $5.00 |
| Cached input (read) | $0.10 |
| Cache write | $1.25 |
💡 With prompt caching, you save up to 90% on cached input tokens — massive for repeated context like system prompts, RAG retrieval, or long conversations.
Monthly cost estimates
Assuming 30% prompt-cache hit rate where available. Adjust for your actual usage.
Small
1M in / 200k out
$1.73
per month
Saves $0.27 via caching
Medium
10M in / 2000k out
$17.30
per month
Saves $2.70 via caching
Large
100M in / 20000k out
$173
per month
Saves $27.00 via caching
Context
- Input window
- 200,000 tokens
- Max output
- 8,192 tokens
Capabilities
- ✅ Vision (image input)
- ✅ Function / tool calling
- ✅ Prompt caching
- ⬜ Web search
- ✅ JSON / response schema
Compare Claude Haiku 4 5 with similar models
Claude 3 5 Haiku
vertex ai-anthropic models
$1.00 in
/ $5.00 out
Claude 3 5 Haiku@20241022
vertex ai-anthropic models
$1.00 in
/ $5.00 out
Claude Haiku 4 5@20251001
vertex ai-anthropic models
$1.00 in
/ $5.00 out
Claude 3 5 Sonnet
vertex ai-anthropic models
$3.00 in
/ $15.00 out
Claude 3 5 Sonnet@20240620
vertex ai-anthropic models
$3.00 in
/ $15.00 out
Claude 3 7 Sonnet@20250219
vertex ai-anthropic models
$3.00 in
/ $15.00 out
Pricing data sourced from LiteLLM and refreshed regularly. Last updated May 20, 2026. Always verify with the provider's official pricing page before making business decisions.