AnthropicVerified Active: September 18, 2026
Claude Haiku 4.5API Pricing & Specifications
Near-instantaneous lightweight intelligence for high-frequency extraction, classification, and chat.
📊 Core Specifications & Pricing Rates
Standard Input
$1.00 / 1M tokens
Standard Output
$5.00 / 1M tokens
Cached Input
$0.1000 / 1M tokens
Cache Write
$1.25 / 1M tokens
Context Window
200K (200,000 tokens)
Max Output Tokens
64,000 tokens
Supported Capabilities:✓ Vision✓ Function Calling / Tools✓ JSON ModeStandard Inference
📦 Asynchronous Batch API Supported: Official provider documentation offers a 50% discount on non-streaming 24h batch requests.
Live Workload Cost Estimator: Claude Haiku 4.5
Adjust token volumes to simulate your exact monthly API bill.
Estimated 60% repeated context
Estimated Total Monthly Cost
Compare All Models in Calculator→$67.25/ month
$0.00269 per API request(Saves $20.25/mo with caching)
💡 Estimated Monthly Workload Scenarios
Customer Support Auto-Responder
$220.00/mo100,000 queries (1,200 input, 200 output)
100,000 requests • 1200 in / 200 out
⚖️ Head-to-Head Competitor Comparisons
Claude Haiku 4.5 vs. GPT-5.1 Mini
Haiku 4.5 has 64K max output and superior formatting adherence, while GPT-5.1 Mini offers lower base rates.
Haiku 4.5 is $1/$5 vs $0.25/$2View GPT-5.1 Mini →
📜 Historical Price Changes & Updates
2026-07-10
Claude Haiku 4.5 updated with 64K max output tokens and 90% cache discount.
🔗 Verified Primary Sources
All pricing, token limits, and capabilities are cross-checked against official provider documentation and live API endpoints.