Anthropic
Claude Haiku 4.5
model
claude-haiku-4-5MidStabilVisionStreamingVisionToolsBatchLong contextUnited States
Konteks
200K
Input / 1M token
$1.00
Output / 1M token
$5.00
Rumus weighted token
1× provider × 4× tier
Tentang model ini
Claude Haiku 4.5
Claude Haiku 4.5 — Anthropic's fastest + cheapest. Speed-optimized for high-throughput chat, classification, and real-time UX while preserving Anthropic's safety + alignment tuning.
Rilis
2024-12
Batas data latih
2024-11
Parameter
Not disclosed
Paling cocok untuk
Kasus penggunaan
- ✓High-volume customer chat
- ✓Classification + routing
- ✓Real-time voice agent backbone
- ✓Cheap-tier model for cost-sensitive tiers
Kelebihan
Yang dikerjakan dengan baik
- ●Sub-second TTFT typical
- ●Strong instruction-following for the size class
- ●200K context window
- ●Same safety tuning as Sonnet/Opus
Keterbatasan
Pahami trade-off-nya
- !Reasoning depth limited vs Sonnet
- !Code generation trails Qwen 2.5 Coder
- !Long-document comprehension weaker on tasks past 50K tokens
Contoh kode
Chat completion dengan Claude Haiku 4.5
from openai import OpenAI
client = OpenAI(
base_url="https://api.anoman.io/v1",
api_key="anm-sk-..."
)
response = client.chat.completions.create(
model="claude-haiku-4-5",
messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)Weighted token
weighted_tokens = raw_tokens × 1 (provider) × 4 (tier)
Paket Pro: 20 jt weighted token/bulan. Multiplier gabungan 4×: 5,000,000 raw token tersedia.
Alternatif
Model serupa di katalog kami
Beban kerja yang cocok dengan Claude Haiku 4.5 sering cocok dengan ini juga. Bandingkan benchmark dan harga sebelum menetapkan default.