Anthropic
Claude Haiku (Bedrock Singapore)
model
claude-haiku-bedrock-sgMidStableVisionStreamingVisionToolsBatchLong contextSingapore
Context
200K
Input / 1M tokens
$1.00
Output / 1M tokens
$5.00
Weighted tokens formula
0.5× provider × 4× tier
About this model
Claude Haiku (Bedrock Singapore)
Claude Haiku via AWS Bedrock in Singapore. Fast Haiku with PDPA residency.
Training cutoff
2024-11
Parameters
Not disclosed
Best for
Use cases
- ✓High-throughput Singapore chat
- ✓PDPA real-time UX
Strengths
What it does well
- ●Sub-second TTFT in SG
- ●Same Haiku pricing
Limitations
Know the trade-offs
- !Reasoning trails Sonnet
- !Bedrock feature gaps
Code example
Chat completion with Claude Haiku (Bedrock Singapore)
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-bedrock-sg",
messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)Weighted tokens
weighted_tokens = raw_tokens × 0.5 (provider) × 4 (tier)
Pro plan: 20M weighted tokens/month. Combined multiplier 2×: 10,000,000 raw tokens available.
Alternatives
Similar models in our catalog
Workloads that fit Claude Haiku (Bedrock Singapore) often fit these too. Compare benchmarks and pricing before locking in a default.