Claude 3.5 Haiku
ActiveFast, low-cost model with stronger capabilities than Claude 3 Haiku.
Overview
Claude 3.5 Haiku improves on Claude 3 Haiku with significantly better coding and instruction-following at competitive latency and cost.
History
Claude 3.5 Haiku became available via the Anthropic API on 2024-11-04.
Training & availability
Training data has a knowledge cutoff of 2024-07-31 — information about events after that date is unlikely to appear in the model's responses. Anthropic has not released the underlying model weights — access is via their hosted API only.
Capabilities
-
Context window: 200K tokens.
-
Max output: 8K tokens.
-
Input modalities: text, image.
Recommended for: vision, agentic, long-context.
Limitations
- The knowledge cutoff is 20 months old — this model will not know about recent events, releases, or API changes.
Pricing
- Input: $0.8000 per 1M tokens
- Output: $4.0000 per 1M tokens
Use the cost calculator above to estimate monthly spend for your workload.
Quick start
Minimal example using the anthropic API. Copy, paste, replace the key.
from anthropic import Anthropic
client = Anthropic(api_key="sk-ant-...")
resp = client.messages.create(
model="claude-3-5-haiku",
max_tokens=1024,
messages=[{"role": "user", "content": "Explain quantum computing in one sentence."}],
)
print(resp.content[0].text)Cost calculator
Estimate your monthly bill. Presets are typical workload sizes.
Integrations & tooling support
- Tool calling
- Supported
- Structured outputs
- Supported
Price vs quality
Standard pricing band. Quality tier pending more benchmark coverage.
- Quality percentile
- —
- Effective price
- $3.2/1M
- Pricing breakdown
- $0.8/1M in
$4/1M out
Community ratings
Rate Claude 3.5 Haiku
Sign in to rate and review.
Comments
Sign in to leave a comment.