# Anthropic: Claude 3.5 Haiku

[Chat](/content/platform/chat?model=anthropic/claude-3.5-haiku/index.html)

Claude 3.5 Haiku features offers enhanced capabilities in speed, coding accuracy, and tool use. Engineered to excel in real-time applications, it delivers quick response times that are essential for dynamic tasks such as chat interactions and immediate coding suggestions.

This makes it highly suitable for environments that demand both speed and precision, such as software development, customer service bots, and data management systems.

by [Anthropic](/content/anthropic/index.html)

## Recent activity on Claude 3.5 Haiku

Tokens processed per day

## Throughput

(tokens/s)

| Providers | Min (tokens/s) | Max (tokens/s) | Avg (tokens/s) |
| --- | --- | --- | --- |
| Amazon Bedrock | 0.95 | 46.92 | 16.69 |
| Google Vertex | 14.03 | 27.22 | 18.65 |

## First Token Latency

(ms)

| Providers | Min (ms) | Max (ms) | Avg (ms) |
| --- | --- | --- | --- |
| Amazon Bedrock | 956 | 19208 | 2526.58 |
| Google Vertex | 1189 | 6198 | 2696.00 |

## Uptime stats for Claude 3.5 Haiku

Uptime stats for Claude 3.5 Haiku across all providers

### Uptime

| Providers | Uptime (%) |
| --- | --- |
| Amazon Bedrock | 100.00% |
| Google Vertex | - |

## Pricing

### Amazon Bedrock
- **Latency**: 2.50 s
- **Throughput**: 25.16 tps
- **Recent uptime**: Apr 30, 2026 6:00 PM
- **Price**:
  - Input: $0.8/ M tokens
  - Output: $4/ M tokens
  - Cache read: $0.08/ M tokens
  - Cache write (5m): $1/ M tokens

### Google Vertex
- **Price**:
  - Input: $0.8/ M tokens
  - Output: $4/ M tokens
  - Cache read: $0.08/ M tokens

## Sample code and API for Claude 3.5 Haiku

ZenMux normalizes requests and responses across providers for you.

```python
from openai import OpenAI

client = OpenAI(
  base_url="https://zenmux.ai/api/v1",
  api_key="<ZENMUX_API_KEY>",
)

# Chat Completion
completion = client.chat.completions.create(
  model="anthropic/claude-3.5-haiku",
  messages=[
    {
      "role": "user",
      "content": "What is the meaning of life?"
    }
  ]
)
print(completion.choices[0].message.content)
```