# claude-haiku-4-5 — API, Pricing & Context Window | Vivgrid

> Source: https://vivgrid.com/docs/models/claude-haiku-4-5

claude-haiku-4-5 on Vivgrid: Anthropic's fast, low-cost Haiku model with a 200K context window, Messages API, and geo-distributed acceleration.

`claude-haiku-4-5` is Anthropic's prior-generation Haiku model, designed for high-volume, latency-sensitive workloads that still benefit from Claude's quality. It offers a **200K-token context window** on the **Messages API**. For new projects, [`claude-haiku-5-5`](/docs/models/claude-haiku-5-5) is the latest Haiku release, with a 1M-token context window at a lower per-token price.

Vivgrid accelerates `claude-haiku-4-5` across **AMER and EMEA**, making it an excellent default for real-time assistants and large-scale agent fleets.

## Specifications

| Field | Value |
| --- | --- |
| Provider | Anthropic |
| Model ID | `claude-haiku-4-5` |
| Best for | Coding |
| Available on | Vibe coding |
| Context window | 200,000 tokens |
| Max output | 64,000 tokens |
| Modalities | Text, Image |
| Tool / function calling | Yes |
| Knowledge cutoff | 2025-02 |
| Acceleration | Geo-distributed — AMER, EMEA |

## Pricing

Pricing in USD per 1M tokens.

| Input | Cached input | Output |
| --- | --- | --- |
| $1.00 | $0.10 | $5.00 |

### What one request costs

The rates above applied to a 20K-token prompt with a 2K-token reply — a typical single agent turn, small enough that every request is billed at the base rate.

| Request | Cost |
| --- | --- |
| Cold prompt, nothing cached | $0.0300 |
| Warm prompt, 90% of the input served from cache | $0.0138 |


## API surfaces

The Vivgrid Console catalogs `claude-haiku-4-5` on one surface, all behind the same API key. The endpoint shown is the one the Console previews for that surface.

| Surface | Primary endpoint | Use it for |
| --- | --- | --- |
| Vibe coding | `/messages` | Coding CLIs and IDE agents that drive the model themselves — point the tool at Vivgrid and keep your own loop. |

## Quick start

Get an API key from the Vivgrid Console (https://console.vivgrid.com), then call `claude-haiku-4-5` directly.

```bash
curl https://api.vivgrid.com/v1/messages \
  -H "Authorization: Bearer $VIVGRID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-haiku-4-5",
    "max_tokens": 1024,
    "messages": [
      { "role": "user", "content": "Say hello in English, Chinese and Spanish." }
    ],
    "stream": true
  }'
```


## Ideal use cases

- Real-time chat and assistant experiences
- High-throughput classification and extraction
- Cost-sensitive tool-calling agents
- Fast first-pass steps in larger agent pipelines

## Related models

- [claude-haiku-5-5](/docs/models/claude-haiku-5-5) — the latest Haiku release
- [claude-sonnet-4-6](/docs/models/claude-sonnet-4-6) — a step up in capability
- [claude-opus-5-5](/docs/models/claude-opus-5-5) — the latest frontier Opus model