# Claude Haiku 5.5 API pricing

ANTHROPIC CLAUDE / TEXT

> Claude Haiku 5.5 via one OpenAI-compatible key: $0.09 in / $0.42 out per 1M tokens, from $0.02 / $0.10 on Route 2. Model ID claude-haiku-5-5.

From $0.02 in / $0.10 out per 1M tokens on Route 2 · main ID $0.09 in / $0.42 out

Claude Haiku 5.5 costs $0.09 per 1M input tokens and $0.42 per 1M output tokens (cached input $0.01). Other context tiers are listed in the price table. The lowest-priced route, Route 2 (`claude-haiku-5-5-2`), costs $0.02 in / $0.10 out. Call it with model ID `claude-haiku-5-5` at `https://api.outrun.to/v1` using one prepaid Outrun key. Prices as of October 30, 2026.

`claude-haiku-5-5`OpenAI compatibleVision[2 routes](https://outrun.to/model/claude-haiku-5-5#routes)

USD / 1M TOKENS

## How much does Claude Haiku 5.5 cost per 1M tokens?

[Get a key ↗](https://outrun.to/overview)

Main ID · up to 100k tokens

| Token type | Outrun |
| --- | --- |
| Input | **$0.09** |
| Cached input | **$0.01** |
| Cache write | **$0.11** |
| Cache write · 1 hour | **$0.17** |
| Output | **$0.42** |

Main ID · over 100k tokens

| Token type | Outrun |
| --- | --- |
| Input | **$0.42** |
| Cached input | **$0.05** |
| Cache write | **$0.53** |
| Cache write · 1 hour | **$0.84** |
| Output | **$2.10** |

Route 2 · Standard

| Token type | Outrun |
| --- | --- |
| Input | **$0.02** |
| Cached input | **$0.01** |
| Cache write | **$0.03** |
| Cache write · 1 hour | **$0.04** |
| Output | **$0.10** |

Billed prices, rounded up to the cent. Prices as of October 30, 2026.

## Which Claude Haiku 5.5 routes can I use?

Claude Haiku 5.5 has 2 model IDs. Each route is its own ID with its own prices and setup; your key, base URL and request format stay the same. The lowest-priced route is Route 2 (`claude-haiku-5-5-2`). The table shows each route's price and setup values.

| Model ID | Input | Output | Cached input | Setup |
| --- | --- | --- | --- | --- |
| Main ID `claude-haiku-5-5` | $0.09 | $0.42 | $0.01 | Tools: Yes · Streaming: Yes · Reasoning: Yes · Structured output: Yes · Image input: Yes · Context: 1,000,000 · Max output: 128,000 |
| Route 2 of Claude Haiku 5.5: `claude-haiku-5-5-2` Route 2 | $0.02 | $0.10 | $0.01 | Tools: Yes · Streaming: Yes · Reasoning: Yes · Structured output: Yes · Image input: Yes · Context: 1,000,000 · Max output: 128,000 |

Context window

1,000,000 tokens

Max output

128,000 tokens

Input

Text + images

## What is Claude Haiku 5.5?

Claude Haiku 5.5 is a text model in the Outrun catalog. Its developer describes it for classification, extraction, routing and high-volume tasks. The standard rate is $0.09 in / $0.42 out per 1M tokens. It has 2 route IDs with their own prices; compare them above.

## What are the Claude Haiku 5.5 model details?

| Model detail | Value |
| --- | --- |
| Developer | Anthropic |
| Kind | Text |
| Developer context | 1,000,000 tokens |
| Developer max output | 128,000 tokens |
| Developer input | Text, Images |

## How do I call Claude Haiku 5.5?

Use your Outrun key and the exact model ID. Requests use prepaid USD credit.

cURL

```
curl https://api.outrun.to/v1/chat/completions \
  -H "Authorization: Bearer $OUTRUN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "claude-haiku-5-5",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "max_tokens": 8192
}'
```

Python · OpenAI SDK

```
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.outrun.to/v1",
    api_key=os.environ["OUTRUN_API_KEY"],
)
reply = client.chat.completions.create(
    model="claude-haiku-5-5",
    messages=[{"role": "user", "content": "Hello!"}],
    max_tokens=8192,
)
print(reply.choices[0].message.content)
```

## Which tools work with Claude Haiku 5.5?

Any client that accepts an OpenAI-compatible base URL and a model ID can use `claude-haiku-5-5`. Setup guides: [Claude Code (Claude models)](https://outrun.to/docs/setup/claude), [Cline (OpenAI Compatible)](https://outrun.to/docs/setup/cline), [OpenCode](https://outrun.to/docs/setup/opencode), [SillyTavern](https://outrun.to/docs/setup/sillytavern), [LiteLLM](https://outrun.to/docs/setup/litellm).

### Main ID · `claude-haiku-5-5`

Use these setup values for this model ID. Recommended output settings can be lower than the route maximum.

| Set this value | Value |
| --- | --- |
| API format | `OpenAI compatible` |
| Base URL | `https://api.outrun.to/v1` |
| Model ID | `claude-haiku-5-5` |
| Context window | `1,000,000` |
| Max output setting | `8,192` |
| Temperature | `1` |
| Streaming | `Yes` |
| Image support | `Yes` |
| R1 format | `No` |
| Include max tokens | `Yes` |
| Reasoning override | `No` |
| Prompt caching setting | `No` |

| Capability | Supported |
| --- | --- |
| Tool calling | Yes |
| Streaming | Yes |
| Reasoning | Yes |
| Structured output | Yes |
| Parallel tools | Yes |
| Image input | Yes |
| Roo Code ready | Yes |

### Route 2 · `claude-haiku-5-5-2`

Use these setup values for this model ID. Recommended output settings can be lower than the route maximum.

| Set this value | Value |
| --- | --- |
| API format | `OpenAI compatible` |
| Base URL | `https://api.outrun.to/v1` |
| Model ID | `claude-haiku-5-5-2` |
| Context window | `1,000,000` |
| Max output setting | `8,192` |
| Temperature | `1` |
| Streaming | `Yes` |
| Image support | `Yes` |
| R1 format | `No` |
| Include max tokens | `Yes` |
| Reasoning override | `No` |
| Prompt caching setting | `No` |

| Capability | Supported |
| --- | --- |
| Tool calling | Yes |
| Streaming | Yes |
| Reasoning | Yes |
| Structured output | Yes |
| Parallel tools | Yes |
| Image input | Yes |
| Roo Code ready | Yes |

## How does Claude Haiku 5.5 compare on cost?

| Model | Input / output | 1,000 chat turns |
| --- | --- | --- |
| [Claude Haiku 5.5](https://outrun.to/model/claude-haiku-5-5) This model | $0.09 / $0.42 | $0.22 |
| [`claude-haiku-5-5-2`](https://outrun.to/model/claude-haiku-5-5#route-2) Route 2 | $0.02 / $0.10 | $0.05 |
| [Claude Sonnet 5.5](https://outrun.to/model/claude-sonnet-5-5) | $0.49 / $2.45 | $1.23 |
| [`claude-sonnet-5-5-2`](https://outrun.to/model/claude-sonnet-5-5#route-2) Route 2 | $0.40 / $2.00 | $1.00 |
| [Claude Sonnet 5](https://outrun.to/model/claude-sonnet-5) | $1.12 / $5.60 | $2.80 |
| [`claude-sonnet-5-2`](https://outrun.to/model/claude-sonnet-5#route-2) Route 2 | $0.40 / $2.00 | $1.00 |
| [Claude Opus 5.5](https://outrun.to/model/claude-opus-5-5) | $2.24 / $11.20 | $5.60 |
| [`claude-opus-5-5-2`](https://outrun.to/model/claude-opus-5-5#route-2) Route 2 | $0.80 / $4.00 | $2.00 |
| [Claude Opus 5](https://outrun.to/model/claude-opus-5) | $3.15 / $15.75 | $7.88 |
| [`claude-opus-5-2`](https://outrun.to/model/claude-opus-5#route-2) Route 2 | $1.00 / $5.00 | $2.50 |
| [Claude Fable 5](https://outrun.to/model/claude-fable-5) | $5.60 / $28.00 | $14.00 |
| [`claude-fable-5-2`](https://outrun.to/model/claude-fable-5#route-2) Route 2 | $2.00 / $10.00 | $5.00 |
| [Claude Fable 5.1](https://outrun.to/model/claude-fable-5-1) | $6.30 / $31.50 | $15.75 |
| [`claude-fable-5-1-2`](https://outrun.to/model/claude-fable-5-1#route-2) Route 2 | $2.00 / $10.00 | $5.00 |

Assumes 1,000 input + 300 output tokens per turn, repeated 1,000 times, at standard-tier rates without caching. Input / output shown per 1M tokens, rounded up to the cent.

## Which similar models can I try?

[Anthropic Claude Claude Sonnet 5.5 $0.49 in / $2.45 out View model ↗](https://outrun.to/model/claude-sonnet-5-5)[Anthropic Claude Claude Sonnet 5 $1.12 in / $5.60 out View model ↗](https://outrun.to/model/claude-sonnet-5)[Anthropic Claude Claude Opus 5.5 $2.24 in / $11.20 out View model ↗](https://outrun.to/model/claude-opus-5-5)

## Common questions about Claude Haiku 5.5

### How much does the Claude Haiku 5.5 API cost?

Claude Haiku 5.5 costs $0.09 per 1M input tokens and $0.42 per 1M output tokens (cached input $0.01). Other context tiers are listed in the price table. The lowest-priced route, Route 2 (`claude-haiku-5-5-2`), costs $0.02 in / $0.10 out. Prices as of October 30, 2026.

### What model ID and base URL do I use for Claude Haiku 5.5?

Use the model ID `claude-haiku-5-5` with the base URL `https://api.outrun.to/v1` and your Outrun API key. Route IDs: `claude-haiku-5-5-2` (Route 2).

### Does Claude Haiku 5.5 accept images?

Yes. Claude Haiku 5.5 accepts text and image input.

### Does Outrun store my prompts when I use Claude Haiku 5.5?

Outrun does not store your prompts, images or outputs unless you choose to save them.

## Where can I find more models?

[Anthropic Claude guide ↗](https://outrun.to/claude-api)[All model prices ↗](https://outrun.to/discounted-ai-api)[Model docs ↗](https://outrun.to/docs/models)[All model pages ↗](https://outrun.to/model/)

---
Source: https://outrun.to/model/claude-haiku-5-5
Outrun: https://outrun.to/ | API base: https://api.outrun.to/v1 | Prices (JSON): https://api.outrun.to/pricing | Docs: https://outrun.to/docs/