Models/Anthropic/Claude Haiku 4.5

Anthropic: Claude Haiku 4.5

Name: Claude Haiku 4.5
Brand: Anthropic
Price: 0.771925 USD
Availability: InStock

Textclaude-haiku-4-5

The fastest, cheapest Claude for light tasks and high volume.

API docs

Playgroundclaude-haiku-4-5

Max tokens

Reasoning

Throughput90 tok/s

24hnow

Latency1.38 s

24hnow

Specifications

Authoranthropic

ModalityText

Context200K tokens

Input$0.77/M tokens$1.00/M tokens

Output$4.00/M tokens$5.00/M tokens

Savings−20%

Capabilitiesreasoning, tool calling, image input

Quick start

from openai import OpenAI

client = OpenAI(
    base_url="https://api.altrouter.ai/v1",
    api_key="ar-...",
)

resp = client.chat.completions.create(
    model="claude-haiku-4-5",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)

Same OpenAI-compatible endpoint — just swap base_url and key.

API

OpenAI-compatible chat completions endpoint, with SSE streaming.

POST/v1/chat/completions

Body parameters

modelstringrequired"claude-haiku-4-5"

The model id.

messagesarrayrequired

The conversation: [{ role, content }].

streambooleandefault false

Stream the response over SSE.

max_tokensnumber1–8192default 4096

Maximum tokens to generate.

reasoning_effortbooleandefault false

Thinking budget for reasoning models.

Structured fields (tools, response_format, stop and more) are in the full parameter reference.

Response

idstring

Completion id.

choicesarray

Completions. Each: index, message { role, content, reasoning_content, tool_calls }, finish_reason.

usageobject

Tokens: prompt_tokens, completion_tokens, total_tokens.

Example

cURLPythonJSON

curl https://api.altrouter.ai/v1/chat/completions \
  -H "Authorization: Bearer ar-..." \
  -H "Content-Type: application/json" \
  -d '{
  "model": "claude-haiku-4-5",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ]
}'

Errors

400Invalid request.

401Missing or invalid API key.

402Insufficient credits, or the key’s spending cap is exhausted.

404Model not found.

429Rate limit exceeded.