Claude 4.5 Haiku API

anthropic/claude-haiku-4.5
Claude 4.5 Haiku is a text-only chat model from Anthropic. It offers a 200,000-token context window and up to 64,000 tokens of output, positioning it as a fast, lighter option in the Claude 4.5 lineup. It supports streaming for real-time response delivery.
Context
200K tokens
Input
$1.3754 / 1M tokens
Output
$6.5 / 1M tokens

How to use Claude 4.5 Haiku API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to anthropic/claude-haiku-4.5.
import requests

r = requests.post(
    "https://api.aimlapi.com/v1/chat/completions",
    headers={"Authorization": "Bearer " + AIMLAPI_KEY},
    json={
      "model": "anthropic/claude-haiku-4.5",
      "messages": [
        {
          "role": "user",
          "content": "Hello!"
        }
      ]
    },
)
print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "anthropic/claude-haiku-4.5",
    "messages": [
      {
        "role": "user",
        "content": "Hello!"
      }
    ]
  }),
});
console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"anthropic/claude-haiku-4.5","messages":[{"role":"user","content":"Hello!"}]}'

OpenAI-compatible — swap the base URL and it works with your existing SDK.

Claude 4.5 Haiku API Pricing

TypePrice
Input
$1.3754 / 1M tokens
Output
$6.5 / 1M tokens
Cached input
$0.13754 / 1M tokens

Claude 4.5 Haiku Benchmarks

BenchmarkScoreWhat it measuresSourceRetrieved
Terminal-Bench
41.75%
Autonomous shell/terminal task completionSourceJuly 13, 2026
SWE-bench Verified
73.3%
Resolving verified real GitHub issuesSourceJuly 8, 2026
Intelligence
17.6
Composite score across standardised reasoning, knowledge and problem-solving evaluations, measured independently by Artificial AnalysisSourceSeptember 12, 2026
Coding
43.9
Composite score across standardised coding evaluations, measured independently by Artificial AnalysisSourceSeptember 12, 2026
Math
83.7
Composite score across standardised mathematics evaluations, measured independently by Artificial AnalysisSourceSeptember 12, 2026

Claude 4.5 Haiku vs other models

ModelInputOutputContextBest for
$1.3754 / 1M tokens
$6.5 / 1M tokens
200K tokens
Chat + assistants
$6.5 / 1M tokens
$39 / 1M tokens
1.05M tokens
Reasoning + agents
$2.6 / 1M tokens
$13 / 1M tokens
1M tokens
Balanced coding + agents
$3.9 / 1M tokens
$19.5 / 1M tokens
1M tokens
Long-context, multimodal & agentic workflows
$0.65 / 1M tokens
$3.9 / 1M tokens
1.05M tokens
Reasoning + agents

Frequently asked questions

Claude 4.5 Haiku has a 200,000 tokens context window and can return up to 64,000 tokens.

Claude 4.5 Haiku takes text as input and returns text.

Use anthropic/claude-haiku-4.5 as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.

Claude 4.5 Haiku is priced at input $1.3754 / 1M tokens, output $6.5 / 1M tokens, cached input $0.13754 / 1M tokens.

Yes, Claude 4.5 Haiku can stream responses as they are generated.

Claude 4.5 Haiku was built by Anthropic.

It is designed as a fast, lightweight model for quick responses and high-throughput applications.

Start building with Claude 4.5 Haiku

Get API Key
1000+ models, one API.