Billed by the tokens actually used; the unused part of the reservation is refunded.
New here?
10 free credits (US$0.10) when you sign up with Google
Usable 24 hours after sign-up, up to 5 runs per day and at most 2 credits per run. Other sign-in methods start without credits. Enough for 16 runs of this model.
02
About Claude Haiku 4.5
TL;DRAs of 23 September 2026
Claude Haiku 4.5 is a model by Anthropic in the Multimodal category. On Railwail, Claude Haiku 4.5 costs US$1.20 per 1M input tokens and US$6.00 per 1M output tokens. The context window holds 200,000 tokens, and one response can be up to 64,000 tokens long.
Claude Haiku 4.5 brings Sonnet-class reliability to the cost-and-latency tier. 200K context, full vision input, native tool use and extended thinking on demand. Designed for high-volume agents, real-time chat, classification, simple coding subagents, and consumer applications where p50 latency matters more than peak reasoning.
Background
About Anthropic
Founded 2021 · San Francisco, USA
Anthropic was founded in 2021 by Dario and Daniela Amodei. The Claude model family launched in March 2023 with Haiku as the lightweight tier optimized for low latency and cost. Successive Haiku generations have steadily closed the gap to Sonnet: Haiku 3 (March 2024), Haiku 3.5 (October 2024), Haiku 4 (May 2025) and Haiku 4.5 (late 2025/early 2026). Anthropic is structured as a Public Benefit Corporation focused on AI safety, with total funding exceeding $20 billion and a 2026 valuation above $150 billion.
Claude Haiku 4.5 is the fastest and cheapest model in the Claude 4.x family. Architecturally it is a smaller decoder-only Transformer distilled from the Sonnet/Opus 4 training stack, optimized aggressively for inference latency and throughput while retaining the full Claude feature set (vision, extended thinking, tool use). It was trained on the same multi-trillion-token curated corpus as its larger siblings with a knowledge cutoff in early 2026. Post-training combined RLHF, Constitutional AI, RLAIF and distillation from larger teacher models. Despite its small size, Haiku 4.5 supports the same 200K context window and tool-use API as Sonnet 4.6 and Opus 4.7, making it a drop-in cheaper option for high-concurrency workloads.
Parameters
Undisclosed (estimated tens of billions of parameters)
Context
200,000 tokens
Capabilities
Lowest p50 latency in the Claude 4.x family
200K token context window matching the larger Claude models
Vision input for images, PDFs and screenshots
Native tool use with parallel tool calling
Optional extended thinking mode for harder reasoning tasks
Sonnet-class reliability at one-third the cost
Strong instruction following and structured JSON output
Constitutional-AI alignment with low refusal rate
Available via Anthropic API, Bedrock and Vertex AI
Pretrained on the same curated multi-trillion-token mixture used by Sonnet and Opus 4.x. Post-training includes distillation from larger Anthropic models alongside RLHF, Constitutional AI and RLAIF. Knowledge cutoff in early 2026.
License: Proprietary commercial license via Anthropic API, Amazon Bedrock and Google Vertex AI.
Safety testing: Same Responsible Scaling Policy ASL-3 safeguards as Sonnet and Opus, with constitutional classifiers and third-party evaluations.
Known limitations
Below Sonnet 4.6 on hard reasoning and agentic coding benchmarks
No native audio or video input
Knowledge cutoff in early 2026
Less depth on niche or long-tail topics than larger models
curl https://railwail.com/api/v1/chat/completions \
-H "Authorization: Bearer $RAILWAIL_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "claude-haiku-4-5",
"messages": [
{
"role": "user",
"content": "Explain what a vector database is in two sentences."
}
],
"max_tokens": 1024
}'
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["RAILWAIL_API_KEY"],
base_url="https://railwail.com/api/v1",
)
completion = client.chat.completions.create(
model="claude-haiku-4-5",
messages=[
{
"role": "user",
"content": "Explain what a vector database is in two sentences.",
},
],
max_tokens=1024,
)
print(completion.choices[0].message.content)
import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.RAILWAIL_API_KEY,
baseURL: "https://railwail.com/api/v1",
});
const completion = await client.chat.completions.create({
model: "claude-haiku-4-5",
messages: [
{
role: "user",
content: "Explain what a vector database is in two sentences."
}
],
max_tokens: 1024
});
console.log(completion.choices[0].message.content);
// npm install railwail
import railwail from "railwail";
const rw = railwail(process.env.RAILWAIL_API_KEY);
const res = await rw.chat("claude-haiku-4-5", [
{ role: "user", content: "Explain what a vector database is in two sentences." },
], { max_tokens: 1024 });
console.log(res.choices[0].message.content);
Claude Haiku 4.5 is a model by Anthropic in the Multimodal category. On Railwail you can call it with an API key through the Railwail API.
How much does Claude Haiku 4.5 cost on Railwail?
On Railwail, Claude Haiku 4.5 costs US$1.20 per 1M input tokens and US$6.00 per 1M output tokens. You are charged for what each request actually uses. Usage is paid from prepaid credits; 1 credit equals US$0.01.
What is the context window of Claude Haiku 4.5?
The context window of Claude Haiku 4.5 holds 200,000 tokens. One response can be up to 64,000 tokens long.
How fast is Claude Haiku 4.5?
There are not enough measured runs of Claude Haiku 4.5 on Railwail yet to state a run time. It depends on the input, the settings and the load at the provider.
Is Claude Haiku 4.5 better than BLIP?
That depends on the task. Claude Haiku 4.5 (Anthropic) and BLIP (Salesforce) are both models in the Multimodal category. The comparison page shows their prices and specifications side by side.
Yes. Claude Haiku 4.5 accepts images as input in addition to text.
How do I use Claude Haiku 4.5 through the API?
Create a Railwail API key and send your request with the model ID claude-haiku-4-5. Code examples for curl, Python and JavaScript are in the API section of this page.
