Obračunava se dejanska poraba žetonov; neporabljeni del rezervacije se vrne.
Novo tukaj?
10 brezplačnih kreditov (0,10 $) ob prijavi z Googlom
Uporabno 24 ur po prijavi, do 5 zaganom na dan in največ 2 kreditov na zagon. Druge metode prijave se začnejo brez kreditov. Dovolj za 16 zagonov tega modela.
02
O Claude Haiku 4.5
PovzetekOd 23. september 2026
Claude Haiku 4.5 je model razvijalca Anthropic iz kategorije Multimodalno. Na Railwail stane Claude Haiku 4.5 1,20 $ na 1M vhodnih žetonov in 6,00 $ na 1M izhodnih žetonov. Kontekstno okno vsebuje 200.000 žetonov, odgovor pa je lahko dolg do 64.000 žetonov.
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.
Ozadje
O Anthropic
Ustanovljeno 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.
Parametri
Undisclosed (estimated tens of billions of parameters)
Kontekst
200.000 žetonov
Zmožnosti
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.
Licenca: Proprietary commercial license via Anthropic API, Amazon Bedrock and Google Vertex AI.
Preizkusi varnosti: Same Responsible Scaling Policy ASL-3 safeguards as Sonnet and Opus, with constitutional classifiers and third-party evaluations.
Znane omejitve
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 je model podjetja Anthropic iz kategorije Multimodalno. Na Railwailu ga lahko pokličete z ključem API prek Railwailovega API-ja.
Koliko stane Claude Haiku 4.5 na Railwailu?
Na Railwail stane Claude Haiku 4.5 1,20 $ na 1M vhodnih žetonov in 6,00 $ na 1M izhodnih žetonov. Zaračunano vam je tisto, kar vsaka zahteva dejansko porabi. Uporaba se plača s predplačanimi krediti; 1 kredit je enak 0,01 $.
Kako veliko je kontekstno okno Claude Haiku 4.5?
Kontekstno okno Claude Haiku 4.5 vsebuje 200.000 žetonov. Odgovor je lahko dolg do 64.000 žetonov.
Kako hiter je Claude Haiku 4.5?
Za Claude Haiku 4.5 je na Railwailu še premalo izmerjenih zagonov, da bi navedli čas izvajanja. Odvisno je od vnosa, nastavitev in obremenitve pri ponudniku.
Je Claude Haiku 4.5 boljši od BLIP?
To je odvisno od naloge. Claude Haiku 4.5 (Anthropic) in BLIP (Salesforce) sta oba modela iz kategorije Multimodalno. Stran za primerjavo prikazuje njune cene in specifikacije drug ob drugem.
Da. Claude Haiku 4.5 sprejema slike kot vhod poleg besedila.
Kako uporabljam Claude Haiku 4.5 prek API-ja?
Ustvarite ključ Railwailovega API-ja in pošljite zahtevo z ID-jem modela claude-haiku-4-5. Primeri kode za curl, Python in JavaScript so v razdelku API na tej strani.
