Claude Sonnet 4.6

Name: Claude Sonnet 4.6
Brand: Anthropic
SKU: claude-sonnet-4-6
Price: 3.6 USD
Availability: InStock

MultimodalniStarija verzijaDostupno

od Anthropicclaude-sonnet-4-6

Anthropic's balanced mid-tier model from February 2026. Best price/performance for production workloads: 5x cheaper than Opus, near-flagship quality.

Isprobaj Preuzmi API ključ Usporedi

Cijena · 1M ulaz/izlaz: 3,60 US$ / 18,00 US$
Kontekst: 1.000.000 tokena
Maks. izlaz: 128.000 tokena
Ulaz → izlaz: Tekst + Slika → Tekst
Razvojni inženjer: Anthropic
Ažurirano: 23. septembar 2026.

Ovo je starija verzija modela.

Dostupna je novija verzija: Claude Sonnet 5

Playground

Isprobaj Claude Sonnet 4.6

Razgovor

3,60 US$/1M in

Pošalji poruku. Odgovor stigne u cijelosti kada je model gotov (bez streaminga).

Sistemski prompt

Maks. duljina odgovora (tokeni)

TemperaturaZadana vrijednost modela

⌘/Ctrl + Enter

Ovaj pokus

najviše 0,0185 US$ · 1,85 kredita rezervirano

Naplata se vrši prema stvarno korištenim tokenima; nekorišteni dio rezervacije se vraća.

Novi si ovdje?

10 besplatnih kredita (0,10 US$) kada se registriraš s Googlom

Dostupno 24 sati nakon registracije, do 5 pokusa dnevno i najviše 2 kredita po pokusu. Ostale metode prijave počinju bez kredita. Dovoljno za 5 pokretanja ovog modela.

O Claude Sonnet 4.6

UkratkoStanje: 23. septembar 2026.

Claude Sonnet 4.6 je model od Anthropic iz kategorije Multimodalni. Na Railwailu, Claude Sonnet 4.6 košta 3,60 US$ po 1M ulaznih tokena i 18,00 US$ po 1M izlaznih tokena. Kontekstni prozor sadrži 1.000.000 tokena, a jedan odgovor može biti dugačak do 128.000 tokena. Novija verzija: Claude Sonnet 5.

Released February 17, 2026, Claude Sonnet 4.6 is the workhorse of the 4.x Claude family. Delivers near-Opus quality on most coding, writing and analysis tasks at one-fifth the cost. 1M-token context window, extended thinking, full vision support, and the same tool-use loop as Opus 4.7. Suited to production agents, developer copilots, customer support, and most enterprise API scenarios.

Pozadina

O Anthropic

Osnovano 2021 · San Francisco, USA

Anthropic was founded in 2021 by Dario and Daniela Amodei together with senior researchers from OpenAI. The company is a Public Benefit Corporation focused on AI safety. Key research milestones include Constitutional AI (2022), Sparse Autoencoders for interpretability, and the Claude model family launched in March 2023. Claude Sonnet has been Anthropic's flagship 'balanced' tier since the Claude 3 family, with major releases including Sonnet 3.5 (June 2024), Sonnet 3.7 with extended thinking (February 2025), Sonnet 4 (May 2025), Sonnet 4.5 (late 2025) and Sonnet 4.6 (February 17, 2026). Investors include Google, Amazon, Spark Capital and Lightspeed; total funding exceeds $20 billion with a 2026 valuation above $150 billion.

Posjetite Anthropic

Arhitektura

Decoder-only Transformer (balanced production model with extended thinking)

Claude Sonnet 4.6 was released February 17, 2026 as the mid-tier workhorse of the Claude 4.x family. It is a decoder-only Transformer engineered to deliver near-Opus quality at one-fifth the cost. Pretraining used the same multi-trillion-token mixture as Opus 4.7 with a knowledge cutoff in early 2026. Post-training combined RLHF, Constitutional AI, RLAIF, and reinforcement learning against verifiable rewards on coding, math and tool-use trajectories. Sonnet 4.6 supports the full Opus feature set: extended thinking mode, native vision, computer use, parallel tool calling, and 200K context. The training emphasis was on efficiency: Sonnet 4.6 outperforms Opus 4 on most coding and writing benchmarks while running ~2x faster and at one-fifth the cost. Anthropic positions Sonnet 4.6 as the recommended default for production workloads.

Parametri: Undisclosed (estimated dense model in the 100B-range)
Kontekst: 200.000 tokena

Mogućnosti

Near-Opus quality on most coding, writing and analysis tasks at 5x lower cost
Extended thinking mode with adjustable thinking budget
200K token context window with strong needle-in-haystack recall
Multimodal input: text, images, PDFs, charts and diagrams
Native computer use: screenshots, mouse and keyboard control
Parallel tool calling and stable multi-turn agent loops
Strong instruction following including XML tags, schemas and strict JSON
Constitutional-AI alignment with low refusal rate on benign questions
Multilingual fluency across 20+ languages
~2x faster latency than Opus 4.7 on equivalent tasks
Best for: production agents, developer copilots, customer support, most enterprise API scenarios.

Obuka i licenca

Pretrained on a curated multi-trillion-token mixture identical to the Opus 4.7 corpus, with heavy quality filtering, deduplication and copyright screening. Knowledge cutoff in early 2026. Post-training uses RLHF, Constitutional AI, RLAIF and RL against verifiable rewards.

Licenca: Proprietary commercial license via Anthropic API, Amazon Bedrock and Google Vertex AI. Commercial use permitted under Anthropic's Usage Policy.

Testiranje sigurnosti: Deployed under Responsible Scaling Policy ASL-3 safeguards with constitutional classifiers, automated red-teaming, third-party evaluations and a public Bug Bounty programme.

Poznata ograničenja

Below Opus 4.7 on the hardest agentic and reasoning benchmarks
No native audio or video input
Knowledge cutoff in early 2026; needs tool use for fresh information
Will refuse some legitimate red-team and security research prompts
No fine-tuning available to external customers

Znanstveni članci

Cijene

Cijene u USD-u. Korištenje se naplaćuje iz unaprijed plaćenih kredita.

Ulaz	3,60 US$ / 1M tokena
Izlaz	18,00 US$ / 1M tokena

Naplaćuje se prema tokenima koje svaki zahtjev zapravo koristi.
1 kredit = 0,01 US$

Kalkulator troškova

Kalkulator cijena

Ulazni tokeni

/ zahtjev

Izlazni tokeni

/ zahtjev

Zahtjevi

Ukupno

1,26 US$

126 kredita

Po zahtjevu

0,0126 US$ · 1,26 kredita

Svaki zahtjev se zaokružuje na 0,01 kredita.

API

Pozovi Claude Sonnet 4.6 sa svojim Railwail API ključem. Koristi ovaj ID modela u zahtjevu:

claude-sonnet-4-6Pogledaj API dokumentaciju Dobij API ključ

curl https://railwail.com/api/v1/chat/completions \
  -H "Authorization: Bearer $RAILWAIL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4-6",
    "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-sonnet-4-6",
    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-sonnet-4-6",
  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-sonnet-4-6", [
  { role: "user", content: "Explain what a vector database is in two sentences." },
], { max_tokens: 1024 });

console.log(res.choices[0].message.content);

Postavite ključ kao RAILWAIL_API_KEYKreiraj API ključ

Specifikacije

ID modela: claude-sonnet-4-6
Razvojni inženjer: Anthropic
Kategorija: Multimodalni
Ulaz: Tekst, Slika
Izlaz: Tekst
Kontekstni prozor: 1.000.000 tokena
Maks. izlaz: 128.000 tokena
Naplata: Po potrošnji (tokeni ili GPU vrijeme)
Objavljeno: 17. februar 2026.
Životni ciklus: Starija verzija
Veličina modela: Undisclosed (estimated dense model in the 100B-range)
Licenca: Proprietary commercial license via Anthropic API, Amazon Bedrock and Google Vertex AI. Commercial use permitted under Anthropic's Usage Policy.
Katalog ažuriran: 23. septembar 2026.

Parametri ulaza

Ulazi i postavke iz sheme ulaza modela. Primjer u odjeljku API pokazuje koje od njih API prihvaća.

ParametarTipZadanoDozvoljene vrijednosti

promptobavezno
User message
Tip: Tekst
Zadano: –
Dozvoljene vrijednosti: do 32.000 znakova
top_p
Tip: Broj
Zadano: 1
Dozvoljene vrijednosti: 0 do 1
stream
Tip: Da/Ne
Zadano: false
Dozvoljene vrijednosti: –
image_url
Optional image URL to analyze
Tip: Tekst
Zadano: –
Dozvoljene vrijednosti: –
max_tokens
Tip: Cijeli broj
Zadano: 4096
Dozvoljene vrijednosti: 1 do 32.000
temperature
Tip: Broj
Zadano: 1
Dozvoljene vrijednosti: 0 do 1
system_prompt
Optional system instruction
Tip: Tekst
Zadano: –
Dozvoljene vrijednosti: do 8.000 znakova

Oznake

anthropic
balanced
production
agentic
vision
extended-thinking

Primjena

Za što se koristi

Production coding assistants and IDE copilots
Customer support chatbots and triage agents
Enterprise document analysis and summarisation
Multi-turn agent loops with tool use
Computer-use automation
Content generation and editing pipelines

Svi modeli: Multimodalni

Često postavljana pitanja

Što je Claude Sonnet 4.6?

Claude Sonnet 4.6 je model od Anthropic iz kategorije Multimodalni. Na Railwailu ga možete pozvati s API ključem kroz Railwail API.

Koliko stoji Claude Sonnet 4.6 na Railwailu?

Na Railwailu, Claude Sonnet 4.6 košta 3,60 US$ po 1M ulaznih tokena i 18,00 US$ po 1M izlaznih tokena. Naplaćuje se ono što svaki zahtjev zapravo koristi. Korištenje se plaća iz unaprijed kupljenih kredita; 1 kredit jednaka je 0,01 US$.

Koliki je kontekstni prozor od Claude Sonnet 4.6?

Kontekstni prozor od Claude Sonnet 4.6 sadrži 1.000.000 tokena. Jedan odgovor može biti dugačak do 128.000 tokena.

Koliko je brz Claude Sonnet 4.6?

Za Claude Sonnet 4.6 na Railwailu još nema dovoljno izmjerenih pokretanja da bi se navedlo vrijeme izvršavanja. Ovisi o unošenju, postavkama i opterećenju kod pružatelja.

Je li Claude Sonnet 4.6 bolji od Claude Sonnet 5?

To ovisi o zadatku. Claude Sonnet 4.6 (Anthropic) i Claude Sonnet 5 (Anthropic) su oba modela iz kategorije Multimodalni. Stranica za usporedbu prikazuje njihove cijene i specifikacije usporedno.

Usporedi Claude Sonnet 4.6 i Claude Sonnet 5

Može li Claude Sonnet 4.6 obraditi slike?

Da. Claude Sonnet 4.6 prihvaća slike kao unos osim teksta.

Kako koristim Claude Sonnet 4.6 kroz API?

Kreiraj Railwail API ključ i pošalji svoj zahtjev s ID-om modela claude-sonnet-4-6. Primjeri koda za curl, Python i JavaScript nalaze se u odjeljku API na ovoj stranici.

Usporedivi modeli

Svi u ovoj kategoriji

Claude Opus 4.7Anthropic
Anthropic's April 2026 flagship. 87.6% on SWE-bench Verified, 3x higher image resolution, output self-verification, vision + reasoning.
6,00 US$/1M in
67 % skupnije po jedinici
Usporedi Claude Sonnet 4.6 i Claude Opus 4.7
Gemini 3 FlashGoogle DeepMind
Google's April 2026 fast multimodal model. Combines Gemini 3 Pro's reasoning with Flash-tier latency and price. Default model in the Gemini app.
0,60 US$/1M in
83 % jeftinije po jedinici
Usporedi Claude Sonnet 4.6 i Gemini 3 Flash
Gemini 3.1 ProGoogle DeepMind
Google DeepMind's February 2026 flagship. 1M-token (1,048,576) context, native multimodal (text/image/audio/video), Deep Think reasoning.
2,40 US$/1M in
33 % jeftinije po jedinici
Usporedi Claude Sonnet 4.6 i Gemini 3.1 Pro

Koristi Claude Sonnet 4.6 preko API-ja

Jedan API ključ za sve modele na Railwailu. Korištenje se naplaćuje iz unaprijed plaćenih kredita, 1 kredit = 0,01 US$.

Dobij API ključ Pogledaj sve modele