Claude Sonnet 4.6

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

MultimodalEldre versjonTilgjengelig

av 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.

Prøv det Få API-nøkkel Sammenlign

Pris · 1M inn/ut: 3,60 USD / 18,00 USD
Kontekst: 1 000 000 tokens
Maks. utdata: 128 000 tokens
Input → output: Tekst + Bilde → Tekst
Utvikler: Anthropic
Oppdatert: 23. september 2026

Dette er en eldre versjon av modellen.

Nyere versjon tilgjengelig: Claude Sonnet 5

Playground

Prøv Claude Sonnet 4.6

Chat

3,60 USD/1M inn

Send en melding. Svaret kommer fullstendig når modellen er ferdig (ingen streaming).

Systemprompt

Maks. svarslengde (tokens)

TemperaturModellstandard

⌘/Ctrl + Enter

Denne kjøringen

maksimalt 0,0185 USD · 1,85 credits reservert

Fakturert etter faktisk brukte tokens; ubrukt del av reservasjonen refunderes.

Ny her?

10 gratis credits (0,10 USD) når du registrerer deg med Google

Kan brukes 24 timer etter registrering, opptil 5 kjøringer per dag og maksimalt 2 credits per kjøring. Andre påloggingsmetoder starter uten credits. Nok for 5 kjøringer av denne modellen.

Om Claude Sonnet 4.6

Kort sagtPer 23. september 2026

Claude Sonnet 4.6 er en modell fra Anthropic i kategorien Multimodal. På Railwail koster Claude Sonnet 4.6 3,60 USD per 1M inndatatokens og 18,00 USD per 1M utdatatokens. Kontekstvinduet inneholder 1 000 000 tokens, og ett svar kan være opptil 128 000 tokens langt. Nyere versjon: 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.

Bakgrunn

Om Anthropic

Grunnlagt 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.

Besøk Anthropic

Arkitektur

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.

Parametere: Undisclosed (estimated dense model in the 100B-range)
Kontekst: 200 000 tokens

Evner

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.

Trening og lisens

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.

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

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

Kjente begrensninger

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

Forskningsartikler

Priser

Priser i amerikanske dollar. Bruk belastes fra forhåndsbetalt kreditt.

Inndata	3,60 USD / 1M tokener
Utdata	18,00 USD / 1M tokener

Faktureres etter tokenene som hver forespørsel faktisk bruker.
1 kreditt = 0,01 USD

Kostnadsberegner

Prisberegner

Input-tokens

/ forespørsel

Output-tokens

/ forespørsel

Forespørsler

Totalt

1,26 USD

126 credits

Per forespørsel

0,0126 USD · 1,26 credits

Hver forespørsel rundes opp til 0,01 credits.

API

Ring Claude Sonnet 4.6 med din Railwail API-nøkkel. Bruk denne modell-IDen i forespørselen:

claude-sonnet-4-6API-dokumentasjon Få en API-nøkkel

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);

Sett nøkkelen din som RAILWAIL_API_KEYOpprett API-nøkkel

Spesifikasjoner

Modell-ID: claude-sonnet-4-6
Utvikler: Anthropic
Kategori: Multimodal
Inndata: Tekst, Bilde
Utdata: Tekst
Kontekstvindu: 1 000 000 tokens
Maks. utdata: 128 000 tokens
Fakturering: Etter bruk (tokens eller GPU-tid)
Utgitt: 17. februar 2026
Livssyklus: Eldre versjon
Modellstørrelse: Undisclosed (estimated dense model in the 100B-range)
Lisens: Proprietary commercial license via Anthropic API, Amazon Bedrock and Google Vertex AI. Commercial use permitted under Anthropic's Usage Policy.
Katalogoppføring oppdatert: 23. september 2026

Inndataparametere

Inndataer og innstillinger fra modellens inndataskjema. Eksemplet i API-delen viser hvilke av dem APIen godtar.

ParameterTypeStandardTillatte verdier

promptobligatorisk
User message
Type: Tekst
Standard: –
Tillatte verdier: opptil 32 000 tegn
top_p
Type: Tall
Standard: 1
Tillatte verdier: 0 til 1
stream
Type: Ja/Nei
Standard: false
Tillatte verdier: –
image_url
Optional image URL to analyze
Type: Tekst
Standard: –
Tillatte verdier: –
max_tokens
Type: Heltall
Standard: 4096
Tillatte verdier: 1 til 32 000
temperature
Type: Tall
Standard: 1
Tillatte verdier: 0 til 1
system_prompt
Optional system instruction
Type: Tekst
Standard: –
Tillatte verdier: opptil 8 000 tegn

Merkelapper

anthropic
balanced
production
agentic
vision
extended-thinking

Brukstilfeller

Hva det brukes til

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

Alle modeller i Multimodal

Ofte stilte spørsmål

Hva er Claude Sonnet 4.6?

Claude Sonnet 4.6 er en modell fra Anthropic i kategorien Multimodal. På Railwail kan du kalle den med en API-nøkkel gjennom Railwail API.

Hvor mye koster Claude Sonnet 4.6 på Railwail?

På Railwail koster Claude Sonnet 4.6 3,60 USD per 1M inndatatokens og 18,00 USD per 1M utdatatokens. Du betaler for det hver forespørsel faktisk bruker. Bruk betales fra forhåndskjøpte kreditter; 1 kreditt tilsvarer 0,01 USD.

Hvor stort er kontekstvinduet til Claude Sonnet 4.6?

Kontekstvinduet til Claude Sonnet 4.6 inneholder 1 000 000 tokens. Ett svar kan være opptil 128 000 tokens langt.

Hvor rask er Claude Sonnet 4.6?

Det finnes ennå ikke nok målte kjøringer av Claude Sonnet 4.6 på Railwail til å angi en kjøretid. Det avhenger av inndataene, innstillingene og belastningen hos leverandøren.

Er Claude Sonnet 4.6 bedre enn Claude Sonnet 5?

Det avhenger av oppgaven. Claude Sonnet 4.6 (Anthropic) og Claude Sonnet 5 (Anthropic) er begge modeller i kategorien Multimodal. Sammenligningssiden viser prisene og spesifikasjonene deres side ved side.

Sammenlign Claude Sonnet 4.6 og Claude Sonnet 5

Kan Claude Sonnet 4.6 behandle bilder?

Ja. Claude Sonnet 4.6 godtar bilder som inndata i tillegg til tekst.

Hvordan bruker jeg Claude Sonnet 4.6 gjennom API-en?

Opprett en Railwail API-nøkkel og send forespørselen din med modell-ID-en claude-sonnet-4-6. Kodeeksempler for curl, Python og JavaScript finnes i API-delen av denne siden.

Sammenlignbare modeller

Alle i denne kategorien

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 USD/1M inn
67 % dyrere per enhet
Sammenlign Claude Sonnet 4.6 og 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 USD/1M inn
83 % billigere per enhet
Sammenlign Claude Sonnet 4.6 og 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 USD/1M inn
33 % billigere per enhet
Sammenlign Claude Sonnet 4.6 og Gemini 3.1 Pro

Bruk Claude Sonnet 4.6 via APIen

Én API-nøkkel for alle modeller på Railwail. Bruk belastes fra forhåndsbetalt kreditt, 1 kreditt = 0,01 USD.

Få API-nøkkel Se alle modeller