Claude Sonnet 4.6

Claude Sonnet 4.6 is Anthropic's mid-tier Sonnet model for coding, computer use, document comprehension, and office automation.

input · usd / 1m tok

$3.00

output · usd / 1m tok

$15.00

context window

1mtokens

modalities · in → out

takes text and image in, gives text out

pricing

base api ratesusd per 1m tokens

input
$3.00
output
$15.00
cache read
$0.30
cache write · default ttl
$3.75
cache write · 1h ttl
$6.00

providers

Different companies host Claude Sonnet 4.6. Impossibl routes your request intelligently and handles failover automatically when a provider is down.

  • Amazon Bedrock
  • Anthropic

specifications

takes text and image in, gives text outanthropic/claude-sonnet-4-6

  • creatorAnthropic
  • model typeText generation
  • context window1,000,000 tokens
  • maximum outputnot published
  • input

    takes text and image in, gives text out

  • outputtext
  • tool callingnot verified
  • releasedfeb 17, 2026
  • endpoint/v1/chat/completions

unknown means the public catalog does not establish that fact. a model's documented capabilities can differ from what a particular api supports. see the model documentation for integration details.

try it · your prompt, this model, live

# responses API
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["IMPOSSIBL_API_KEY"],
    base_url="https://api.impossibl.com/v1",
)

resp = client.responses.create(
    model="anthropic/claude-sonnet-4-6",
    input="",
)
print(resp.output_text)

edit the prompt, then run

benchmarks

intelligence index

24.7#69 of 113 models on the gateway

  1. omniscience-3.5#44 of 90
  2. gpqa79.9%#59 of 82
  3. humanity’s last exam13.3%#71 of 93
  1. GPQA79.9%
  2. Tau279.5%
  3. MMMU-Pro70.6%
  4. AA-LCR68.3%
  5. Terminal-Bench Hard46.2%
  6. IFBench41.2%
  7. Humanity’s Last Exam13.3%
  8. CritPt0.9%
  • Intelligence Index24.69
  • Omniscience Index-3.55
  • intelligence index (API)24.7

view source ↗all source data and breakdowns (json) ↗

each configuration is listed separately; these evaluations describe the tested model configuration, and performance and costs can differ on impossibl. unmeasured scores are omitted and api values keep their source units. last checked 2026-10-22.

compare Claude Sonnet 4.6 with other models

frontier labs and open weights, best-ranked firstusd / 1m tok · in / out

impossibl models --all →

frequently asked questions

What is Claude Sonnet 4.6?

Claude Sonnet 4.6 is Anthropic's mid-tier Sonnet model for coding, computer use, document comprehension, and office automation. Compared with Sonnet 4.5 it is less prone to overengineering, follows instructions more closely, hallucinates less, and gains a much larger context window in beta.

How much does Claude Sonnet 4.6 cost?

Claude Sonnet 4.6 costs $3.00 per million input tokens and $15.00 per million output tokens through the Impossibl API. Cache reads cost $0.30 per million tokens; cache writes cost $3.75 per million tokens; cache writes with one-hour retention cost $6.00 per million tokens. All rates are in USD.

view the pricing table ↑

What is the context length of Claude Sonnet 4.6?

Claude Sonnet 4.6 has a 1,000,000-token context window through the Impossibl API.

What inputs and outputs does Claude Sonnet 4.6 support?

Claude Sonnet 4.6 accepts text and image as input. Claude Sonnet 4.6 returns text.

How do I use Claude Sonnet 4.6 through an API?

Claude Sonnet 4.6 is available through the Impossibl API. Use anthropic/claude-sonnet-4-6 as the model identifier with /v1/chat/completions. The quickstart explains how to create an API key and send your first request.

follow the api quickstart →

When was Claude Sonnet 4.6 released?

Anthropic released Claude Sonnet 4.6 on February 17, 2026.

this page describes Claude Sonnet 4.6 as listed by the impossibl public api. prices and availability come from that catalog, refreshed here every five minutes. this is an impossibl offering, not a comparison of independent hosting-provider quotes. model descriptions and release dates, where available, use the creator sources linked under the answers above.

view the source catalog ↗model as markdown ↗report a correction →