Claude Sonnet 5

Claude Sonnet 5 is Anthropic's mid-tier Sonnet model, positioned for multi-step coding, business automation, legal research, and computer-use agents at lower cost than Opus.

start building →

compare models

                        ....   . ..             ... . ..  .
                     .-***********-.        ..+++*+++++++-..
                    .-%@@@@@@@#@#@%+.       .:*%@@@@@@%@%%-..
                   .:=@#####@@@@##@%-.      ..-=@@@@@@@@@%=:.
                  .:*@########@#@@@@=:.       .+@@@@@@@@@%%*:
                  .+@@#@@@@##@@@@@#@@+..      .:*@@@@@@@@@%%-.
                 .:%@@##@@@#@@##@#@@@%-.       .:%@@@@@@@@@@=:.
                 .*@@###@#@@@#@#@@@@@@=:        .+%%@@@@@@%%%+.
                .-@@@#@####@@#@@@@@@@@@+.       .:*%@@@@@@@@@=-.
               .:=@@###@##@#@@@@#@@@@@@%:.       .:=%@@@@%@%%%=:.
              .:*@@@#@##@@@@=%@@@@@@@@@%*:.       :+%%%@@%@@@%%+.
              .-%@@#@@#@#@@=-+@@@@@@@@@@%+..      .:*%@@@%@%@%%%:..
             .:=@#@@#@#@@@=:.:=@@@@@@@@@@%:.       .:=%@@@%%@%@%*..
            .:*@@@@@##@@@@-...-%@@@@@@@@@%=:        .-%@@@%%@%%%=+:.
            .-@@@##@@@#@%*:. ..+@@@@@@@@@@%+..       :*%@%%%%%%%==-..
           .:=@@##@@@@@@%:.   .:=%@@@@@@@@%=:.       .-=%%%@%%%%%%*..
          ..*@#@#@@#@@@%+.     .-%@@@@@@@@@%*.       ..-=%%%%%%%%%%+..
          .-%@@@@#@@@@@=:.     .:+@@@@@@@@%%%-:.      .:*%%%%%%%%=%=-.
         .:=@@@@#@@@@@%-.       .:=%@@@%@@%%%=-.       .:*%%%%%%%%%=*..
        .:+@@@##@@@@@%+..        .-%@@@@@%@%@%*:       ..-=%%%%%%%%%=-.
        .-%@@@@@@@@@@%*-----------+=@@%%%@@%%%%+..       .+=%%%%%=%%=*:.
        :=@@@@@@@@@@@@%@%@@%%%%@%@%@%%%%%%@%@%%=:.       .:==%%%%%%=%=+..
      .:*@@@@@@@@@@@@@@@@@@@@@%@%%%%@@@@%@%%@%%%*..       .-==%%=%%%===-.
      .:%@@@@@@@@@@@@@@@@@@@@%@@@@@@@%@%@%%@%%%%%-..      ..*=%=%===%==*:.
      :=@@@@@@@@@@@@@@@@@@@@@@@@%%@%%%%@@%%%%@%%==:.       .:*======%===+.
    ..+@@@@@@@@@@@@@@@@@@@@@%%%%@%%@%%@%%%%%%%%%%%+..      ..-=%%=%=====*-.
   ..-%@@@@@@@@@@%%%================*==%%%%%%%%%%%=-.        .+==%=======*:.
   .:=@@@@@@@@@@%-:...::..........:.:..-==%%%%%%%%%*:.       .:*=========*+..
   :*@@@@@@@@@@%+:.                    .-=%%%%%%%%==+.       ..-*=========*-.
  .-%@@@@@@@@@%=:.                     .:*=%%%%%%=%==-.        .+*=====*==**:.
  :=@@@@@@@@@@%-..                      .:=%%%%%%%%==*..        :***====*==*+:.
 :+%@@@@@@@@%%*..                        .-===%%=%=%%=+..       .-**=*===****:.
.-=%%@@@%%@@%=:.                         ..+==========*-.        .-*==*===***+.
.:+*+*****+++-.                           .:-+-++-++---:.        ..-------:--::
  .. ... . ..                               . .  .. ...           ...  .    .

input · usd / 1m tok

$2.00

output · usd / 1m tok

$10.00

context window

1mtokens

modalities · in → out

pricing

base api ratesusd per 1m tokens

input: $2.00
output: $10.00
cache read: $0.20
cache write · default ttl: $2.50
cache write · 1h ttl: $4.00

providers

Different companies host Claude Sonnet 5. Impossibl routes your request intelligently and handles failover automatically when a provider is down.

Azure AI Foundry
Azure AI Foundry serving options
endpoint location routes
East US 1
East US 2 1
locations describe provider endpoints; they do not guarantee where inference runs.
Anthropic

Azure AI Foundry serving options
endpoint location	routes
East US	1
East US 2	1

specifications

takes text and image in, gives text outanthropic/claude-sonnet-5

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
releasedjun 30, 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-5",
    input="▌",
)
print(resp.output_text)

edit the prompt, then run

# 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-5",
    input="▌",
)
print(resp.output_text)

edit the prompt, then run

benchmarks

intelligence index

38.2#33 of 108 models on the gateway

coding index71.5#19 of 64
agentic index43.6#14 of 53
omniscience16.4#17 of 84
gpqa91.1%#20 of 80
humanity’s last exam41.3%#21 of 87

GPQA91.1%
AA-LCR82.0%
MMMU-Pro77.3%
Multilingual LCR55.0%
SciCode54.3%
AnalystAgent46.3%
Humanity’s Last Exam41.3%
Tau Banking37.3%
AutomationBench Partial36.5%
CritPt16.9%
GDP.pdf All-pass13.2%

Intelligence Index38.16
Omniscience Index16.45
GDPval Elo1463.43
legal index (API)42.3
coding index (API)71.5
agentic index (API)43.6
economics index (API)49.4
engineering index (API)40.2
intelligence index (API)38.2
strategy and ops index (API)39.2
finance and accounting index (API)40.4
healthcare and medical index (API)42.8

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 2026-10-14.

compare Claude Sonnet 5 with other models

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

openai/gpt-6-astra$10.00 / $50.00compare →
google/gemini-4-argon$2.00 / $10.00compare →
meta/muse-wonder$4.00 / $20.00compare →
xiaomi/mimo-v2.6-pro$0.435 / $0.87compare →

impossibl models --all →

frequently asked questions

What is Claude Sonnet 5?

Claude Sonnet 5 is Anthropic's mid-tier Sonnet model, positioned for multi-step coding, business automation, legal research, and computer-use agents at lower cost than Opus. Anthropic calls it the most agentic Sonnet yet: it finishes tasks earlier Sonnets stopped short on, verifies its work unprompted, and offers selectable reasoning effort levels.

How much does Claude Sonnet 5 cost?

Claude Sonnet 5 costs $2.00 per million input tokens and $10.00 per million output tokens through the Impossibl API. Cache reads cost $0.20 per million tokens; cache writes cost $2.50 per million tokens; cache writes with one-hour retention cost $4.00 per million tokens. All rates are in USD.

view the pricing table ↑

What is the context length of Claude Sonnet 5?

Claude Sonnet 5 has a 1,000,000-token context window through the Impossibl API.

What inputs and outputs does Claude Sonnet 5 support?

Claude Sonnet 5 accepts text and image as input. Claude Sonnet 5 returns text.

How do I use Claude Sonnet 5 through an API?

Claude Sonnet 5 is available through the Impossibl API. Use anthropic/claude-sonnet-5 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 5 released?

Anthropic released Claude Sonnet 5 on June 30, 2026.

Creator release announcement ↗

this page describes Claude Sonnet 5 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 →