Skip to main content

Claude Sonnet 4.5

Live
Anthropic198K context · Text, Vision, Tools, ReasoningBenchmark price · $3 input / $15 output per 1M tokens
Use this model
Best discount now75.1%offYou pay 24.9% of reference.
Median discount17.0%offAcross 47 live offers.
Realized · 7 days50.2%avgRequest-weighted average.
Requests · 24h10,00847 offers from 40 sellers.
Current offers
47 of 132 offers
Availability
Providers
ProviderDiscountPriceLatencyUptimeCacheSold
InferHub
75%
$0.75 in
$3.74 out
-
-
-
-
OpenRouter
75%
$0.75 in
$3.74 out
1.7s
43.4%
53.4%
$0.088
Anthropic
70%
$0.90 in
$4.50 out
-
-
-
$71
Concentrate.ai
60%
$1.20 in
$6.00 out
-
-
-
$0.980
Concentrate.ai
60%
$1.20 in
$6.00 out
-
-
-
-
Concentrate.ai
60%
$1.20 in
$6.00 out
-
-
-
-
Concentrate.ai
60%
$1.20 in
$6.00 out
-
-
-
-
Concentrate.ai
60%
$1.20 in
$6.00 out
-
-
-
-
Concentrate.ai
60%
$1.20 in
$6.00 out
-
-
-
-
Concentrate.ai
60%
$1.20 in
$6.00 out
-
-
-
-
Total
Cumulative offers
Sold
$293

Discount trend

Realized · 7 days
92.6%−6.8 pts vs last week
Best, twice dailyMedian 17.0%

Recent fills

23:10413 tokensAnthropic direct70.0%
23:09477 tokensAnthropic direct70.0%
23:09373 tokensAnthropic direct70.0%
23:09385 tokensAnthropic direct70.0%
23:09365 tokensAnthropic direct70.0%
23:09427 tokensAnthropic direct70.0%
23:08420 tokensAnthropic direct70.0%
23:08408 tokensAnthropic direct70.0%
23:08357 tokensAnthropic direct70.0%
23:0826 tokensVenice AI25.9%
23:08437 tokensAnthropic direct70.0%
23:08533 tokensAnthropic direct70.0%
23:07462 tokensAnthropic direct70.0%
23:07365 tokensAnthropic direct70.0%
23:07342 tokensVenice AI25.9%
23:069,721 tokensOpenRouter50.1%
23:06357 tokensAnthropic direct70.0%
23:05376 tokensAnthropic direct70.0%
23:05340 tokensAnthropic direct70.0%
23:05507 tokensAnthropic direct70.0%
Times in UTCSettled on Base in USDC.

Performance by provider route · 24h

Measured on Surplus traffic
Uncensored AI direct82% of traffic
80.8% success
p50 24.87 s · p95 61.18 s · 30 tok/s
Venice AI direct11% of traffic
99.8% success
p50 1.67 s · p95 5.55 s · -
OpenRouter7% of traffic
43.4% success
p50 33.57 s · p95 150.53 s · 30 tok/s
Use this model

Change your base URL.
Keep your code.

Any OpenAI-compatible client works. Add /min30 to the path to only buy at 30% off or better.

Read the quickstart ↗
Parameters this model acceptsPOST /v1/chat/completions
  • modelstringThis model’s id
  • messagesarrayThe conversation, as role and content pairs
  • streambooleanSend the answer as server-sent events
  • max_tokensintegerMost output tokens to generate
  • temperaturenumberSampling temperature
  • top_pnumberNucleus sampling
  • top_kintegerTop-k sampling
  • stopstring | arrayStop sequences
  • toolsarrayFunctions the model may call, in the OpenAI format
  • tool_choicestring | objectauto, required, none, or one named function
  • response_formatobjectJSON mode or a JSON schema for structured output
  • structured_outputsbooleanAccepts a JSON schema in response_format
  • reasoningobjectReasoning options as an object, such as {"effort": "high"}
  • include_reasoningbooleanStripped before the request reaches the provider
Context window 198K tokens · Max output 64K tokensOthers are passed through; most providers ignore what they don’t support. Parameter compatibility ↗
from openai import OpenAI

client = OpenAI(
    api_key="inf_your_key_here",
    base_url="$SURPLUS_BASE_URL"
)

response = client.chat.completions.create(
    model="claude-sonnet-4.5",
    messages=[{"role": "user",
               "content": "Hello!"}]
)

SURPLUS_BASE_URL
https://api.surplusintelligence.ai/v1

Related models