Skip to main content

Kimi K3 Fast

Live
Moonshot1M context · Text, Vision, Tools, ReasoningBenchmark price · $4.5 input / $22.5 output per 1M tokens
Use this model
Best discount now26.0%offYou pay 74.0% of reference.
Median discount20.0%offAcross 13 live offers.
Realized · 7 days31.4%avgRequest-weighted average.
Requests · 24h8413 offers from 12 sellers.
Current offers
13 of 42 offers
Availability
Providers
ProviderDiscountPriceLatencyUptimeCacheSold
Venice AI
26%
$3.33 in
$16.65 out
916ms
97.6%
60.4%
$0.089
Venice AI
25%
$3.38 in
$16.88 out
916ms
97.6%
60.4%
-
Venice AI
20%
$3.56 in
$17.82 out
916ms
97.6%
60.4%
$0.005
Venice AI
20%
$3.56 in
$17.82 out
916ms
97.6%
60.4%
-
Venice AI
20%
$3.60 in
$18.00 out
916ms
97.6%
60.4%
-
Venice AI
20%
$3.60 in
$18.00 out
916ms
97.6%
60.4%
-
Venice AI
20%
$3.60 in
$18.00 out
916ms
97.6%
60.4%
-
Venice AI
20%
$3.60 in
$18.00 out
916ms
97.6%
60.4%
$0.017
Venice AI
20%
$3.60 in
$18.00 out
916ms
97.6%
60.4%
-
Venice AI
20%
$3.60 in
$18.00 out
916ms
97.6%
60.4%
$0.002
Total
Cumulative offers
Sold
$0.112

Discount trend

Realized · 7 days
60.0%−11.5 pts vs last week
Best, twice dailyMedian 20.0%

Recent fills

15:59105 tokensVenice AI28.0%
15:29105 tokensVenice AI26.1%
14:58105 tokensVenice AI26.1%
14:401,089 tokensVenice AI26.0%
14:33796 tokensVenice AI26.0%
14:29808 tokensVenice AI26.0%
14:25784 tokensVenice AI26.0%
14:24105 tokensVenice AI26.1%
14:21832 tokensVenice AI26.0%
14:19822 tokensVenice AI26.0%
13:59105 tokensVenice AI26.1%
13:19105 tokensVenice AI26.2%
12:58105 tokensVenice AI26.2%
12:14105 tokensVenice AI26.2%
12:00105 tokensVenice AI26.2%
11:09105 tokensVenice AI26.2%
10:59105 tokensVenice AI26.2%
10:04105 tokensVenice AI26.2%
09:59105 tokensVenice AI30.0%
08:59105 tokensVenice AI30.0%
Times in UTCSettled on Base in USDC.

Performance by provider route · 24h

Measured on Surplus traffic
Venice AI direct100% of traffic
97.6% success
p50 1.67 s · p95 - · -
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
  • 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
  • reasoning_effortstringHow hard to think, as a string such as "high"
  • reasoningobjectReasoning options as an object, such as {"effort": "high"}
  • include_reasoningbooleanStripped before the request reaches the provider
  • frequency_penaltynumberPenalises tokens by how often they appeared
  • presence_penaltynumberPenalises tokens that appeared at all
Context window 1M tokens · Max output 131K 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="kimi-k3-fast-api",
    messages=[{"role": "user",
               "content": "Hello!"}]
)

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

Related models