Skip to main content

Kimi K2 Thinking

Live
Moonshot256K context · Text, Tools, ReasoningBenchmark price · $0.6 input / $2.5 output per 1M tokens
Use this model
Best discount now99.0%offYou pay 1.0% of reference.
Median discount94.0%offAcross 188 live offers.
Realized · 7 days98.9%avgRequest-weighted average.
Requests · 24h2,000188 offers from 32 sellers.
Current offers
188 of 257 offers
Availability
Providers
ProviderDiscountPriceLatencyUptimeCacheSold
Amazon Bedrock
99%
$0.00594 in
$0.0248 out
679ms
71.5%
31.5%
$0.672
Amazon Bedrock
99%
$0.00594 in
$0.0248 out
679ms
71.5%
31.5%
$0.648
Amazon Bedrock
99%
$0.00594 in
$0.0248 out
679ms
71.5%
31.5%
$0.569
Amazon Bedrock
99%
$0.00594 in
$0.0248 out
679ms
71.5%
31.5%
$0.269
Amazon Bedrock
99%
$0.00594 in
$0.0248 out
679ms
71.5%
31.5%
$0.104
Amazon Bedrock
99%
$0.00594 in
$0.0248 out
679ms
71.5%
31.5%
$0.085
Amazon Bedrock
99%
$0.00594 in
$0.0248 out
679ms
71.5%
31.5%
$0.044
Amazon Bedrock
99%
$0.00594 in
$0.0248 out
679ms
71.5%
31.5%
$0.017
Amazon Bedrock
99%
$0.00594 in
$0.0248 out
679ms
71.5%
31.5%
$0.015
Amazon Bedrock
99%
$0.00600 in
$0.0250 out
679ms
71.5%
31.5%
$0.009
Total
Cumulative offers
Sold
$2

Discount trend

Realized · 7 days
99.5%+0.0 pts vs last week
Best, twice dailyMedian 94.0%

Recent fills

23:381,140 tokensAWS Bedrock98.8%
23:381,140 tokensAWS Bedrock98.8%
23:381,140 tokensAWS Bedrock98.8%
23:3539 tokensAWS Bedrock98.8%
23:331,140 tokensAWS Bedrock98.8%
23:331,140 tokensAWS Bedrock98.8%
23:331,140 tokensAWS Bedrock98.8%
23:3028 tokensAWS Bedrock100.0%
23:281,140 tokensAWS Bedrock98.8%
23:281,140 tokensAWS Bedrock98.8%
23:281,140 tokensAWS Bedrock98.8%
23:25101 tokensAWS Bedrock98.9%
23:231,140 tokensAWS Bedrock98.8%
23:231,140 tokensAWS Bedrock98.8%
23:231,140 tokensAWS Bedrock98.8%
23:2047 tokensAWS Bedrock99.0%
23:2028 tokensAWS Bedrock100.0%
23:181,140 tokensAWS Bedrock98.8%
23:181,140 tokensAWS Bedrock98.8%
23:181,140 tokensAWS Bedrock98.8%
Times in UTCSettled on Base in USDC.

Performance by provider route · 24h

Measured on Surplus traffic
AWS Bedrock100% of traffic
71.5% success
p50 679 ms · p95 4.11 s · 329 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
  • min_pnumberDrops tokens below this share of the top token’s probability
  • stopstring | arrayStop sequences
  • seedintegerDeterministic sampling
  • 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
  • frequency_penaltynumberPenalises tokens by how often they appeared
  • presence_penaltynumberPenalises tokens that appeared at all
  • repetition_penaltynumberPenalises repeated tokens
  • logit_biasobjectPer-token bias on the logits
Context window 256K tokens · Max output 66K 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-k2-thinking",
    messages=[{"role": "user",
               "content": "Hello!"}]
)

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

Related models