Requesty
Sign in

identity

open weights
Novita AI logo

moonshotai/kimi-k2-instructNovita AI

in /1M$0.57input tokens
out /1M$2.30output tokens
context131Ktokens
trainingnoon your prompts
api
chat
hosting
US
model lab
Moonshot AI
weights
open
added
July 2025
model id
novita/moonshotai/kimi-k2-instruct

capabilities 1/8

visionreasoningtoolscachingweb searchjson schemacomputer useimage gen

pricing

no markup
input
$0.57
output
$2.30
cache write
-
cache read
-

worked cost

Estimated cost for three request volumes
volumecost
100K in + 10K out$0.0800
1M in + 100K out$0.80
10M in + 1M out$8.00

Requesty charges what the upstream provider charges, with no markup and no per-request fee. Prompt caching and smart routing cut the effective cost further on repeated context. Gateway pricing

provider price, passed throughper 1M tokens

measured

through Sep 12

no measured traffic for this endpoint yet. pricing above is the provider's own

benchmarks

artificial analysis
Benchmark scores, each normalised to 100
evalScore as a share of 100/100
Math Index94.7
AIME 202594.7
τ²-Bench93.0
LiveCodeBench85.3
MMLU Pro84.8
GPQA Diamond83.8
Terminal-Bench Hard31.1
Humanity's Last Exam23.8
Intelligence Index22.0
9 evalsmean68.1

Scores from Artificial Analysis and public leaderboards, normalised to 100. Bar colour is the band, not the rank: green 80 and up, blue 55 and up, amber 30 and up. Benchmarks measure narrow skills, so test on your own workload before committing. Released 2025-11-06.

policy

data terms
retention
none
trains on prompts
no
hosted in
US

Terms are the provider's, not Requesty's: routing a request here puts it under them. Novita AI Privacy Policy

Need every request to stay in one jurisdiction? EU hosting routes only through EU-hosted providers.

quickstart

openai compatible
novita/moonshotai/kimi-k2-instruct

this id pins the novita ai deployment, with no routing and no failover. the managed id on the canonical page routes across all 1 providers instead

main.py
from openai import OpenAI client = OpenAI(    api_key="YOUR_REQUESTY_API_KEY",    base_url="https://router.requesty.ai/v1",) response = client.chat.completions.create(    model="novita/moonshotai/kimi-k2-instruct",    messages=[        {"role": "user", "content": "Explain quantum computing in one paragraph."},    ],) print(response.choices[0].message.content)

Change the base url to https://router.requesty.ai/v1, use your Requesty key, set the model to the id above. Existing OpenAI SDK code needs no other edit, and the same key reaches every other model in the catalog. Browse all models

notes

reference

Kimi K2 Instruct

questions 6

How much does moonshotai/kimi-k2-instruct cost?
moonshotai/kimi-k2-instruct is priced at $0.57 per million input tokens and $2.30 per million output tokens when accessed via Requesty. Requesty charges exactly what the upstream provider charges, we don't add markup.
What is the context window of moonshotai/kimi-k2-instruct?
moonshotai/kimi-k2-instruct has a context window of 131K tokens. That is roughly 175 words of input you can fit in a single prompt.
How does moonshotai/kimi-k2-instruct perform on benchmarks?
moonshotai/kimi-k2-instruct scores 94.7% on Math Index, 94.7% on AIME 2025, 93.0% on τ²-Bench. The benchmarks pane shows every published result, each normalised to 100.
What can moonshotai/kimi-k2-instruct do?
moonshotai/kimi-k2-instruct supports tool calling. You can call it through any OpenAI-compatible client by pointing base_url to Requesty.
How do I use moonshotai/kimi-k2-instruct with the OpenAI SDK?
Install the OpenAI SDK, set base_url to "https://router.requesty.ai/v1", set your API key to your Requesty key, and set the model to "novita/moonshotai/kimi-k2-instruct". The quickstart pane shows Python, JavaScript and cURL snippets.
Can I run moonshotai/kimi-k2-instruct through Requesty?
Yes. moonshotai/kimi-k2-instruct runs through Requesty's OpenAI-compatible API, served from Novita AI. You do not host the model yourself: point base_url at Requesty, set the model to "novita/moonshotai/kimi-k2-instruct", and requests are routed to the upstream provider with automatic failover. The same key gives you 600+ other models too.

more from novita ai 8

Other Novita AI endpoints
endpointctxin /M
deepseek-v4.1-flash1.0M$0.30
glm-5.3-flash1.0M$0.15
inclusionai/ling-3.0-tiny262Kfree
qwen/qwen3.8-max1M$2.00
deepseek-v4-flash-07311.0M$0.14
tencent/hy3262K$0.14
stepfun/step-3.7-flash262K$0.20
inclusionai/ring-2.6-1t262K$0.30

call moonshotai/kimi-k2-instruct through one endpoint

One key for this endpoint and 600+ other models. No markup on provider prices, automatic failover when a provider degrades, and prompt caching built in. Methodology

moonshotai/kimi-k2-instructnovita aiin $0.57 /1Mout $2.30 /1Mctx 131Khosted US