Requesty
Sign in

identity

open weights
Moonshot AI logo

kimi-k2.7-codeMoonshot AI

from /1M in$0.75inceptron ab
context262K262K out
best ttft700msinceptron ab
price spread1.7x4 endpoints
endpoints
4
regions
2
best tok/s
145
api
chat
released
June 2026
eu routing
available

capabilities 5/8

visionreasoningtoolscachingweb searchjson schemacomputer useimage gen

The same weights cost 1.7x more on tensorx ltd. than on inceptron ab. That is what the endpoints table is for.

endpoints

4 / 2 regions
Providers serving kimi-k2.7-code, with pricing and measured performance. Best value in each column is coloured.
#flags
1Inceptron ABEU256K$0.75$3.50$0.20700ms106.0zdr
2Fireworks AIGlobal262K$0.95$4.00$0.191.32s96.0zdr
3Moonshot AIGlobal262K$0.95$4.00$0.192.49s35.0-zdr
4TensorX Ltd.EU262K$1.25$4.50$0.31859ms145.0zdr
provider price, no markupper 1M tokensblank where no qualifying sample

measured

through Sep 12
median
-177ms3.42s7.03s07-0608-0309-075.58s1.55s1.48s990ms423ms
hover the plot for weekly values
time to first token per provider: current value, window low and high, and change across the window
providernowlowhighchange
Inceptron AB700ms423ms1.34s-68%
TensorX Ltd.859ms990ms2.11s-13%
Fireworks AI1.32s1.09s1.54s+8.6%
Parasail2.44s1.22s3.06s-32%
Moonshot AI2.49s2.00s6.42s+179%

median wait before the first token lands. this is the number a user feels, and it moves with provider load through the day.

Lines are steps: each sample is one week of traffic held flat, not a slide from the week before. Click a name in the key to drop it from the plot. Measured through Sep 12.

benchmarks

artificial analysis
Benchmark scores, each normalised to 100
evalScore as a share of 100/100
τ²-Bench90.1
GPQA Diamond89.6
Coding Index60.8
SciCode47.8
Terminal-Bench Hard44.7
Humanity's Last Exam35.0
Intelligence Index26.3
7 evalsmean56.3

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 2026-06-12.

call it

model=
kimi-k2.7-code

requesty routes this id across every provider serving kimi-k2.7-code, picking on price and health and failing over automatically. the id stays valid when a provider changes underneath it

Base url is https://router.requesty.ai/v1 for every id here. One key reaches the whole catalog.

quickstart

openai compatible
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="kimi-k2.7-code",    messages=[        {"role": "user", "content": "Explain quantum computing in one paragraph."},    ],) print(response.choices[0].message.content)

Change the base url, use your Requesty key, set the model to any id in the call pane. Existing OpenAI SDK code needs no other edit, and the same key reaches every other model in the catalog, so switching later is a one-parameter change. Browse all models

notes

reference

Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts architecture that accepts text and image input, and it always operates in a thinking mode, preserving full reasoning content across multi-turn conversations. With a 256K-token context window, it targets long-horizon coding, agentic task decomposition, and multi-turn dialogue. The model activates 32B parameters out of roughly 1T total.

questions 7

Which providers serve kimi-k2.7-code?
kimi-k2.7-code is available from 4 providers through Requesty: Inceptron AB, Fireworks AI, Moonshot AI, TensorX Ltd.. All endpoints share one OpenAI-compatible API and one key, and Requesty fails over between them automatically.
How much does kimi-k2.7-code cost?
Pricing starts at $0.75 per million input tokens and $3.50 per million output tokens on the cheapest provider. Prices vary by provider and region; the table above shows every endpoint. Requesty charges exactly what the upstream provider charges, with no markup.
Is kimi-k2.7-code open weights?
Yes. kimi-k2.7-code is an open-weights model from Moonshot AI, which is why multiple inference providers can host it. Provider choice affects price, latency, and data-privacy terms, all compared above.
What is the context window of kimi-k2.7-code?
kimi-k2.7-code supports up to 262K tokens of context, with up to 262K output tokens per response. Some providers expose a smaller window; check the per-endpoint context column above.
Which provider is fastest for kimi-k2.7-code?
In recent production traffic through Requesty, Inceptron AB had the lowest median time to first token (700ms) for kimi-k2.7-code. Latency shifts over time, so Requesty's latency-based routing picks the fastest healthy provider per request automatically.
How do I use kimi-k2.7-code 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 "kimi-k2.7-code" or any endpoint id from the table above. The quickstart section shows Python, JavaScript and cURL snippets.
Should I call kimi-k2.7-code by its managed id or a provider id?
Use the managed id, "kimi-k2.7-code". Requesty picks which of the 4 providers serves each request based on price and health, and fails over when one degrades, so the id keeps working while the routing changes underneath it. There is also an EU-only id, "kimi-k2.7-code@eu", which routes the same way but only through EU-hosted providers. Send a provider id like "inceptron/kimi-k2.7-Code" only when you need one specific deployment and want no failover.

more from moonshot ai 5

Other Moonshot AI models
modelcontextfrom /Mproviders
kimi-k31.0M$3.005
kimi-k2.6262K$0.605
kimi-k2.5262K$0.453
kimi-k2262K$0.601
kimi-k2-instruct131K$0.571

route kimi-k2.7-code through one endpoint

One key for 4 providers on this model and 600+ others. No markup on provider prices, automatic failover, caching built in. Weekly aggregates in the measured pane come from production traffic routed through Requesty, one line per provider on a shared axis. Methodology

kimi-k2.7-code4 providers4 endpointsfrom $0.75 /1M inctx 262Kttft 700msspread 1.7xupdated Sep 12