Kimi K2.7 Code API model profile

Evidence snapshot: 2026-08-12

Kimi K2.7 Code is a Moonshot AI model profile with a 262,144-token context window. The dated catalog snapshot records text, image modalities and interfaces for agentic, coding, prompt caching, reasoning, reasoning controls.

Kimi K2.7 Code is available under the Kendr alias kc-kimi-k2.7-code. Current account availability and customer credit quotes come from Kendr's live public model API and applicable account policy.

Kimi K2.7 Code accepts text and image and returns text. The snapshot records agentic, coding, prompt caching, reasoning, reasoning controls, structured output, text generation, tool calling, tools, and vision as capabilities or interfaces.

Kimi K2.7 Code ranked #55 in the cited trailing-7-day third-party catalog usage dataset as of 2026-08-12. Observed within the cited trailing-7-day third-party catalog usage dataset; this is not global AI market share.

Profile data was reviewed for the 2026-08-12 snapshot. Claims retain their source dates, and unavailable fields are shown as unavailable instead of estimated.

Profile facts

Profile type: Kendr API model
Kendr API alias: kc-kimi-k2.7-code
Model developer: Moonshot AI
Kendr route provider: Provider-routed Kimi
Context window: 262K
Snapshot date: 2026-08-12
Reference catalog ID: moonshotai/kimi-k2.7-code

Context, modalities, and identity

Model developer: Moonshot AI
Kendr route provider: Provider-routed Kimi
Context window: 262K
Maximum output: 262,144 tokens
Input modalities: text and image
Output modalities: text
Knowledge cutoff: Not disclosed

Capabilities and supported controls

Capabilities and parameters are reported from the dated catalog and source records; their presence does not guarantee identical behavior across every provider route.

Supported parameters: frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, parallel_tool_calls, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p

agentic
coding
prompt caching
reasoning
reasoning controls
structured output
text generation
tool calling
tools
vision

Dated pricing snapshot

Reference figures are dated 2026-08-12; the live Kendr quote can differ by selected provider route, context tier, caching, tools, region, and current rate card.

Price date: 2026-08-12
Input: $0.67 per 1M tokens
Cached input: $0.15 per 1M tokens
Output: $3.4 per 1M tokens

Benchmark evidence and limitations

Third-party catalog fields normalized from the cited model dataset; benchmark methodology and coverage differ by source.

Intelligence Index: 43
Coding Index: 60.8
Agentic Index: 30.3

Design Arena category	Elo	Win rate	Rank
agenticgamedev	1137	43%	#16
androidnative	1167	47%	#23
fullstack	1210	53.6%	#13
godotgamedev	1184	49.2%	#12
htmlslides	1231	54.1%	#7
mobileapps	1205	50.8%	#18
python-pptxslides	1160	44%	#15
webapps	1216	48.5%	#19
3d	1298	52.4%	#19
asciiart	1247	51.9%	#14
codecategories	1285	52.5%	#21
dataviz	1250	50.7%	#33
gamedev	1256	50.2%	#29
svg	1218	48.3%	#23
uicomponent	1294	53%	#20
website	1293	54.1%	#16

Popularity and market context

Third-party catalog rank: #55
Global market share: Not inferred
Observation date: 2026-08-12

OpenAI-compatible API example

This example applies to the published Kendr alias on this hosted profile. Check the live public catalog before use.

curl https://api.kendr.org/v1/chat/completions \
  -H "Authorization: Bearer $KENDR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"kc-kimi-k2.7-code","messages":[{"role":"user","content":"Hello"}]}'

Frequently asked questions

What is Kimi K2.7 Code?

What context window does Kimi K2.7 Code have?

The dated profile lists 262K of context and up to 262,144 output tokens. Provider routes, variants, and runtime configuration can impose lower effective limits.

What benchmark evidence is available for Kimi K2.7 Code?

The 2026-08-12 snapshot includes 3 Artificial Analysis indexes and 16 Design Arena categories. Publisher-reported launch results are labeled and are not presented as Kendr measurements; scores from different suites are not treated as interchangeable. Third-party catalog fields normalized from the cited model dataset; benchmark methodology and coverage differ by source.

What is the Kendr API alias for Kimi K2.7 Code?

Use kc-kimi-k2.7-code as the model value. The live public model API and signed-in catalog remain authoritative for route availability and customer credit quotes.

How is Kimi K2.7 Code priced on Kendr?

The dated reference snapshot lists $0.67 input and $3.4 output per million tokens. Cached input is $0.15 per million tokens. The separately published provider-route reference is Provider-specific (QwenCloud $0.95 / $4 ($0.19/M cached); direct route priced separately). Kendr applies one 5% markup to configured provider model cost; the live quote and settled routing receipt are authoritative for a request.

Sources and evidence dates

Kimi K2.7 Code third-party catalog record (catalog, checked 2026-08-12)
Third-party model catalog methodology (methodology, checked 2026-08-12)
Moonshot AI official model documentation (primary, checked 2026-08-12)
Artificial Analysis capability indices methodology (benchmark, checked 2026-08-12)
Design Arena leaderboard and methodology (benchmark, checked 2026-08-12)
Kimi K2.7 Code provider or route reference (primary, checked 2026-08-12)