The Orchestrator › Models › Moonshot AI

Moonshot AI: MoonshotAI: Kimi K2.7 Code

MoonshotAI: 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...

Specifications

ProviderMoonshot AI
Model IDmoonshotai/kimi-k2.7-code
Context window262K tokens (262,144)
Modalitiestext + image → text
TokenizerOther
Router sourcesOpenRouter, TrustedRouter, Vercel AI Gateway, Cloudflare
Released2026-06-12
Tracked since2026-11-14
PopularityNot in the ranked set
ReasoningMandatory

Pricing (per million tokens)

VariantSourceAPI IDInputOutputContext
standardOpenRoutermoonshotai/kimi-k2.7-code$0.6$3.50262K
standardTrustedRoutermoonshotai/kimi-k2-7-code$0.791$3.69256K
standardVercel AI Gatewaymoonshotai/kimi-k2.7-code$0.95$4.00256K
standardCloudflaremoonshotai/kimi-k2.7-code$0.95$4.00—

Recorded price history

DateInput / 1MOutput / 1MContext
2026-11-14$0.95$4.00—
2026-11-14$0.95$4.00256K
2026-11-14$0.791$3.69256K
2026-11-14$0.633$3.17262K
2026-11-14$0.6$3.50262K

Capabilities

Vision (image input)Agentic tool useStructured outputsReasoning (always on)256K+ context windowControllable reasoningNo content storage (attested)Zero data retentionNo training on inputs (attested)

Trust flags come from TrustedRouter's per-provider attestations.

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