Kimi · Kimi coding flagship

Host Kimi K2.7 Code

Moonshot's current open-weight coding flagship for long-horizon software work, tools, images, and video input.

Customize workload
Parameters
1059B
Context
262,144 tokens
Baseline
640GB VRAM
Quantization
Native INT4 MoE weights

Current hosting recommendations

Default interactive workload, 8K context, one concurrent request, always on.

36 qualifying tracked rows
Lowest cost

More evidence needed

Kimi K2.7 Code needs at least 8 co-located GPUs plus a verified interconnect. Per-GPU price rows do not prove that topology is available.

Review workload inputs
Balanced fit

More evidence needed

Kimi K2.7 Code needs at least 8 co-located GPUs plus a verified interconnect. Per-GPU price rows do not prove that topology is available.

Review workload inputs
Production

More evidence needed

Kimi K2.7 Code needs at least 8 co-located GPUs plus a verified interconnect. Per-GPU price rows do not prove that topology is available.

Review workload inputs

Planning floor

A planning floor derived from catalog VRAM, quantization, context, concurrency, and traffic headroom; benchmark the final runtime before purchase.

Total VRAM
640GB
Per GPU
80GB
GPU count
8

Continue the decision

Change traffic and uptimeRecalculate cost and headroom for your workload. Kimi K2.7 Code on RunPodInspect provider-specific qualifying rows. Compare other modelsReview quality, memory, and hosting envelopes.
Agent-assisted setup

Hand this runbook to Claude Code or Codex

Open a terminal in the repository where you want the deployment files, start claude or codex, then paste this prompt. It asks the agent to verify sources and stop before it creates billable infrastructure.

Claude Code quickstart ↗ Codex docs ↗
Deployment prompt 
Use the infrastructure or model context on this page to create a reproducible open-model deployment. Use this guide as the starting context: https://www.getflops.ai/llms/kimi-k2.7-code. Read the linked model card and provider documentation before choosing hardware or runtime settings. Open every linked primary source and flag any mismatch instead of guessing. Create a deployment folder containing README.md, .env.example with no secrets, a pinned start script or infrastructure manifest, and smoke-test.sh. Make the endpoint OpenAI-compatible where the runtime supports it. Run local/static validation, estimate the billable resources, and stop before provisioning paid infrastructure until I approve.
Guardrails included No secrets in files · verify primary docs · approval before spend