Model provider cost

Host Kimi K2.7 Code on RunPod

Kimi K2.7 Code needs 8x 80GB+ GPUs, and RunPod's current cheapest qualifying row is A100 PCIE at $11.12/hr.

8x 80GB+ GPUs 1059B params Kimi coding flagship Modified MIT
Cheapest on this provider
$11.12/hr
A100 PCIE
Monthly estimate
$8,118/mo
730 hours at the current median
VRAM baseline
80GB
8x 80GB+ GPUs
Qualifying rows
8
Updated Jul 27, 2026

RunPod rows that can host Kimi K2.7 Code

The cheapest tracked way to host Kimi K2.7 Code on RunPod is A100 PCIE at $11.12/hr. The overall tracked market floor is $8.02/hr on Vast.ai, so RunPod is $3.10/hr above the current floor.

Price source RunPod GraphQL API Provider API pricing; availability and spot/community rows can move quickly.
GPU VRAM Per GPU Estimated hourly Estimated monthly Offers Updated
A100 PCIE 80GB $1.39/hr $11.12/hr $8,118/mo 1 Jul 27, 2026
RunPod GraphQL API 1 offer · Jul 27, 2026 global aggregate
A100 SXM4 80GB $1.49/hr $11.92/hr $8,702/mo 1 Jul 27, 2026
RunPod GraphQL API 1 offer · Jul 27, 2026 global aggregate
MI300X 192GB $2.39/hr $19.12/hr $13,958/mo 1 Jul 27, 2026
RunPod GraphQL API 1 offer · Jul 27, 2026 global aggregate
H100 PCIE 80GB $2.89/hr $23.12/hr $16,878/mo 1 Jul 27, 2026
RunPod GraphQL API 1 offer · Jul 27, 2026 global aggregate
H100 SXM 80GB $2.99/hr $23.92/hr $17,462/mo 1 Jul 27, 2026
RunPod GraphQL API 1 offer · Jul 27, 2026 global aggregate
H100 NVL 94GB $3.19/hr $25.52/hr $18,630/mo 1 Jul 27, 2026
RunPod GraphQL API 1 offer · Jul 27, 2026 global aggregate
H200 NVL 141GB $3.79/hr $30.32/hr $22,134/mo 1 Jul 27, 2026
RunPod GraphQL API 1 offer · Jul 27, 2026 global aggregate
H200 141GB $4.39/hr $35.12/hr $25,638/mo 1 Jul 27, 2026
RunPod GraphQL API 1 offer · Jul 27, 2026 global aggregate

Why this setup does or does not fit

VRAM floor

8x 80GB+ GPUs

8x 80GB GPUs minimum, with fast interconnects. Long prompts, batching, and KV cache can require extra headroom.

Model quality

Kimi coding flagship

A genuinely current open coding model, but self-hosting it is a cluster decision rather than a simple endpoint choice.

Operational note

Kimi 1059B

The 32B active path helps compute efficiency; the trillion-parameter expert pool still drives memory, download, and startup cost.

Kimi K2.7 Code on RunPod FAQ

Can I host Kimi K2.7 Code on RunPod?

The cheapest tracked way to host Kimi K2.7 Code on RunPod is A100 PCIE at $11.12/hr.

What GPU memory does Kimi K2.7 Code need?

Our baseline for Kimi K2.7 Code is 8x 80GB+ GPUs. The practical recommendation is 8x 80GB GPUs minimum, with fast interconnects.

Is RunPod the cheapest provider for Kimi K2.7 Code?

The overall tracked market floor is $8.02/hr on Vast.ai, so RunPod is $3.10/hr above the current floor.

How fresh is this RunPod Kimi K2.7 Code cost page?

This page recalculates from the latest tracked on-demand rows. The freshest qualifying RunPod row shown here is from Jul 27, 2026.

Compare this 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.

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/runpod. 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