Kimi K2.7 Code.
Kimi K2.7 Code is a modified-MIT coding agent model, 1T total and 32B active, with image and text input and a 256K context, built on Kimi K2.6.
8× Nvidia A100 SXM4 · $5.73/hr.
Most-aggressive quantisation we have a working recommendation for. Lower precision = less VRAM = cheaper hardware, at a small accuracy cost.
Cheapest hosted endpoints.
Variants in the Kimi family.
Moonshot's frontier open-weight MoE — 1T total, 32B active.
Moonshot's open-weight reasoning variant — extended chain-of-thought training...
Multimodal agentic variant — adds a vision encoder to the K2 backbone.
Long-horizon coding + autonomous-execution upgrade over K2.5.
Kimi K3 is Moonshot AI's open-weight multimodal agentic model, 2.8T parameter...
Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning mode...
Kimi K2 0905 is a modified-MIT mixture-of-experts model, 1T total and 32B act...
Cheapest hardware per quantisation.
Each row is one quantisation tier (the same weights compressed differently). Lower precision → lower VRAM → cheaper hardware, at the cost of small accuracy loss. $/h es la tarifa más baja disponible ahora. Una configuración multitarjeta usa una instancia real de ese tamaño cuando se alquila; si no, es la tarifa de una tarjeta por el número de tarjetas.
| Quantisation | Cheapest GPU config | Total VRAM | Live $/hr | tokens/sec | |
|---|---|---|---|---|---|
|
FP8
FP8 — 8-bit float (Hopper / Blackwell)
|
1536 GB |
$22.60/hr
Cyfuture AI · bajo demanda
|
— | Compare → | |
|
INT4
INT4 — 4-bit integer (~4× VRAM saving)
|
640 GB |
$5.73/hr
est. 8 × tarifa de una tarjeta
Nosana · bajo demanda
|
— | Compare → |
What it costs per month across providers.
Estimate your monthly bill for Kimi K2.7 Code across every host that publishes per-token pricing. Slide your token volumes; the chart + table re-rank cheapest-first.
El proveedor más barato, a la izquierda.
Coste mensual total — tokens de entrada y salida juntos.
Desglose de la factura.
| Proveedor | Total mensual | |
|---|---|---|
| $13.0 | Registrarse ↗ | |
| $17.5 | Registrarse ↗ |
Alquila la GPU en lugar de pagar por token.
Para un modelo de pesos abiertos como Kimi K2.7 Code, puedes alquilar una GPU y servir la inferencia tú mismo. La cuenta: alquiler de GPU más barato × 730 horas/mes. La electricidad ya está incluida en el precio por hora del alquiler.
Supone que la GPU funciona 24/7 con ~85 % de uso. Si tu tráfico es irregular, pagarás menos por la API y probablemente más por la GPU (las horas ociosas también se cobran). El análisis del punto de equilibrio está en la herramienta de punto de equilibrio autoalojar vs. API.
About Kimi K2.7 Code.
Kimi K2.7 Code is a coding-focused agentic model from Moonshot AI, built on Kimi K2.6, with open weights under a modified MIT licence. It is a mixture-of-experts model with 1T parameters in total and 32B active, plus a 400M vision encoder, so it takes images as well as text. Context length is 256K tokens. Moonshot aims it at long software engineering tasks carried through to the end, and says it spends fewer thinking tokens than K2.6.