LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Kimi K2 Instruct

moonshotai·moonshotai/kimi-k2-instruct·GA·Open weights·kimi-k2 series
Non-thinking Kimi K2 MoE instruction model for coding and tool-using agents

Specs & pricing

Input / output per 1M tokens
Official price
—
Lowest paid·NanoGPTGateway
$0.40 / $1.80
Blended $0.75 · 2.5× spread
Context
131,072
Output limit
16,384
Knowledge cutoff
2024-10
Released / updated
2025-07-11 / 2025-07-11
Capabilities
Reasoning✓ Tool useStructured output✓ TemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
TextPDF
License
Modified MIT
Weights
Hugging Face

Kimi K2 Instruct by moonshotai is offered by 7 providers on this page. No official API price is listed for it; the prices below come from third-party channels. The lowest paid channel is NanoGPT at $0.40 / $1.80 per 1M. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. Prices vary about 2.5× across the providers that host it.

The context window is 131,072 tokens at the reference host, but hosts report different limits, from 128,000 to 256,000, so the usable window depends on the provider you pick. It supports tool use. Accepted input modalities are Text and PDF. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2024-10.

Available at 7 providers7 with public prices

  • ProviderInput / Output
  • NanoGPTGateway
    kimi-k2-instruct-fast
    $0.40 / $1.80
    Cache read $0.20Context 131,072Output limit 16,384deprecated
  • NanoGPTGateway
    $0.40 / $1.80
    Cache read $0.20Context 256,000 ⚠Output limit 8,192
  • NanoGPTGateway
    moonshotai/kimi-k2-instruct-0711
    $0.40 / $1.80
    Cache read $0.20Context 128,000 ⚠Output limit 8,192
  • Eden AIGateway
    deepinfra/moonshotai/Kimi-K2-Instruct
    $0.50 / $2.00
    Context 131,072Output limit 32,768
  • Jiekou.AIGateway
    $0.57 / $2.30
    Context 131,072Output limit 100,352
  • Novita AIGateway
    $0.57 / $2.30
    Context 131,072Output limit 98,304
  • Hugging FaceCloud
    moonshotai/Kimi-K2-Instruct
    $1.00 / $3.00
    Context 131,072Output limit 16,384
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
NanoGPT
kimi-k2-instruct-fast
Gateway$0.40$1.80$0.20—131,07216,384deprecated
NanoGPTGateway$0.40$1.80$0.20—256,000 ⚠8,192
NanoGPT
moonshotai/kimi-k2-instruct-0711
Gateway$0.40$1.80$0.20—128,000 ⚠8,192
Eden AI
deepinfra/moonshotai/Kimi-K2-Instruct
Gateway$0.50$2.00——131,07232,768
Jiekou.AIGateway$0.57$2.30——131,072100,352
Novita AIGateway$0.57$2.30——131,07298,304
Hugging Face
moonshotai/Kimi-K2-Instruct
Cloud$1.00$3.00——131,07216,384

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

Common scenarios
1NanoGPT$146.00
2NanoGPT$146.00
3NanoGPT$146.00
4Eden AI$200.00
5Jiekou.AI$229.00
6Novita AI$229.00
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input list —Output list —Min blended $0.75

Price history accumulates from each data sync; currently only 1 sample(s) (2026-08-05). Each future sync adds a point, and once accumulated a line is drawn here.

Related models

Kimi K2.8 Previewsame series—Kimi K2.7 Codesame series$0.95 / $4.00Kimi K2.7 Code Highspeedsame series—Kimi K2 Instruct 0905same lab—Kimi K2 Thinkingsame lab—
Data partly from models.dev (MIT)