Moonshot AI

Kimi K2 Instruct

Generally availableOpen weights131K context

Summary

Kimi K2 Instruct is an open-weight language model from Moonshot AI, released on 11 Jul 2025. It accepts text and generates text, with a 131K-token context window and up to 131K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.57 per million input tokens and $2.30 per million output tokens (OpenRouter), across 2 providers we track.

Kimi model for long-context chat, coding, and agentic reasoning

Last verified 18 Nov 2026. Every figure on this page links to its source.

Specifications

DeveloperMoonshot AI
Release date11 Jul 2025 [models.dev]
StatusGenerally available [models.dev]
WeightsOpen weights [Hugging Face]
Licensemodified-mit [Hugging Face]
Parameters1T [Hugging Face]
Context window131K (131,072 tokens) [models.dev]
Max output131K tokens [models.dev]
Knowledge cutoff31 Dec 2024 [models.dev]
InputText [models.dev]
OutputText [models.dev]
Reasoning modeNo [models.dev]
Tool callingYes [models.dev]
Structured outputNo [models.dev]
Hugging Facemoonshotai/Kimi-K2-Instruct [Hugging Face]

Kimi K2 Instruct API pricing by provider

USD per million tokens. Sorted by input price.

ProviderInputOutputCached inputContextSource
OpenRouter
moonshotai/kimi-k2
$0.57$2.30–131KOpenRouter, 18 Nov 2026
Vercel AI Gateway
moonshotai/kimi-k2
$0.57$2.30–131Kmodels.dev, 18 Nov 2026

Running Kimi K2 Instruct locally

Estimated memory, from the parameter count and the architecture in config.json on Hugging Face. Includes about 0.8 GB of runtime overhead.

QuantizationWeightsTotal, 8K contextTotal, 32K context
Q4_K_M (4-bit)622 GB624 GB625 GB
Q8_0 (8-bit)1091 GB1092 GB1094 GB
FP16 / BF16 (16-bit)2053 GB2054 GB2056 GB

At 4-bit with an 8K conversation, Kimi K2 Instruct needs about 624 GB, more than any single consumer graphics card; it needs a unified-memory machine, a multi-GPU setup or a split between graphics card and system RAM. Check your own hardware, or see Best computer for local AI on our sister site AIPCs.

Frequently asked questions

What is the context window of Kimi K2 Instruct?

Kimi K2 Instruct has a context window of 131,072 tokens (131K) and can generate up to 131,072 tokens in a single response, according to models.dev.

How much does the Kimi K2 Instruct API cost?

Kimi K2 Instruct is listed from $0.57 per million input tokens and $2.30 per million output tokens (OpenRouter). Prices last verified 18 Nov 2026.

Is Kimi K2 Instruct open source?

Kimi K2 Instruct is an open-weight model: its weights are published on Hugging Face as moonshotai/Kimi-K2-Instruct under the modified-mit license. Check the license terms before commercial use.

When was Kimi K2 Instruct released?

Moonshot AI released Kimi K2 Instruct on 11 Jul 2025, according to models.dev.

Which providers offer Kimi K2 Instruct?

We track Kimi K2 Instruct on 2 providers: OpenRouter, Vercel AI Gateway.

How much VRAM does Kimi K2 Instruct need?

About 624 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 1092 GB at 8-bit. That is more than any single consumer graphics card holds. These are estimates from the model's published parameter count and architecture.

Similar models from other labs

Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.

ModelLabReleasedContextInput $/1MOutput $/1MWeights
GLM-4.5Zhipu AI (Z.ai)28 Jul 2025131K$0.60$2.20Open
DeepSeek-R1-0528DeepSeek28 May 2025164K$0.50$2.15Open
Hermes-4-405BNousresearch26 Aug 2025131K$1$3Open
Magistral Small 1.2Mistral AI18 Sept 2025128K$0.50$1.50Open
Qwen3-235B-A22B-Thinking-2507Alibaba (Qwen)25 Jul 2025262K$0.30$3Open
UncensoredCognitivecomputations9 Jul 2025128K$0.20$0.90Open

Change history

  • Max output changed from 98K to 131K
  • Name changed from Kimi K2 0711 to Kimi K2 Instruct
  • Max output changed from 131K to 98K
  • Name changed from Kimi K2 Instruct to Kimi K2 0711
  • Name changed from Kimi K2 0711 to Kimi K2 Instruct
  • Max output changed from 98K to 131K
  • Max output changed from 131K to 98K
  • Name changed from Kimi K2 Instruct to Kimi K2 0711
  • Max output changed from 98K to 131K
  • Name changed from Kimi K2 0711 to Kimi K2 Instruct
  • Name changed from Kimi K2 Instruct to Kimi K2 0711
  • Max output changed from 131K to 98K
  • Name changed from Kimi K2 0711 to Kimi K2 Instruct
  • Max output changed from 98K to 131K
  • Max output changed from 131K to 98K
  • Name changed from Kimi K2 Instruct to Kimi K2 0711
  • Max output changed from 98K to 131K
  • Name changed from Kimi K2 0711 to Kimi K2 Instruct
  • Max output changed from 131K to 98K
  • Name changed from Kimi K2 Instruct to Kimi K2 0711
  • Name changed from Kimi K2 0711 to Kimi K2 Instruct
  • Max output changed from 98K to 131K
  • Max output changed from 131K to 98K
  • Name changed from Kimi K2 Instruct to Kimi K2 0711
  • Name changed from Kimi K2 0711 to Kimi K2 Instruct

Sources