Kimi K2 Instruct
Kimi K2 Instruct
Version: 1
Fireworks•Last updated April 2026
Kimi K2 Instruct is an updated Mixture-of-Experts model with 1 trillion total parameters featuring improved coding abilities, agentic tool use, and an extended 256K token context window.
Coding
Agents

Fireworks on Foundry

Models available for use with Fireworks on Foundry deliver optimized, best-in-class performance on the Fireworks Inference Cloud. Fireworks on Foundry is a Preview subject to Azure Preview terms and the following supplemental terms: When you use Fireworks on Foundry, data is shared between Microsoft and Fireworks AI, and different compliance and data handling rules will apply. See documentation for details. Customers are responsible for evaluating whether data sharing between Microsoft and Fireworks is appropriate for their organization’s compliance requirements.

Key capabilities

About this model

Kimi K2-Instruct-0905 is an updated version of Kimi K2, a state-of-the-art mixture-of-experts (MoE) language model with 32 billion activated parameters and 1 trillion total parameters. Kimi K2-Instruct-0905 has improved coding abilities, agentic tool use, and a longer (262K) context window.

Key model capabilities

  • Enhanced agentic coding intelligence: Kimi K2-Instruct-0905 demonstrates significant improvements in performance on public benchmarks and real-world coding agent tasks.
  • Improved frontend coding experience: Kimi K2-Instruct-0905 offers advancements in both the aesthetics and practicality of frontend programming.
  • Extended context length: Kimi K2-Instruct-0905's context window has been increased from 128k to 256k tokens, providing better support for long-horizon tasks.

Use cases

See Responsible AI for additional considerations for responsible use.

Key use cases

  • Code assistance and agentic coding tasks
  • Frontend programming
  • Conversational AI
  • Tool-augmented interaction
  • Long-context reasoning (256K tokens)
  • Enterprise-grade retrieval-augmented generation (RAG)

Out of scope use cases

The provider has not supplied this information.

Pricing

Pricing is based on a number of factors, including deployment type and tokens used. See pricing details here.

Technical specs

The provider has not supplied this information.

Training cut-off date

The provider has not supplied this information.

Training time

The provider has not supplied this information.

Input formats

Text

Output formats

Text

Supported languages

English

Sample JSON response

The provider has not supplied this information.

Model architecture

Kimi K2-Instruct-0905 is a state-of-the-art mixture-of-experts (MoE) language model, featuring 32 billion activated parameters and a total of 1 trillion parameters.
PropertyValue
ArchitectureMixture-of-Experts (MoE)
Total Parameters1T
Activated Parameters32B
Number of Layers (Dense layer included)61
Number of Dense Layers1
Attention Hidden Dimension7168
MoE Hidden Dimension (per Expert)2048
Number of Attention Heads64
Number of Experts384
Selected Experts per Token8
Number of Shared Experts1
Vocabulary Size160K
Context Length256K
Attention MechanismMLA
Activation FunctionSwiGLU

Long context

Extended context length: Kimi K2-Instruct-0905's context window has been increased from 128k to 256k tokens, providing better support for long-horizon tasks.

Optimizing model performance

The provider has not supplied this information.

Additional assets

The provider has not supplied this information.

Training disclosure

Training, testing and validation

The provider has not supplied this information.

Distribution

Distribution channels

The provider has not supplied this information.

More information

The provider has not supplied this information.
Model Specifications
Context Length262144
LicenseOther
Last UpdatedApril 2026
Input TypeText
Output TypeText
ProviderFireworks
Languages1 Language