Kimi K2.5
Kimi K2.5
Version: 1
FireworksLast updated April 2026
Kimi K2.5 is an open-source, native multimodal agentic model built through continual pretraining on approximately 15 trillion mixed visual and text tokens atop Kimi-K2-Base.
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 K2.5 is Moonshot AI's flagship agentic model and a new SOTA open model. It is an open-source, native multimodal agentic model built through continual pretraining on approximately 15 trillion mixed visual and text tokens atop Kimi-K2-Base. It unifies vision and text, thinking and non-thinking modes, and single-agent and multi-agent execution into one model. Users can control the reasoning behavior of the Kimi K2.5 model and inspect its reasoning history for greater transparency.

Key model capabilities

  • Native multimodal: unifies vision and text understanding
  • Dual reasoning modes: instant (non-thinking) and thinking
  • Agent swarm: supports single-agent and multi-agent execution
  • 256K token context window
  • Function calling and tool use

Use cases

See Responsible AI for additional considerations for responsible use.

Key use cases

  • Native Multimodality
  • Agent Swarm
  • Coding with Vision

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 K2.5 is built on the Kimi K2 base, a Mixture-of-Experts (MoE) language model with 1 trillion total parameters and 32 billion activated parameters per forward pass, with continual pretraining on approximately 15 trillion mixed visual and text tokens.
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

Context Length: 256K

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