Moonshot AI · Official-source model record
Kimi-K2.6
Kimi · Version Kimi-K2.6
Publisher-sourced inventory. Specifications come from official documentation and model cards. “Not documented” means we have no verified value. This inventory is separate from our editorial reviews.
Coverage & sources ↗Current catalog answers
What to know about Kimi-K2.6
AI-compiled from linked model documentation. This is a catalog reference, not an independent performance review. Catalog checked October 23, 2026.
How can you access Kimi-K2.6?
The catalog documents API and Open weights access for Kimi-K2.6. Source 1 · Source 2
As of the catalog check, this version was listed as available. Source
For API use, confirm the exact model identifier, your account and region, and the endpoint's current limits in the linked documentation. An API listing does not establish access through a consumer subscription.
Open weights means the model weights are distributed for use under their stated terms. It does not establish a hosted API, an open-source license, or a hardware requirement. This record documents API access separately.
Which Kimi-K2.6 does this page describe?
Kimi-K2.6 is a model record from Moonshot AI in the Kimi family. Source
The recorded model identifier or checkpoint is Kimi-K2.6. Use that exact identifier when checking documentation or a provider listing. Source
What are Kimi-K2.6's context and output limits?
The documented context window is 256,000 tokens. Source
A separate maximum-output value is not established in this record. The context or input figure should not be used as an output allowance.
Context, input and output limits describe different constraints. Do not add the figures together to infer a larger window. Check the endpoint's accounting for conversation history, system instructions, tools, media and generated tokens; a documented maximum is not a guarantee of answer quality or a measured usable capacity.
What can Kimi-K2.6 receive and generate?
Documented inputs: text and image. Source
Documented outputs: text. Source
Input support and output generation are separate capabilities. Reading an image does not establish image generation; a text output listing does not establish speech output. File sizes, formats and media limits depend on the documented implementation.
What license is recorded for Kimi-K2.6?
The recorded license label is modified-mit. Source
Read the linked license and associated use terms for this exact version before redistribution, commercial deployment or fine-tuning. A label alone does not establish every permission, restriction or obligation, and it does not determine the terms of a separate hosted service.
What is documented about the Kimi-K2.6 checkpoint?
This evidence refers to moonshotai/Kimi-K2.6 at recorded revision 7eb5002f6aadc958aed6a9177b7ed26bb94011bb, checked October 23, 2026. Repository metadata
Safetensors metadata records 1,026,879,376,368 stored parameters. This is a stored-weight count, not necessarily the number activated per token, a download size or a GPU-memory requirement. Repository metadata
Recorded architecture class: KimiK25ForConditionalGeneration. Repository metadata
Repository task tag: image-text-to-text. A task tag identifies a distribution category; it does not measure performance on that task. Repository metadata
Listed library: transformers. Check that library's version and model support before loading the weights. Repository metadata
Repository access gate: false. This records the repository's gate setting when checked; licensing and use terms still apply. Repository metadata
What the configuration file says
The pinned config.json section text_config contains these values. Pinned configuration
max_position_embeddings- 262,144
rope_scaling- {"beta_fast":32,"beta_slow":1,"factor":64,"mscale":1,"mscale_all_dim":1,"original_max_position_embeddings":4096,"type":"yarn"}
torch_dtype- bfloat16
num_attention_heads- 64
num_key_value_heads- 64
num_hidden_layers- 61
hidden_size- 7,168
Configuration values describe the checkpoint and its implementation. In particular, max_position_embeddings, sliding_window and rope_scaling do not independently establish an API context limit, tested usable length or hardware requirement. Runtime, quantization, cache, batch size and input length affect deployment behavior.
Read the retrieved model card for setup and qualifications. Model card
Keep the exact version in view
Other Kimi models from Moonshot AI.
These are separate records in the same publisher family. A shared family name does not establish equal capabilities or interchangeable licenses.
Kimi-Dev-72B
Open weights
Kimi-K2-Base
Open weights
Kimi-K2-Instruct
Open weights
Kimi-K2-Instruct-0905
Open weights
Kimi-K2-Thinking
Open weights
Kimi-K2.5
Open weights
The documented record
Specifications, with their sources.
A missing value remains unknown. Input limits, output limits and the total context window are separate measurements.
- Publisher
- Moonshot AISource ↗
- Family
- KimiSource ↗
- Version
- Kimi-K2.6Source ↗
- Availability
- AvailableSource ↗
- Access
- API · Open weightsSource 1 ↗Source 2 ↗
- Inputs
- Text · ImageSource ↗
- Outputs
- TextSource ↗
- Context window
- 256,000 tokensSource ↗
- Maximum input
- Not documented
- Maximum output
- Not documented
- Knowledge cutoff
- Not documented
- Training-data cutoff
- Not documented
- Training completed
- Not documented
- Release date
- Not documented
- License
- modified-mitSource ↗
- Input price / 1M tokens
- Not documented
- Output price / 1M tokens
- Not documented
Read this with the numbers.
Official publisher weight listing; availability refers to this distribution, not a guaranteed hosted API. Base, SFT and research variants are identified by their exact published names. Official context label is 256k; numeric context uses decimal K/M display normalization. Publisher repository evidence (2026-10-23): Publisher task label: image-text-to-text. Published architecture metadata: KimiK25ForConditionalGeneration. Repository library label: transformers. Published safetensors metadata counts 1,026,879,376,368 stored parameters; this is not an active-parameter count for mixture-of-experts models. Published text_config configuration: max_position_embeddings=262144; dtype=bfloat16; 61 hidden layers. The configuration includes explicit RoPE scaling ({"beta_fast":32,"beta_slow":1,"factor":64,"mscale":1,"mscale_all_dim":1,"original_max_position_embeddings":4096,"type":"yarn"}); no effective context extension is inferred. Checkpoint configuration is not a verified hosted serving limit; context and output limits remain separate documented fields.
Model identifiers and aliases 2
kimi-k2.6moonshotai/Kimi-K2.6
Follow the evidence
Official sources.
- Kimi-K2.6 official model card ↗huggingface.co
- models — official Moonshot AI documentation ↗platform.kimi.com
- Kimi-K2.6: official publisher repository metadata ↗huggingface.co
- Kimi-K2.6: publisher model card at revision 7eb5002f6aad ↗huggingface.co
- Kimi-K2.6: published checkpoint configuration at revision 7eb5002f6aad ↗huggingface.co