- Source
- Model registry API
- Verified
- 19 Sep 2026
- Confidence
- High
01What this is
- Author
- moonshotai
- Family
- Kimi K2.5
- Task
- vision-language
- Hugging Face
- moonshotai/Kimi-K2.5
- OpenRouter
- moonshotai/kimi-k2.5
- Also known as
- Kimi K2.5, kimi-k2.5
02Registry facts
- LicenceFACT
other
- FreshRetrieved 19 Sep 2026
- ParametersFACT
1026.9B
- FreshRetrieved 19 Sep 2026
- Context lengthFACT
not returned by the registry
- Evidence not verified
- Downloads (30 days)FACT
323,660
- FreshRetrieved 19 Sep 2026
- LikesFACT
2,872
- FreshRetrieved 19 Sep 2026
- GatedFACT
no
- FreshRetrieved 19 Sep 2026
Model
- downloadsFACT
323660
- Verification may be outdatedRetrieved 19 Sep 2026
- gatedFACT
false
- Verification may be outdatedRetrieved 19 Sep 2026
- hosted context length · VeniceFACT
256000
- Verification may be outdatedRetrieved 19 Sep 2026
- hosted context length · AtlasCloudFACT
262144
- Verification may be outdatedRetrieved 19 Sep 2026
- hosted context length · SiliconFlowFACT
262144
- Verification may be outdatedRetrieved 19 Sep 2026
- likesFACT
2872
- Verification may be outdatedRetrieved 19 Sep 2026
- model licenseFACT
other
- Verification may be outdatedRetrieved 19 Sep 2026
- parameter countFACT
1026879376368
- Verification may be outdatedRetrieved 19 Sep 2026
Pricing
- hosted price completion per m · VeniceFACT
3.3250
- AgeingRetrieved 19 Sep 2026
- hosted price completion per m · AtlasCloudFACT
2.5000
- AgeingRetrieved 19 Sep 2026
- hosted price completion per m · SiliconFlowFACT
2.2500
- AgeingRetrieved 19 Sep 2026
- hosted price prompt per m · VeniceFACT
0.5320
- AgeingRetrieved 19 Sep 2026
- hosted price prompt per m · AtlasCloudFACT
0.4900
- AgeingRetrieved 19 Sep 2026
- hosted price prompt per m · SiliconFlowFACT
0.4500
- AgeingRetrieved 19 Sep 2026
Other
- available on platform · azureFACT
azure
Evidence not verified — the quoted phrase was not found in the fetched document.
- Evidence not verified
- available on platform · awsFACT
aws
The source document changed after this was recorded; it is queued for re-checking.
- Verification may be outdatedRetrieved 19 Sep 2026
- last modifiedFACT
2026-04-30T03:56:40.000Z
- Verification may be outdatedRetrieved 19 Sep 2026
- libraryFACT
transformers
- AgeingRetrieved 19 Sep 2026
03VRAM by quantisation
Peak VRAM for serving this model, computed by lib/deployment/hardware.ts from weights + KV cache + 15% runtime overhead. Inputs: 1026.9B parameters, 8,192 tokens of context (assumed — none fetched yet), 4 concurrent requests (assumed).
| Quantisation | Weights | Total |
|---|---|---|
| bf16bf16 is two bytes per weight, the same arithmetic as fp16. | 2053.76 GB | 2379.11 GB |
| fp8 | 1026.88 GB | 1198.2 GB |
| int4 | 513.44 GB | 607.74 GB |
What this estimate assumes
- Weights: 1026.9B parameters × 2 bytes per parameter (fp16) = 2053.76 GB.
- No model configuration was supplied, so the KV cache uses the size heuristic for this band: 0.459 MB per token, from extrapolated above 90B — no configuration was fetched for this band.
- KV cache: 0.459 MB per token × 8,192 tokens of context × 4 concurrent requests = 15.03 GB, sized for every user holding a full context at once.
- Overhead: 15% of weights plus KV cache for the runtime, activations and memory fragmentation = 310.32 GB.
- GB means 10⁹ bytes, matching how GPU memory is advertised.
- KV cache held at fp16 (2 bytes per element); quantising weights does not by itself quantise the cache.
- Peak figure, not average: prefix caching and paged attention usually keep real usage lower, while speculative decoding, CUDA graphs and a second resident model push it higher.
- "Concurrent" counts requests generated at the same instant, not people: 4 simultaneous requests is the worst case this estimate is built on — measure yours before buying.
04Hardware profiles
No hardware profile was sized for this answer.
05Hosted providers
- Prompt (per million tokens, USD)FACT
0.44999999999999996
Source: openrouter
- FreshRetrieved 19 Sep 2026
- Completion (per million tokens, USD)FACT
2.25
- FreshRetrieved 19 Sep 2026
| Provider | Context |
|---|---|
| SiliconFlow | 262,144 |
| AtlasCloud | 262,144 |
| Venice | 256,000 |
| Novita | 262,144 |
| Amazon Bedrock | 262,144 |
06Deployment stacks
No published deployment stack names this model yet.
07Evidence
- 01Tier 2official vendor legal documentationVendor legal and technical documentation
Models at a glance - Amazon Bedrock
https://docs.aws.amazon.com/bedrock/latest/userguide/model-cards.html
AgeingRetrieved 19 Sep 2026sha256:4c3b2b5762261 record
- 02–10Tier 4official repository / model cardOpenRouter
OpenRouter endpoints — moonshotai/kimi-k2.5
https://openrouter.ai/api/v1/models/moonshotai/kimi-k2.5/endpoints
AgeingRetrieved 19 Sep 2026sha256:1636332d06799 records · · · · · · · ·
- 11–17Tier 4official repository / model cardHugging Face Hub
Hugging Face model card data — moonshotai/Kimi-K2.5
https://huggingface.co/api/models/moonshotai/Kimi-K2.5
Verification may be outdatedRetrieved 19 Sep 2026sha256:cd97ff08fd0a7 records · · · · · ·
Improve this page
Sign in to contribute
From the field
0 deployments · 0 questions
Nobody has reported deploying this here yet, and no question has been opened against this page. Both appear once a reviewer accepts them.