Moonshot AIOpen-weight·262K context· params

Kimi K2.5moonshot/kimi-k2-5

Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...

Cheapest blended:$0.80 / 1M tokenson Moonshot AI · 1 provider listed

Pricing across providers

Sort by:
ProviderInput /1MOutput /1MBlended /1MLatency p50FormatFreshnessAction
Moonshot AI
kimi-k2.5
$0.40$1.98$0.80OpenAI-compatibleNeeds 27d agoTry →

Affiliate disclosure: We may earn a commission from qualified signups. Pricing independence is enforced at the data layer — see our Editorial Independence Policy.

Works with

Point any of these clients at a hosting's base URL — they all speak at least one of this model's endpoint protocols (OPENAI_COMPATIBLE).

Capabilities

  • chat
  • reasoning
  • code
  • vision
  • long_context

Languages: en, zh

Code samples

Example using Moonshot AI — the cheapest hosting for this model as of last verification. Swap base_url and model to use a different provider from the matrix above.

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.moonshot.cn/v1",
)

response = client.chat.completions.create(
    model="kimi-k2.5",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

Technical specs

Context
262K
Max output
262K
Parameters
Release
Training cutoff
License

Similar models

Compare with

  • Kimi K2.5 vs Kimi K2.6
    Comparison planned — not yet published
  • Kimi K2.5 vs Qwen VL Max
    Comparison planned — not yet published
  • Kimi K2.5 vs Qwen3.5-122B-A10B
    Comparison planned — not yet published

Frequently asked

How much does Kimi K2.5 cost?+
The cheapest public hosting is $0.80 per 1M blended tokens on Moonshot AI. 1 total providers are listed above with per-input / per-output / cached pricing.
How do I access Kimi K2.5 from outside China?+
All hostings listed above support global access. The official API (e.g. api.deepseek.com, dashscope-intl.aliyuncs.com) accepts international credit cards and does not require a Chinese mobile number. For privacy-sensitive workloads, third-party aggregators like Together.ai host the model on US/EU infrastructure.
Is Kimi K2.5 open-source? Can I fine-tune it?+
Yes. Kimi K2.5 is open-weight under the unspecified license. Weights are available on Hugging Face for local inference, fine-tuning, and commercial use (see license for specific terms).
Is Kimi K2.5 OpenAI-compatible?+
Most listed hostings expose an OpenAI-compatible API, so you can point an existing openai SDK client at the Provider's base_url and use the Provider's model name. See the Code Samples above for a copy-pasteable example.
What's the maximum context window for Kimi K2.5?+
The model supports up to 262,144 tokens of context (input + output). Some hosted versions may impose a smaller limit — check the "Context" column in the pricing matrix for each provider.