🎁 New Sign up free, 10 calls on us. Up to $1, no card needed.

Kimi K2.5 Released 2026-01

Moonshot chat vision code reasoning tools
Input$0.574/M
Output$3.011/M
Cache read$0.115/M
Context262K
vs GPT-4o~89% cheaper

Provider list prices: no platform markup, pay-as-you-go. These are official list prices. Logged-in customers may see effective prices including workspace discounts on /console/pricing. Effective input at a 70% cache-hit rate:$0.2527/M. Automatic caching with hit/miss pricing: cached input tokens bill at the discounted cache-hit rate, no cache management required.

Use Kimi K2.5 in 30 seconds

OpenAI-compatible: swap the base_url, keep your SDK. POST /v1/chat/completions

from openai import OpenAI

client = OpenAI(
    base_url="https://synthorai.io/v1",
    api_key="sk-syn-...",
)

resp = client.chat.completions.create(
    model="kimi-k2.5",
    messages=[{"role": "user", "content": "Summarize this diff"}],
    reasoning_effort="medium",
)
print(resp.choices[0].message.content)

About Kimi K2.5

Vision-language understanding and code from visual specs
Agent swarm for coordinated multi-agent operation
1T-parameter MoE under modified MIT license

Kimi K2.5 is Moonshot AI's open-source, native multimodal agentic model, built by continual pretraining on roughly 15T mixed visual and text tokens atop Kimi-K2-Base.

  • Its Mixture-of-Experts design totals 1T parameters with 32B activated, adds the MoonViT vision encoder, and supports a 256K context.
  • Versus Kimi K2, it introduces vision-language understanding, code generation from visual specifications, and Agent Swarm, moving from single-agent execution to coordinated swarm-like operation, with both thinking and instant modes.
  • Weights ship under a Modified MIT license.
  • Synthorai makes Kimi K2.5 callable through its OpenAI-compatible API surface.

Specs & limits

Modalitiestext + image + video → text
Parameters1T total · 32B active (MoE)
Featurestools · structured_output · streaming · vision · reasoning
LicenseModified-MIT ↗
Notable1T/32B active MoE, 256K context, native multimodal (MoonViT encoder, image + video input), instant + thinking modes, Agent Swarm up to 100 sub-agents; native INT4 quantization.
Prompt cachingautomatic

per Moonshot official docs ↗

FAQ

Is the Kimi K2.5 API free to try?

Yes: new accounts get 10 trial calls and up to $1 in free credit, no card required. At $0.574/M input tokens, that credit alone covers roughly 217 requests of ~8K tokens against Kimi K2.5.

What is Kimi K2.5 best at?

Vision-language understanding and code from visual specs, plus agent swarm for coordinated multi-agent operation and 1T-parameter MoE under modified MIT license. See the About section for the full picture from the vendor's own release notes.

How much does Kimi K2.5 cost?

Kimi K2.5 costs $0.574 per million input tokens and $3.011 per million output tokens on Synthorai. That is the provider's list price, with no platform markup. Cached input tokens bill at $0.115/M.

Does Kimi K2.5 support prompt caching?

Yes, automatically: Moonshot-served prompts cache with no code changes. Cached input tokens bill at $0.115/M vs $0.574/M uncached. Prompt caching guide →

How do I get access to Kimi K2.5?

Point your existing OpenAI SDK at base_url="https://synthorai.io/v1", set model="kimi-k2.5", and you're done. One API key covers every model on the gateway.

Is Kimi K2.5 open source?

Yes: the weights are published under the Modified-MIT license (official repository linked in the About section). Or skip the GPUs: the hosted version here is pay-as-you-go with no infrastructure to run. Running open-weight models →

Related models

Get your free API key Compare your cost →