Kimi K3 with Jev
Kimi K3 is a model from MoonshotAI, released 2026-07-16. It costs $3.00 per million input tokens and $15 per million output tokens, reads up to 1.05M tokens of context, and writes up to 943,718 tokens in one reply. Through llm11, set model to moonshotai/kimi-k3.
- Input price
- $3.00 / 1M
- Output price
- $15 / 1M
- Context window
- 1.05M tokens
- Max output
- 944K tokens
- Cached input
- $0.300 / 1M
- Released
- 2026-07-16
- Accepts
- text, image, video
- Intelligence index
- 43.6
Read from the provider's prompt cache
Artificial Analysis, via the catalogue
Read from the live catalogue and refreshed daily. At blended list price, 8% of the 332 priced models we can call cost more.
Using Kimi K3 with Jev
Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. Kimi K3 does the answering when Jev sends it work, or when you name it yourself. At list price Kimi K3 falls in the llm11-smart band, but no pack routes to it because MoonshotAI is not one of the labs the packs draw from. You can still pin it: pass moonshotai/kimi-k3 as model and routing steps aside while verification still runs.
Jev is new, so we have not published results for Kimi K3 with and without it, and this page does not invent any. Every response comes with a receipt that names the model that answered and what it cost against your most expensive model, so you can measure the pairing on your own traffic.
What a request costs
List price arithmetic, the same sum a receipt does. llm11 adds nothing per request; the only fee is on buying credits.
| Request | Tokens in / out | One | A thousand |
|---|---|---|---|
| Short chat turn | 500 / 200 | $0.00450 | $4.50 |
| Question over retrieved documents | 4,000 / 500 | $0.019 | $19.50 |
| Long document summary | 30,000 / 1,000 | $0.105 | $105.00 |
Cheaper models to try
Nearest in price and below Kimi K3, each within a few points of it on the intelligence index.
| Model | Input / 1M | Output / 1M | Context | Index | Released |
|---|---|---|---|---|---|
| OpenAI GPT-5.6 Terra | $2.00 | $12 | 1.05M | 42.1 | |
| Anthropic Claude Sonnet 5.5 | $2.00 | $10 | 1M | 56 | |
| OpenAI GPT-6 Sol | $2.00 | $10 | 1.05M | 47.5 | |
| OpenAI GPT-5.6 Sol | $2.00 | $10 | 1.05M | 47 |
Call it
Same OpenAI request shape. Naming the model pins it, so nothing is routed, and the answer is still checked.
python
from openai import OpenAI
client = OpenAI(base_url="https://www.llm11.com/v1", api_key="llm11_live_...")
res = client.chat.completions.create(
model="moonshotai/kimi-k3",
messages=[{"role": "user", "content": "Hello"}],
)More from MoonshotAI
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Kimi K2.7 Code | $0.656 | $3.30 | 262K | |
| Kimi K2.6 | $0.650 | $3.41 | 262K | |
| Kimi K2.5 | $0.450 | $2.25 | 262K | |
| Kimi K2 Thinking | $0.600 | $2.50 | 262K | |
| Kimi K2 0905 | $0.600 | $2.50 | 262K | |
| Kimi K2 0711 | $0.570 | $2.30 | 131K |
Questions
- What is Kimi K3 with Jev?
- Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. Kimi K3 does the answering when Jev sends it work, or when you name it yourself. At list price Kimi K3 falls in the llm11-smart band, but no pack routes to it because MoonshotAI is not one of the labs the packs draw from. You can still pin it: pass moonshotai/kimi-k3 as model and routing steps aside while verification still runs. Routing decisions are made by Jev, TypeSafe AI's System One model.
- Is Kimi K3 a System One model?
- No. Kimi K3 answers requests. The System One model is Jev, which decides which model answers each one, so the two do different jobs and llm11 uses both.
- How much does Kimi K3 cost?
- $3.00 per million input tokens and $15 per million output tokens. A 4,000 token prompt with a 500 token answer costs about $0.019, so a thousand of them is about $19.50. llm11 passes provider list price through and charges 5% when you buy credits.
- What is the Kimi K3 context window?
- 1,048,576 tokens, with up to 943,718 tokens in a single reply.
- Does Kimi K3 support tool calling and structured output?
- The catalogue lists tool calling, structured output and reasoning controls.
- Can I use Kimi K3 through llm11?
- Yes. Set model to moonshotai/kimi-k3 on the OpenAI-compatible endpoint and the request goes to it directly, with verification still running.
- Does Jev route to Kimi K3?
- Routing decisions are made by Jev, TypeSafe AI's System One model. At list price Kimi K3 falls in the llm11-smart band, but no pack routes to it because MoonshotAI is not one of the labs the packs draw from. You can still pin it: pass moonshotai/kimi-k3 as model and routing steps aside while verification still runs.
- What is a cheaper alternative to Kimi K3?
- Nearest in price and below it: OpenAI GPT-5.6 Terra at $2.00 in and $12 out, Anthropic Claude Sonnet 5.5 at $2.00 in and $10 out and OpenAI GPT-6 Sol at $2.00 in and $10 out. Nearest in price and below Kimi K3, each within a few points of it on the intelligence index.