Kimi K3
by MoonshotAImoonshotai/kimi-k3
LLMCompare cannot run Kimi K3 yet.No route to this model is configured on this site yet. Its prices and parameters are listed below for reference.
See the models that can be run nowKimi K3 at a glance
- Context length
- 1,048,576 tokens
- Maximum output
- 943,718 tokens
- Accepts
- Text, Image, Video
- Returns
- Text
- Features
- ReasoningJSON outputTool callingPrompt cachingImage input
- Reasoning effort levels
maxhighlownoneReasoning can be turned off.- Released
- 16 Jul 2026
- Knowledge cutoff
- Not published
Model facts synced from the OpenRouter model list on 21 Oct 2026.
Kimi K3 pricing by route
A route is the service LLMCompare calls to reach the model. Kimi K3 has 1 route. Prices are in US dollars.
| Route | On LLMCompare | Inputper 1M tokens | Outputper 1M tokens | Cache readper 1M tokens | Price verified on | Source |
|---|---|---|---|---|---|---|
| OpenRouterDefault | Not configured | $0.239 | $11.94 | $0.21 | openrouter.ai/moonshotai/kimi-k3 |
The cost shown in an LLMCompare report is calculated from these prices as they were at the time of the run.
Cost calculator
Estimate what a batch of calls to Kimi K3 costs. The starting numbers are examples. Change them to match your task.
Part of the input tokens above, billed at the cache read price.
Billed in addition to the output tokens.
- Cost per call
- $0.0062
- 8 credits
- Cost of 100 calls
- $0.6207
- 800 credits
Calculated from the OpenRouter prices verified on 21 Oct 2026. Credits are the cost plus a 20% service fee, at $0.001 per credit, rounded up for each call, with a minimum of 1 per call. A real run is charged for the usage the provider reports.
Parameters you can set
These are the parameters LLMCompare can set when it calls the model through OpenRouter.
| Parameter | Type | Range or options | Default |
|---|---|---|---|
temperature | Number | 0 to 2in steps of 0.1 | Provider default |
top_p | Number | 0 to 1in steps of 0.05 | Provider default |
max_tokens | Integer | 1 to 943,718 | Provider default |
reasoning_effort | One of | maxhighlownone | max |
seed | Integer | -2,147,483,648 to 4,294,967,295 | Provider default |
response_format | One of | textjson_object | Provider default |
About Kimi K3
Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...
Description as published for this model. LLMCompare has not edited it.
Models to compare with Kimi K3
Text models from the same provider and models at the nearest price. The order is not a ranking.
| Add to comparison | Model | Context | Max output | Input priceper 1M tokens | Output priceper 1M tokens | Features | Released | On LLMCompare |
|---|---|---|---|---|---|---|---|---|
Kimi K2.6MoonshotAImoonshotai/kimi-k2.6 | 262k | 236k | $0.65 | $3.41 | JSONToolsCacheVision | No route yet | ||
Kimi K2.7 CodeMoonshotAImoonshotai/kimi-k2.7-code | 262k | 236k | $0.6712 | $3.35 | JSONToolsCacheVision | No route yet | ||
Kimi K2 ThinkingMoonshotAImoonshotai/kimi-k2-thinking | 262k | 98.3k | $0.60 | $2.50 | JSONToolsCache | No route yet | ||
Gemini 4 ArgonGooglegoogle/gemini-4-argon | 1.05M | 944k | $2.00 | $10.00 | ReasoningJSONToolsCacheVision | No route yet | ||
GPT-6.1 Sol ProOpenAIopenai/gpt-6.1-sol-pro | 1.05M | 128k | $2.00 | $10.00 | ReasoningJSONToolsCacheVision | No route yet | ||
GPT-6.1 SolOpenAIopenai/gpt-6.1-sol | 1.05M | 128k | $2.00 | $10.00 | ReasoningJSONToolsCacheVision | No route yet |
Questions about Kimi K3
- How much does Kimi K3 cost?
- On the OpenRouter route, Kimi K3 costs $0.239 per 1 million input tokens and $11.94 per 1 million output tokens, in US dollars. Input tokens that Kimi K3 reads from the prompt cache cost $0.21 per 1 million tokens. LLMCompare verified this price on 21 Oct 2026.
- What is the context length of Kimi K3?
- Kimi K3 has a context length of 1,048,576 tokens and returns up to 943,718 output tokens in one call.
- What inputs does Kimi K3 accept?
- Kimi K3 accepts these inputs: Text, Image, Video. Kimi K3 returns: Text.
- Which reasoning effort levels does Kimi K3 support?
- Kimi K3 supports these reasoning effort levels: max, high, low, none. Reasoning can be turned off for Kimi K3.
- Can I test Kimi K3 on my own data?
- Not yet. LLMCompare lists the prices and parameters of Kimi K3, but no route to Kimi K3 is configured on LLMCompare, so it cannot be selected for an evaluation.