Type
Spec
Rate
Input
per 1M prompt tokens
$3.00
Output
per 1M generated tokens
$15.00
Web search
per call when invoked
$0.015
Kimi K3 and Kimi K2.6 side by side: specs, capabilities, parameters, and live pricing from the EmpirioLabs catalog.
Moonshot AI Text GenerationKimi K3 and Kimi K2.6 are both Moonshot AI models in the Text Generation category, available through the EmpirioLabs API.
| Spec | Kimi K3 | Kimi K2.6 |
|---|---|---|
| Model ID | kimi-k3 | kimi-k2-6 |
| Author | Moonshot AI | Moonshot AI |
| Released | Jul 15, 2026 | Apr 20, 2026 |
| Context window | 1M tokens | 256K tokens |
| Max output | 131,072 tokens | 16,000 tokens |
| Input | Text Image Video | Text Image Video |
| Output | Text | Text |
| Structured output | JSON Schema | JSON Schema |
| Region | International | China |
| Endpoints | POST /v1/chat/completions POST /v1/responses POST /v1/messages POST /v1beta/models/kimi-k3:generateContent | POST /v1/chat/completions POST /v1/responses POST /v1/messages POST /v1beta/models/kimi-k2-6:generateContent |
| Capabilities |
Live rates from the EmpirioLabs catalog for both models. Each rate card always matches what the API charges.
Request parameters each model lists on EmpirioLabs, with the allowed values or range where one applies. A dash marks a parameter the model does not list.
| Parameter | Kimi K3 | Kimi K2.6 |
|---|---|---|
| max_tokens | 1 to 1048576 Default: 131072 | 1 to 16000 |
| stop | string | string |
| reasoning_effort | low, high, max Default: max | none, low, medium, high, max Default: medium |
| tool_web_search | boolean Default: false | - |
| max_tool_calls | 1 to 20 Default: 5 | - |
| response_format | enum | enum |
| temperature | - | 0 to 1.99 Default: 0.7 |
| top_p | - | 0 to 1 Default: 0.9 |
| enable_thinking | - | boolean Default: true |
| thinking_budget | - | 1 to 81920 Default: 32768 |
| web_search_linkup | - | boolean Default: false |
| disable_formatting | - | boolean Default: false |
Supports text, image, and video inputs with a 1M token context, function calling, JSON schema structured output, and built-in web search at $0.015 per invoked call. Thinking is always on; reasoning depth is tunable with the reasoning_effort control (max is recommended) and reasoning tokens are billed as output tokens. Temperature and other sampling settings are fixed by the model service. Multi-step function calling through the API must replay the assistant message with its reasoning_content field intact.
Kimi K3 serves the OpenAI-compatible Chat Completions API. Point any OpenAI SDK at https://api.empiriolabs.ai/v1 with your EmpirioLabs API key and use the model id kimi-k3. Both models are called through the same endpoint. Set model to kimi-k3 or kimi-k2-6. Get an API key from the EmpirioLabs dashboard.
curl https://api.empiriolabs.ai/v1/chat/completions \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "kimi-k3",
"messages": [
{"role": "user", "content": "Write a haiku about the ocean."}
]
}'Kimi K3 is the newer release (Jul 15, 2026); Kimi K2.6 was released on Apr 20, 2026. Kimi K3 has the larger context window: 1M tokens, against 256K for Kimi K2.6. Kimi K3 returns up to 131,072 output tokens per response, Kimi K2.6 up to 16,000. The specs, rate cards, and parameters on this page come from the live EmpirioLabs catalog.
Kimi K3 is the newer release (Jul 15, 2026); Kimi K2.6 was released on Apr 20, 2026.
Kimi K2.6 lists the lower rate for Input (per 1M prompt tokens) and Output (per 1M generated tokens). Both live rate cards are on this page and always match what the API charges.
Yes. Both models use POST /v1/chat/completions with the same EmpirioLabs API key, so most integrations switch by changing the model value. Check the parameters table on this page first if you rely on a model-specific parameter.
Yes. Open each model in the EmpirioLabs playground and run the same prompt on both, with the parameters the API exposes.
Check out our pricing or reach out if you want your own model deployed on our stack.