Type
Spec
Rate
Input
per 1M prompt tokens
$0.95$0.8939
Output
per 1M generated tokens
$4.00$3.7131
Implicit cache read
per 1M cached input tokens
$0.1788
Web Search (Linkup)
per call when invoked
$0.013
Kimi K2.6 and Qwen3.6 Plus side by side: specs, capabilities, parameters, and live pricing from the EmpirioLabs catalog.
Moonshot AI 
Alibaba Cloud Text GenerationKimi K2.6 from Moonshot AI and Qwen3.6 Plus from Alibaba Cloud are both in the Text Generation category, available through the EmpirioLabs API.
| Spec | Kimi K2.6 | Qwen3.6 Plus |
|---|---|---|
| Model ID | kimi-k2-6 | qwen3-6-plus |
| Author | Moonshot AI | Alibaba Cloud |
| Released | Apr 20, 2026 | Apr 2, 2026 |
| Context window | 256K tokens | 983.6K tokens |
| Max output | 16,000 tokens | 65,536 tokens |
| Input | Text Image Video | Text Image Video |
| Output | Text | Text |
| Structured output | JSON Schema | JSON Mode |
| Region | China | Singapore |
| Endpoints | POST /v1/chat/completions POST /v1/responses POST /v1/messages POST /v1beta/models/kimi-k2-6:generateContent | POST /v1/chat/completions POST /v1/responses POST /v1/messages POST /v1beta/models/qwen3-6-plus: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 K2.6 | Qwen3.6 Plus |
|---|---|---|
| temperature | 0 to 1.99 Default: 0.7 | 0 to 1.99 Default: 0.7 |
| top_p | 0 to 1 Default: 0.9 | 0 to 1 Default: 0.9 |
| max_tokens | 1 to 16000 | 1 to 65536 |
| stop | string | string |
| enable_thinking | boolean Default: true | boolean Default: true |
| reasoning_effort | none, low, medium, high, max Default: medium | none, low, medium, high, max |
| thinking_budget | 1 to 81920 Default: 32768 | 1 to 131072 |
| response_format | enum | enum |
| web_search_linkup | boolean Default: false | - |
| disable_formatting | boolean Default: false | boolean Default: false |
| preserve_thinking | - | boolean Default: false |
| seed | - | 0 to 2147483647 |
| top_k | - | 1 to 100 |
| presence_penalty | - | -2 to 2 |
| repetition_penalty | - | 0.1 to 2 |
| n | - | 1 to 4 Default: 1 |
Pricing is 4x for input and 2x for output above 256K tokens. Built-in tool calls are NOT supported when video is attached.
Text-to-Image Search and Image-to-Image Search use the Image Search pricing row. Each invoked image search is billed at that listed per-call rate.
Kimi K2.6 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-k2-6. Both models are called through the same endpoint. Set model to kimi-k2-6 or qwen3-6-plus. 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-k2-6",
"messages": [
{"role": "user", "content": "Write a haiku about the ocean."}
]
}'Kimi K2.6 is the newer release (Apr 20, 2026); Qwen3.6 Plus was released on Apr 2, 2026. Qwen3.6 Plus has the larger context window: 983.6K tokens, against 256K for Kimi K2.6. Qwen3.6 Plus returns up to 65,536 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 K2.6 is the newer release (Apr 20, 2026); Qwen3.6 Plus was released on Apr 2, 2026.
The two models are priced on different units or tiers, so compare the live rate cards on this page. They 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.