Type
Spec
Rate
Input
per 1M prompt tokens
$2.00
Output
per 1M generated tokens
$10.00
Implicit cache read
per 1M cached input tokens
$0.184
Web Search (Linkup)
per call when invoked
$0.013
Kimi K3.1 Pro and Fugu Ultra v1.1 side by side: specs, capabilities, parameters, and live pricing from the EmpirioLabs catalog.
Moonshot AI 
Sakana AI Text GenerationKimi K3.1 Pro from Moonshot AI and Fugu Ultra v1.1 from Sakana AI are both in the Text Generation category, available through the EmpirioLabs API.
| Spec | Kimi K3.1 Pro | Fugu Ultra v1.1 |
|---|---|---|
| Model ID | kimi-k3-1-pro | fugu-ultra-v1-1 |
| Author | Moonshot AI | Sakana AI |
| Released | Oct 23, 2026 | Jul 23, 2026 |
| Context window | 1M tokens | 1M tokens |
| Max output | 131,072 tokens | 131,072 tokens |
| Input | Text Image | Text Image |
| Output | Text | Text |
| Structured output | JSON Schema | JSON Schema |
| Region | Germany | - |
| Endpoints | POST /v1/chat/completions POST /v1/responses POST /v1/messages POST /v1beta/models/kimi-k3-1-pro:generateContent | POST /v1/chat/completions POST /v1/responses POST /v1/messages POST /v1beta/models/fugu-ultra-v1-1: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 K3.1 Pro | Fugu Ultra v1.1 |
|---|---|---|
| max_tokens | 1 to 131072 Default: 131072 | 16 to 131072 |
| stop | string | - |
| enable_thinking | boolean Default: true | - |
| reasoning_effort | low, medium, high, max Default: max | high, xhigh, max Default: high |
| response_format | enum | enum |
| web_search_linkup | boolean Default: false | - |
| disable_formatting | boolean Default: false | - |
| tool_web_search | - | boolean Default: false |
| tools | - | array Default: [] |
| tool_choice | - | object |
Supports text and image inputs with a 1M token context, function calling, and JSON schema structured output. Linkup web search is available through web_search_linkup and adds $0.013 per call when invoked. Thinking is on by default: set its depth with reasoning_effort (max is the default), or turn it off with enable_thinking, which lowers output quality. Reasoning tokens are billed as output tokens. Stop strings apply to reasoning as well as the answer, so a stop string that appears in the reasoning ends the reply early. Temperature and other sampling settings are fixed by the model service.
Fugu Ultra v1.1 is an updated multi-agent conductor: each request coordinates a pool of expert models and composes their work into a single answer.
Kimi K3.1 Pro 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-k3-1-pro. Both models are called through the same endpoint. Set model to kimi-k3-1-pro or fugu-ultra-v1-1. 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-k3-1-pro",
"messages": [
{"role": "user", "content": "Write a haiku about the ocean."}
]
}'Kimi K3.1 Pro is the newer release (Oct 23, 2026); Fugu Ultra v1.1 was released on Jul 23, 2026. Both models have a context window of 1M tokens. Capabilities listed only for Kimi K3.1 Pro: vision. The specs, rate cards, and parameters on this page come from the live EmpirioLabs catalog.
Kimi K3.1 Pro is the newer release (Oct 23, 2026); Fugu Ultra v1.1 was released on Jul 23, 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.