MiniMax M3.1 Flash Save up to 25%minimax-m3-1-flash
Type
Spec
Rate
Input
per 1M prompt tokens
$0.15$0.1125
Output
per 1M generated tokens
$0.60$0.45
Implicit cache read
per 1M cached input tokens
$0.015$0.01125
Web search
per call when invoked
$0.01
MiniMax M3.1 Flash and Kimi K3 side by side: specs, capabilities, parameters, and live pricing from the EmpirioLabs catalog.
MiniMax 
Moonshot AI Text GenerationMiniMax M3.1 Flash from MiniMax and Kimi K3 from Moonshot AI are both in the Text Generation category, available through the EmpirioLabs API.
| Spec | MiniMax M3.1 Flash | Kimi K3 |
|---|---|---|
| Model ID | minimax-m3-1-flash | kimi-k3 |
| Author | MiniMax | Moonshot AI |
| Released | Oct 19, 2026 | Jul 15, 2026 |
| Context window | 1M tokens | 1M tokens |
| Max output | 524,288 tokens | 131,072 tokens |
| Input | Text Image Video | Text Image Video |
| Output | Text | Text |
| Structured output | Not supported | JSON Schema |
| Region | Singapore | International |
| Endpoints | POST /v1/chat/completions POST /v1/responses POST /v1/messages POST /v1beta/models/minimax-m3-1-flash:generateContent | POST /v1/chat/completions POST /v1/responses POST /v1/messages POST /v1beta/models/kimi-k3: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 | MiniMax M3.1 Flash | Kimi K3 |
|---|---|---|
| reasoning_effort | low, medium, high, xhigh, max Default: max | low, high, max Default: max |
| max_completion_tokens | 1 to 524288 Default: 32768 | - |
| stop | array | string |
| tool_web_search | boolean Default: false | boolean Default: false |
| tools | array | - |
| tool_choice | object | - |
| disable_formatting | boolean Default: false | - |
| max_tokens | - | 1 to 1048576 Default: 131072 |
| max_tool_calls | - | 1 to 20 Default: 5 |
| response_format | - | enum |
Text, image, and video input with text output, a 1M token context, and up to 524,288 output tokens. The model always reasons: reasoning_effort sets how deeply (low, medium, high, xhigh, or max; the default is max), and the reasoning text is returned in reasoning_content. Reasoning tokens are billed as output tokens. Repeated prompt prefixes are cached automatically and billed at the cached input rate. Set tool_web_search to true to let the model search the web; each executed search is billed, and one request can run several searches. Answers that used web search end with a Sources list unless disable_formatting is true. Structured output through response_format is not supported; ask for JSON in the prompt instead.
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.
MiniMax M3.1 Flash 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 minimax-m3-1-flash. Both models are called through the same endpoint. Set model to minimax-m3-1-flash or kimi-k3. 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": "minimax-m3-1-flash",
"messages": [
{"role": "user", "content": "Write a haiku about the ocean."}
]
}'Prompt tests and comparison runs that cover both models.
MiniMax M3.1 Flash is the newer release (Oct 19, 2026); Kimi K3 was released on Jul 15, 2026. Both models have a context window of 1M tokens. MiniMax M3.1 Flash returns up to 524,288 output tokens per response, Kimi K3 up to 131,072. The specs, rate cards, and parameters on this page come from the live EmpirioLabs catalog.
MiniMax M3.1 Flash is the newer release (Oct 19, 2026); Kimi K3 was released on Jul 15, 2026.
MiniMax M3.1 Flash 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.
