Type
Spec
Rate
Input
per 1M prompt tokens
$0.14
Output
per 1M generated tokens
$0.28
Web search
per call when invoked
$0.015
MiMo V2.6 Flash and Step 3.7 Flash side by side: specs, capabilities, parameters, and live pricing from the EmpirioLabs catalog.
Xiaomi 
StepFun Text GenerationMiMo V2.6 Flash from Xiaomi and Step 3.7 Flash from StepFun are both in the Text Generation category, available through the EmpirioLabs API.
| Spec | MiMo V2.6 Flash | Step 3.7 Flash |
|---|---|---|
| Model ID | mimo-v2-6-flash | step-3-7-flash |
| Author | Xiaomi | StepFun |
| Released | Sep 22, 2026 | May 28, 2026 |
| Context window | 1M tokens | 256K tokens |
| Max output | 131,072 tokens | 131,072 tokens |
| Input | Text Image Video Audio | Text Image Video |
| Output | Text | Text |
| Structured output | JSON Schema | JSON Mode |
| Region | Singapore | International |
| Endpoints | POST /v1/chat/completions POST /v1/responses POST /v1/messages POST /v1beta/models/mimo-v2-6-flash:generateContent | POST /v1/chat/completions POST /v1/responses POST /v1/messages POST /v1beta/models/step-3-7-flash: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 | MiMo V2.6 Flash | Step 3.7 Flash |
|---|---|---|
| enable_thinking | boolean Default: true | - |
| video_fps | 0.1 to 10 | - |
| media_resolution | default, max Default: default | - |
| tool_web_search | boolean Default: false | - |
| web_search_force | boolean Default: false | - |
| web_search_max_keyword | 1 to 5 Default: 3 | - |
| web_search_limit | 1 to 10 Default: 5 | - |
| temperature | 0 to 1.5 Default: 1 | 0 to 2 Default: 0.5 |
| top_p | 0.01 to 1 Default: 0.95 | 0.01 to 1 Default: 0.9 |
| max_tokens | 1 to 131072 Default: 8192 | 1 to 131072 Default: 4096 |
| stop | string | array |
| response_format | enum | object |
| disable_formatting | boolean Default: false | boolean Default: false |
| frequency_penalty | - | -2 to 2 Default: 0 |
| reasoning_effort | - | low, medium, high Default: low |
| reasoning_format | - | general, deepseek-style Default: general |
Web search ($0.015/call) is charged only when invoked. Accepts text, image, video, and audio input and returns text. Thinking is on by default and can be turned off.
Supports text, image, and video input with 256K context, function tools, JSON object mode, reasoning_effort low, medium, or high, and optional Linkup web search. Video input supports MP4 under 128 MB, with clips under 5 minutes recommended.
MiMo V2.6 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 mimo-v2-6-flash. Both models are called through the same endpoint. Set model to mimo-v2-6-flash or step-3-7-flash. 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": "mimo-v2-6-flash",
"messages": [
{"role": "user", "content": "Write a haiku about the ocean."}
]
}'Prompt tests and comparison runs that cover both models.
MiMo V2.6 Flash is the newer release (Sep 22, 2026); Step 3.7 Flash was released on May 28, 2026. MiMo V2.6 Flash has the larger context window: 1M tokens, against 256K for Step 3.7 Flash. Input types only MiMo V2.6 Flash accepts: Audio. The specs, rate cards, and parameters on this page come from the live EmpirioLabs catalog.
MiMo V2.6 Flash is the newer release (Sep 22, 2026); Step 3.7 Flash was released on May 28, 2026.
MiMo V2.6 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.
