Skip to content

Ask AI

I answer questions about Radeon Cloud from these docs and link to the pages I used.

Answers are generated from the docs by a model on Token Factory and can be wrong; the docs are authoritative. Don't enter API keys or other secrets here.

MiMo-V2.6-Flash

POST /v1/chat/completions model: MiMo-V2.6-Flash

The weights served here are MiMo-V2.6-Flash, the efficiency-balanced member of Xiaomi’s MiMo-V2.6 line — a sparse Mixture-of-Experts model built for text, images, video and audio. On this endpoint it takes text and images, and it always thinks before answering.

From the shipped config.json:

ArchitectureMiMoV2ForCausalLM, model_type = mimo_v2
Parameters309B total, 15B activated per token
Layers48 — 39 sliding-window + 9 global; the first block is global attention with a dense FFN, the other 47 are MoE
Hidden dimension4,096
Attention64 query heads; 4 KV heads on the global layers, 8 on the sliding-window ones
Head dimensions192 for Q/K, 128 for V — asymmetric
Sliding window128 tokens
Mixture of Experts256 routed experts, 8 activated per token, expert intermediate 2,048, no shared expert
Multi-token prediction3 layers declared in config.json; the shipped dflash/ drafter is 5 layers
Vocabulary152,576
Native context1,048,576
Quantisationquant_method: fp8 e4m3, block [128, 128], stored as MXFP4 (store_dtype: mxfp4, block 32)
LicenceMIT

The vision tower is a 681M-parameter MiMo ViT (28 layers, 24 sliding-window + 4 full, patch 16, spatial merge 2×2). Audio goes through a 308M AudioTokenizer plus a 127M patch encoder.

Context length1,048,576 tokens
Input modalitiestext, image
Streaming✅
Tool calling✅
JSON output✅ json_object and json_schema
Thinking✅ — always on
Inference engineSGLang
Stabilityexperimental

The weights were built for audio and video too, but this endpoint rejects audio input. See Audio input.

A system message may sit at any position, and there may be more than one.

Thinking is always on. Omit reasoning_effort entirely and the response still carries a populated reasoning:

"message": {
"role": "assistant",
"content": "4",
"reasoning": "2+2 is 4."
}

reasoning_effort is accepted with any value (none, minimal, low, medium, high, xhigh, max), but in tests on 2026-10-19 none of them changed the result: even none returned a short reasoning. Usage reports 0 reasoning tokens, both at the top level and in completion_tokens_details, so the thinking is counted only in completion_tokens.

Images are passed as image_url parts, base64 data URLs included:

{
"role": "user",
"content": [
{ "type": "image_url", "image_url": { "url": "data:image/png;base64,..." } },
{ "type": "text", "text": "How many blue circles?" }
]
}

usage.prompt_tokens_details.image_tokens reports what the image cost — a 1200×420 PNG came back as 494 image tokens.

Not available on this endpoint. An OpenAI input_audio part is rejected with 400 (“data did not match any variant of untagged enum MessageContent”), as of 2026-10-19. Send text and images only.

Both forms work:

response_formatResult
{"type": "json_object"}✅ {"北京": 2174, "上海": 2487}
{"type": "json_schema", "json_schema": {..., "strict": true}}✅ {"city":"北京","pop":2174}
Context window1,048,576 tokens, counted as a total budget — prompt plus output
Inputtext, image
JSON outputjson_object and strict json_schema
Thinking tiersreasoning_effort accepts every value but doesn’t change the output; thinking can’t be turned off
Terminal window
curl https://developer.amd.com.cn/radeon/api/v1/chat/completions \
-H "Authorization: Bearer $RADEON_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "MiMo-V2.6-Flash",
"messages": [
{ "role": "user", "content": "Why is the sky blue?" }
]
}'

The answer is in content; the thinking trace is in reasoning.