MiMo-V2.5
mimo-v2.5MiMo-V2.5 by XiaoMi, with Vision, Function Calling, Reasoning, Prompt Caching, Audio, Video. Via WandAPI, Input (prompt) costs 0.75 Credits / M tokens, 25% below list price. Compatible with Anthropic Messages / OpenAI Responses: swap the base URL and you are connected.
Capabilities
Listed exactly as the catalog flags them, including what this model does not support.
Vision
Natively multimodal: captioning, classification, visual Q&A, chart and screenshot understanding. Images are converted to tokens at the input rate.
Function Calling
Connect the model to external tools and APIs: it decides when to call which function and with what arguments, your code runs it. Force or forbid calls with tool_choice.
Reasoning
The model thinks before answering, which markedly improves multi-step planning and reasoning for coding, math and data analysis. Thinking tokens bill at the output rate.
Prompt Caching
Repeated prefixes (system prompts, long documents) hit the cache: reads cost far less than input, writes are priced by retention time.
Audio
Audio input or speech output.
Video
Video input understanding or video generation.
Response SchemaNot supported
Constrain output to a JSON Schema you provide for predictable, type-safe results without parsing free text.
File InputNot supported
Upload PDFs and other documents directly; the model reads the whole document with native vision.
StreamingNot supported
Tokens arrive over SSE as they are generated; the first frame is forwarded immediately with no buffering. Claude Code, Codex and similar tools depend on this.
Web SearchNot supported
Vendor-hosted live web retrieval; the model decides when to search and cites sources.
RealtimeNot supported
Bidirectional low-latency voice / text sessions over WebSocket.
SessionNot supported
Server-side multi-turn context (e.g. previous_response_id in Responses) so you need not resend history.
MediaNot supported
Image / video / music generation endpoints.
Multipart FormNot supported
multipart/form-data file-upload requests.
Binary ResponseNot supported
Endpoints that return raw audio / image bytes.
Protocols & code samples
Change the base URL to WandAPI, keep everything else. Native protocols pass straight through; “adapted” ones are translated by the gateway.
Anthropic SDK or any Messages-protocol client: point base_url at https://api.wandapi.com and use a WandAPI key.
curl https://api.wandapi.com/v1/messages \
-H "x-api-key: $WANDAPI_KEY" \
-H "anthropic-version: 2023-06-01" \
-H "content-type: application/json" \
-d '{
"model": "mimo-v2.5",
"max_tokens": 1024,
"messages": [{"role": "user", "content": "Explain prompt caching in one sentence"}]
}'| Endpoint | Path | Mode |
|---|---|---|
| System OneSystem One | POST /v1/systemone | native |
Full price list
List price → WandAPI price per channel, every pricing dimension, nothing hidden.
| Item | Unit | XiaoMi list price | 小米 MiMo ×0.7525% off |
|---|---|---|---|
| Input (prompt) | per 1M tokens | 0.75 Credits | |
| Output (completion) | per 1M tokens | 1.5 Credits | |
| Cache read | per 1M tokens | 0.015 Credits |
“Off” is computed at 1 Credit = ¥1 and today’s rate: 1 − channel multiplier × (1 Credit in the list currency).
FAQ
How much does the MiMo-V2.5 API cost?
Via WandAPI, Input (prompt) costs 0.75 Credits / M tokens, with 1 Credit = ¥1. That is 25% below the XiaoMi list price.
Does MiMo-V2.5 support function calling and structured outputs?
Function calling with tool_choice control is supported; structured outputs (JSON Schema) are not enabled — use a function-call parameter schema for type-safe results instead.
How do I use MiMo-V2.5 in Claude Code?
Set ANTHROPIC_BASE_URL=https://api.wandapi.com, ANTHROPIC_API_KEY to your WandAPI key and ANTHROPIC_MODEL=mimo-v2.5, then run claude. No config files to edit.
One API key for MiMo-V2.5 and 30+ models
Free credits on sign-up, pay as you go, no monthly fee.