Capability badges appear only where the provider catalog explicitly lists support. A blank cell means the source is silent, not that the feature is absent.
Listed rates
Price across providers
Input price per million tokens as published by each provider. Bars are drawn from listed rates only — no traffic weighting, since the catalog observes no requests.
Lowest input$0.435/M
Across 7 priced providers
Median input$1/M
Midpoint of listed rates
Highest input$2/M
4.6× the lowest listed rate
Output range$0.87 – $6
Per million output tokens
Xiaomi$0.435/MLowest
Vercel AI Gateway$1/M
ZenMux$1/M
Abacus$1/M
Kilo Gateway$1/M
NanoGPT$1/M
Novita AI$2/M
Cost calculator
Estimate a workload
$0.00
Excludes taxes, non-token charges, and tiered discounts.
Context limits also differ by provider, from 1M to 1.04858M tokens. Compare the provider table above before choosing on price alone.
Specification
Capabilities
Recorded from the source catalog and provider listings.
Every result stays attached to its source, version, metric and harness. Scores from different versions are never merged, and the profile below plots each benchmark against its own population rather than on a shared scale.
ModelBench does not infer quality from price, context size, or model name. When a source publishes a comparable result, it appears here with its version and link.
Answered directly from the stored record — nothing here is generated beyond the catalog's own fields.
What is MiMo-V2-Pro?
Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks. It is published by Xiaomi and catalogued here from Models.dev.
How much does MiMo-V2-Pro cost?
Listed input pricing starts at $0.435 per million tokens from Xiaomi, rising to $2 across 7 listed providers.
What is the context length of MiMo-V2-Pro?
MiMo-V2-Pro accepts up to 1.04858M tokens of context and returns up to 131.072K output tokens.
Does MiMo-V2-Pro support tool calling and structured output?
Provider catalogs list support for tool calling, and reasoning.
Which providers serve MiMo-V2-Pro?
10 providers list this model: Xiaomi Token Plan (Europe), Xiaomi Token Plan (China), Xiaomi Token Plan (Singapore), Xiaomi, Vercel AI Gateway, ZenMux and 4 more.
Are the weights for MiMo-V2-Pro open?
No. This model is served through hosted APIs only.
When was MiMo-V2-Pro released?
The catalog records a release date of 2026-03-18, last verified Oct 24, 2026.
Xiaomi
ZenMux
Abacus
Novita AI