Back to model shop
Minimax
Rendered from D1 model snapshot · D1 read 117msCache check: checking

minimax/MiniMax-M2.7-highspeed

Open weights
MiniMax-M2.7-highspeed

Low-latency M2.7 variant for interactive coding plans and agent loops

This model's cache

This model page returns the exact headers below. The page and /api/models/minimax--MiniMax-M2.7-highspeed share the model:minimax--MiniMax-M2.7-highspeed tag, so invalidation stays scoped to this model.

Cache key/models/minimax--MiniMax-M2.7-highspeed
Cache-Controlpublic, max-age=300, stale-while-revalidate=3600
Cache-Tagcatalogmodel:minimax--MiniMax-M2.7-highspeed

Workers Cache derives the key from this path/query, plus the Worker entrypoint and current Worker version.

export const Route = createFileRoute('/models/$modelSlug')({
  headers: () => ({
    'Cache-Control': 'public, max-age=300, stale-while-revalidate=3600',
    'Cache-Tag': 'catalog,model:minimax--MiniMax-M2.7-highspeed',
  }),
})

Invalidate this cache tag

await ctx.cache.purge({ tags: ['model:minimax--MiniMax-M2.7-highspeed'] })

Use this when one model changes and you do not want to evict the whole catalog.

MinimaxReasoningTool callingTemperature control
Released
Mar 18, 2026
Last updated
Mar 18, 2026
Context window
204.8K tokens
Max output
131.1K tokens
Open weights
Yes
Family
Minimax

Starts at

$0.6

per 1M input tokens

Output

$2.4

Sellers

1

No cart or checkout in this MVP — pick a provider below and open their docs when you're ready to use it.

Capabilities & modalities
Reasoning
Tool calling
Structured output
Attachments
InputText
OutputText
Provider shelf
Where to get MiniMax-M2.7-highspeed

Sorted by lowest input price

ProviderInput / 1MOutput / 1MContext

MiniMax (minimax.io)

MiniMax-M2.7-highspeed

$0.6$2.4204.8KDocs
More from Minimax