MiniMax-M2.5-highspeed
High-speed MiniMax model for low-latency coding and agent workflows
Context
204,800
Max output
131,100
Input / 1M
$0.60
Output / 1M
$2.40
Providers
11
01Profile
Profile
Released
2026-02-13
Last updated
2026-02-14
Knowledge cutoff
—
Weights
Open
02Capabilities
Capabilities
Input
text
Output
text
Reasoning
Yes
Tool calling
Yes
Structured output
No
Attachments
No
Cache read
$0.06
Cache write
$0.38
03Pricing
Pricing across 8 providers
Per 1M tokens, USD. Sorted by input price. First-party row highlighted.
04History
Change history
12+ recent events since 2026-02-13
2026-08-20Addedllmgateway-providersoffering→ new
2026-07-29Contextmerge-gatewayMax output—→ 8,192
2026-07-09Removedrouting-runofferingremoved→ new
2026-06-07ContextvercelContext window204,800→ new
2026-06-06ContextvercelContext window0→ 204,800
2026-06-06ContextvercelMax output0→ 131,000
2026-06-04Contextrouting-runMax output131,072→ new
2026-06-03Price upllmgatewayinput / 1M—→ $0.60
2026-06-03Price upllmgatewayoutput / 1M—→ $2.40
2026-06-03Price upmerge-gatewayinput / 1M—→ $0.60
2026-06-03Price upmerge-gatewayoutput / 1M—→ $2.40
2026-05-27Addedmerge-gatewayoffering→ new