LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

MiniMax Latest

minimax·minimax/minimax-latest·GA·Closed·minimax series
Lab latest market for MiniMax supply. You contract for the latest qualifying route, not a specific model.

Specs & pricing

Input / output per 1M tokens
Official price
—
Lowest paid·NanoGPTGateway
$0.30 / $1.20
Blended $0.53
Context
512,000
Output limit
80,000
Knowledge cutoff
—
Released / updated
2026-07-06 / 2026-07-06
Capabilities
✓ Reasoning✓ Tool use✓ Structured outputTemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
TextImage

Available at 2 providers1 with public prices

  • ProviderInput / Output
  • NanoGPTGateway
    $0.30 / $1.20
    Cache read $0.06Context 512,000Output limit 80,000
  • The Grid AIGateway
    — / —
    Context 1,000,000 ⚠Output limit 512,000hostTable.undisclosed
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
NanoGPTGateway$0.30$1.20$0.06—512,00080,000
The Grid AIGateway————1,000,000 ⚠512,000hostTable.undisclosed

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Reasoning control

Toggle (on / off)effort = loweffort = mediumeffort = high

Interleaved thinking (reasoning between tool calls) is declared by 1 of 2 providers.

Your usage cost

Common scenarios
1NanoGPT$91.20
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.53$02026-08-052026-11-13
2026-11-13Input list —Output list —Min blended $0.53

Related models

MiniMax-M3.1-Flashsame series$0.15 / $0.60MiniMax H3same series—MiniMax H3 Maxsame series—
Data partly from models.dev (MIT)