fireworks/minimax-m3

Common Name: MiniMax-M3

Fireworks
SupportedTool InvocationSupportedReasoning
CompareTry in Chat

MiniMax's reasoning model for long-context coding and agentic tasks.

Specifications

Context
512K
Maximum Output
512K
Inputtext
Outputtext

Performance (7-day Average)

Collecting…
Collecting…
Collecting…

Pricing

Input$0.30/MTokens
Cached Input$0.06/MTokens
Output$1.20/MTokens

Performance Metrics (24h)

Similar Models

$0.40/$1.60/M
ctx262Kmax66Kavailtps
InOutCap

Alibaba's multimodal reasoning model for general-purpose and agentic workloads.

$0.60/$2.40/M
ctx262Kmaxavailtps
InOutCap

NVIDIA's frontier-scale reasoning model for complex agents, long-context analysis, code, math, and science.

$0.22/$0.66/M
ctx1.0Mmax384Kavailtps
InOutCap

DeepSeek's cost-efficient hybrid-thinking model in the V4 family.

$0.22/$0.66/M
ctx1.0Mmax131Kavailtps
InOutCap

DeepSeek's official V4 Flash release for cost-efficient reasoning and agentic workloads.