SShogo Bench

MiniMax-M3.1-Flash

Frontier multimodal coding model with 1M context window and tunable thinking depth

Shogo Agent Index

Unranked

Not ranked yet: 0 agentic benchmarks measured, and we need at least 2 plus an overall capability score. It will be ranked as results are published.

Agentic coding
—
estimated
Long-horizon autonomy
—
estimated
Knowledge-work agents
—
estimated
Computer use
—
estimated
Security & context learning
—
estimated

Price

Input
$0.15/M
Output
$0.60/M
Cache read
$0.015/M
3:1 blend
$0.26/M
Agent-effective
$0.060/M

Cheapest host for agents: DigitalOcean at $0.060/M.

Agent-effective = 20 input tokens per output token, 85% cache hits. Why.

Agentic benchmarks

BenchmarkScoreNormalisedIndex weightHarness / source
SWE-bench Verifiedest.8%—
Terminal-Bench 2.0est.8%—
DeepSWEest.6%—
FrontierSWEest.5%—
CursorBenchest.4%—
GSO-Benchest.4%—
METR Time Horizonsest.10%—
Vending-Bench 2est.6%—
PostTrainBenchest.4%—
APEX-Agentsest.8%—
GDPvalest.7%—
Remote Labor Indexest.5%—
DeepResearch Benchest.5%—
OSWorld 2.0est.6%—
OSWorldest.4%—
Cybenchest.5%—
CL-benchest.5%—

API hosts

Live prices and uptime for every host serving MiniMax-M3.1-Flash via OpenRouter.

HostInputOutputCache readAgent $/MUptime 24hQuant
DigitalOcean$0.15$0.60$0.015$0.06099.8%—
Fireworks$0.15$0.60$0.015$0.06094.0%—
GMICloud$0.15$0.60$0.015$0.06097.6%fp8
Inferact vLLM$0.15$0.60$0.015$0.060100.0%nvfp4
InferenceNet$0.15$0.60$0.015$0.06099.0%fp4
InferenceNet$0.15$0.60$0.015$0.06099.5%fp4
Makora$0.15$0.50$0.015$0.06099.6%fp4
Minimax$0.15$0.60$0.015$0.060100.0%—
ModelRun$0.15$0.60$0.015$0.060100.0%fp4
Nebius$0.15$0.60$0.015$0.060100.0%fp4
Parasail$0.15$0.60$0.015$0.06099.9%fp8
SambaNova$0.15$0.60$0.015$0.06099.4%—
StreamLake$0.14$0.54$0.013$0.060100.0%fp8
Together$0.15$0.60$0.015$0.06099.7%—
Wafer$0.14$0.54$0.013$0.06099.9%nvfp4