Capability badges appear only where the provider catalog explicitly lists support. A blank cell means the source is silent, not that the feature is absent.
Listed rates
Price across providers
Input price per million tokens as published by each provider. Bars are drawn from listed rates only — no traffic weighting, since the catalog observes no requests.
Lowest input$0.2/M
Across 45 priced providers
Median input$0.3/M
Midpoint of listed rates
Highest input$0.72/M
3.6× the lowest listed rate
Output range$0.88 – $2.88
Per million output tokens
Vultr$0.2/MLowest
Kilo Gateway$0.224/M
Ambient$0.23/M
Vancine$0.24/M
DevPass (LLM Gateway)$0.28/M
Deep Infra$0.28/M
Boundless$0.28/M
AIHubMix$0.288/M
Hugging Face$0.3/M
Fireworks AI$0.3/M
Cortecs$0.3/M
ZenMux$0.3/M
Pioneer$0.3/M
Abacus$0.3/M
OpenCode$0.3/M
Together AI$0.3/M
OpenRouter$0.3/M
MiniMax (minimax.io)$0.3/M
Nebius Token Factory$0.3/M
ClinePass$0.3/M
Eden AI$0.3/M
Jalapeno Cloud$0.3/M
OrcaRouter$0.3/M
Requesty$0.3/M
IteraCompute$0.3/M
Inco$0.3/M
SiliconFlow$0.3/M
Tempr Gateway$0.3/M
Novita AI$0.3/M
CommandCode$0.3/M
Standard Compute$0.3/M
MiniMax (minimax.cn)$0.314/M
Charm Hyper$0.327/M
CrossModel$0.33/M
Wafer$0.33/M
Kenari$0.36/M
TensorX$0.4/M
Merge Gateway$0.6/M
Synthetic$0.6/M
Ofox$0.6/M
Opper$0.6/M
GMI Cloud$0.6/M
Opper$0.6/M
SambaNova$0.6/M
302.AI$0.72/M
Cost calculator
Estimate a workload
$0.00
Excludes taxes, non-token charges, and tiered discounts.
Context limits also differ by provider, from 131.072K to 1.04858M tokens. Compare the provider table above before choosing on price alone.
Specification
Capabilities
Recorded from the source catalog and provider listings.
Every result stays attached to its source, version, metric and harness. Scores from different versions are never merged, and the profile below plots each benchmark against its own population rather than on a shared scale.
Each axis is this model's percentile among the 4 benchmarks it has published results for, measured against every other model with a score on that same benchmark. Percentiles are used because benchmarks do not share a scale — a 60 on one is not a 60 on another. Hover any point for the raw score.
SWE-Bench Pro
resolve rate · Claude Code · 2026-06-01
Source ↗
SWE-Bench Pro#2 of 3
59.0
56.2median 59.067.7
SWE-Bench Verified
resolved · Claude Code · 2026-06-01
Source ↗
80.52 models scored — too few for a distribution
Each strip shows every published score for that benchmark, with this model marked. The lighter shape behind the ticks is the density of results, and the dashed line is the median.
Cost against capability
Price and performance
Listed input price plotted against OSWorld-Verified, the benchmark with the widest published coverage that this model appears in.
The stepped line is the efficient frontier: at each price, the best score available for that money or less. A model sitting on it is not being beaten by anything cheaper. Price is log-scaled because listed rates span four orders of magnitude. Only models with both a listed price and a score on this benchmark can appear.
Catalog activity
Change log
Field-level changes detected between successful source imports.
Answered directly from the stored record — nothing here is generated beyond the catalog's own fields.
What is MiniMax-M3?
MiniMax multimodal model for long-context coding, perception, and agent planning. It is published by MiniMax and catalogued here from Models.dev.
How much does MiniMax-M3 cost?
Listed input pricing starts at $0.2 per million tokens from Vultr, rising to $0.72 across 45 listed providers.
What is the context length of MiniMax-M3?
MiniMax-M3 accepts up to 1.04858M tokens of context and returns up to 512K output tokens.
Does MiniMax-M3 support tool calling and structured output?
Provider catalogs list support for tool calling, reasoning, and image input.
Which providers serve MiniMax-M3?
49 providers list this model: MiniMax Token Plan (minimax.io), Nvidia, MiniMax Token Plan (minimax.cn), SCNet Token Plan, Volcengine Ark Coding Plan, Vultr and 43 more.
Are the weights for MiniMax-M3 open?
Yes. The weights are published and downloadable from Hugging Face.
When was MiniMax-M3 released?
The catalog records a release date of 2026-06-01, last verified Oct 24, 2026.
Nvidia
Vultr
Ambient
Deep Infra
AIHubMix
Hugging Face
Fireworks AI
Cortecs
ZenMux
Pioneer
Abacus
OpenCode
Together AI
OpenRouter
OrcaRouter
Requesty
SiliconFlow
Novita AI
CrossModel
Kenari
TensorX
Merge Gateway
Synthetic
Ofox
GMI Cloud