BroadRouter

MiniMax M3.1 Flash API pricing

Updated

Among the 9 providers we checked (prices read 2026-11-14 to 2026-11-15), 7 tie for the lowest blended standard price for MiniMax M3.1 Flash; MiniMax charges USD 0.15 per 1M input tokens and USD 0.60 per 1M output tokens. The median across 9 standard prices is USD 0.15 / USD 0.60. That is MiniMax's own API. Each price is read from the provider's own pricing page.

MiniMax · slug minimax-m3.1-flash · up to 1,048,576 tokens of context · 9 providers with a standard price. Every price is read from the provider's own pricing page and linked in its row, checked 2026-11-15. No aggregator feed. Download all prices (every provider and model, with sources, CSV or JSON). How it compares with the market: the LLM API price index.

What does MiniMax charge for MiniMax M3.1 Flash?

Input
USD 0.15
Cached input
USD 0.015
Output
USD 0.60
Blended 3:1
USD 0.2625

USD per 1M tokens on MiniMax, model MiniMax-M3.1-Flash, standard tier. Source, checked 2026-11-14.

Is a host cheaper than MiniMax? They tie. DigitalOcean and MiniMax's own API both work out at USD 0.2625 per 1M tokens on the 3:1 blend.

MiniMax M3.1 Flash model facts

Facts from MiniMax's model card for MiniMaxAI/MiniMax-M3.1-Flash and the Hugging Face model API, read 2026-11-16. BroadNet did not verify them, and hosts may serve the model at a different precision. BroadRouter is BroadNet's site.

MiniMax M3.1 Flash: facts as stated by the model card and the Hugging Face model API, with sources
FactAs statedSource
Open weightsYes. The weights are in a public Hugging Face repository (MiniMaxAI/MiniMax-M3.1-Flash) with no access gate.Hugging Face model API, checked 2026-11-16
Quote
“"private": false, "gated": false, 49 .safetensors files listed”
LicenceCustom licence: minimax-communityMiniMax model card metadata, checked 2026-11-16
Quote
“license: other; license_name: minimax-community”
Total parametersApproximately 428BMiniMax model card, checked 2026-11-16
Quote
“Parameters: Approximately 428B total; 23B activated per token”
Active parameters per token23BMiniMax model card, checked 2026-11-16
Quote
“Parameters: Approximately 428B total; 23B activated per token”
Context lengthUp to 1,000,000 tokensMiniMax model card, checked 2026-11-16
Quote
“Context window: Up to 1,000,000 tokens”
Input and outputText, image and video in; text outMiniMax model card, checked 2026-11-16
Quote
“Inputs / output: Text, image, and video inputs; text output”
Tool callingNot found on MiniMax's model card when we read itchecked 2026-11-16
First published on Hugging Face (not necessarily the release date)2026-10-17Hugging Face model API, checked 2026-11-16
Quote
“"createdAt": "2026-10-17T06:37:50.000Z"”

MiniMax M3.1 Flash price per provider

USD per 1M tokens. Standard prices are ranked on a blend of 3 input tokens to 1 output token, cheapest first; the dearest standard price is 2.0× the cheapest.

MiniMax M3.1 Flash API prices by provider
#ProviderInputCached inputOutputBlended 3:1ContextPrecisionSource
1MiniMax tied cheapest maker
MiniMax-M3.1-Flash
Notes and source quote

Cached price is the prompt-caching read price.

“MiniMax-M3.1-Flash $0.15 $0.60 $0.015”
USD 0.15USD 0.015USD 0.60USD 0.2625not statednot statedMiniMax page
checked 2026-11-14
re-checked 2026-11-16
2DigitalOcean tied cheapest
Notes and source quote

DigitalOcean-hosted; public preview.

“MiniMax M3.1-Flash (Public Preview) — Processing modePrompt lengthInputOutputCache read: Standard All prompts$0.15$0.60$0.015”
USD 0.15USD 0.015USD 0.60USD 0.2625not statednot statedDigitalOcean page
checked 2026-11-14
re-checked 2026-11-16
3Featherless tied cheapest
MiniMaxAI/MiniMax-M3.1-Flash
Notes and source quote

Developer plan (per-token billing, from 50 USD a month in credits).

“PRICING: INPUT $0.15 / CACHED $0.015 / OUTPUT $0.6”
USD 0.15USD 0.015USD 0.60USD 0.26251,048,576FP8Featherless page
checked 2026-11-15
re-checked 2026-11-16
4Fireworks AI tied cheapest
accounts/fireworks/models/minimax-m3p1-flash
Notes and source quote
“Available Serverless $0.15 / $0.015 / $0.60 Run queries immediately, pay only for usage Per 1M Tokens (input/cached input/output)”
USD 0.15USD 0.015USD 0.60USD 0.26251,048,576not statedFireworks AI page
checked 2026-11-14
re-checked 2026-11-16
5GMI Cloud tied cheapest
MiniMaxAI/MiniMax-M3.1-Flash
Notes and source quote
“Price (per 1M tokens) Input $0.15 Output $0.60 Cache Read $0.015 Cache Write -”
USD 0.15USD 0.015USD 0.60USD 0.26251,048,576FP8GMI Cloud page
checked 2026-11-15
re-checked 2026-11-16
6Parasail tied cheapest
Notes and source quote
“MiniMax M3.1 Flash $0.15 $0.60 $0.015”
USD 0.15USD 0.015USD 0.60USD 0.2625not statednot statedParasail page
checked 2026-11-14
re-checked 2026-11-16
7Together AI tied cheapest
Notes and source quote

US geo-pinned option: $0.1875 in / $0.75 out.

“MiniMax M3.1 Flash $0.15 $0.015 (cached) $0.60”
USD 0.15USD 0.015USD 0.60USD 0.2625not statednot statedTogether AI page
checked 2026-11-14
re-checked 2026-11-16
8Venice
minimax-m3-1-flash
Notes and source quote
“| MiniMax M3.1 Flash | `minimax-m3-1-flash` | $0.1875 | $0.75 | $0.01875 | — | Private |”
USD 0.1875USD 0.01875USD 0.75USD 0.32811,000,000not statedVenice page
checked 2026-11-15
re-checked 2026-11-16
9SambaNova
MiniMax-M3.1-Flash
Notes and source quote
“MiniMax-M3.1-Flash 0.03 USD 0.30 USD 1.20 USD”
USD 0.30USD 0.03USD 1.20USD 0.525not statednot statedSambaNova page
checked 2026-11-14
re-checked 2026-11-16

Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).

What does MiniMax M3.1 Flash cost for a real workload?

Monthly cost over 30 days at each standard price, using the presets of the LLM API cost calculator. Providers without a cached price bill cached input at the input price.

  • Support chatbot: 2,000 requests a day, 1,500 input tokens (60% cached), 300 output.
  • RAG over documents: 1,000 requests a day, 8,000 input tokens (30% cached), 500 output.
  • Coding agent (one developer): 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning.
Monthly cost of three workloads on MiniMax M3.1 Flash, by provider
ProviderSupport chatbotRAG over documentsCoding agent (one developer)
MiniMax (maker)USD 17.01USD 35.28USD 117.45
DigitalOceanUSD 17.01USD 35.28USD 117.45
FeatherlessUSD 17.01USD 35.28USD 117.45
Fireworks AIUSD 17.01USD 35.28USD 117.45
GMI CloudUSD 17.01USD 35.28USD 117.45
ParasailUSD 17.01USD 35.28USD 117.45
Together AIUSD 17.01USD 35.28USD 117.45
VeniceUSD 21.26USD 44.10USD 146.81
SambaNovaUSD 34.02USD 70.56USD 234.90

For the support chatbot, the cheapest price (MiniMax and 6 others, tied, USD 17.01 a month) saves USD 0 against the median (USD 17.01). For the coding agent the gap is USD 0 a month.

Which MiniMax M3.1 Flash provider is cheapest for your traffic?

MiniMax, DigitalOcean, Featherless, Fireworks AI, GMI Cloud, Parasail and Together AI share the lowest input price (USD 0.15) and the lowest output price (USD 0.60), so they are the cheapest standard price at every mix of input and output tokens, before cache discounts.

MiniMax M3.1 Flash: price per 1M tokens at 3 input to 1 output, by share of input served from cache
ProviderNo cache hits50% cached90% cached
MiniMax (maker)USD 0.2625 cheapestUSD 0.2119 cheapestUSD 0.1714 cheapest
DigitalOceanUSD 0.2625 cheapestUSD 0.2119 cheapestUSD 0.1714 cheapest
FeatherlessUSD 0.2625 cheapestUSD 0.2119 cheapestUSD 0.1714 cheapest
Fireworks AIUSD 0.2625 cheapestUSD 0.2119 cheapestUSD 0.1714 cheapest
GMI CloudUSD 0.2625 cheapestUSD 0.2119 cheapestUSD 0.1714 cheapest
ParasailUSD 0.2625 cheapestUSD 0.2119 cheapestUSD 0.1714 cheapest
Together AIUSD 0.2625 cheapestUSD 0.2119 cheapestUSD 0.1714 cheapest

USD per 1M tokens, 3 input tokens to 1 output token, each provider's cheapest standard row; 2 dearer providers are in the price table above. A provider without a cached price bills cached input at the input price. Any charge for writing to the cache, which some providers add, is not included.

All 9 providers publish a cached-input price below the input price: MiniMax (90% off), DigitalOcean (90% off), Featherless (90% off), Fireworks AI (90% off), GMI Cloud (90% off) and 4 more.

Context windows differ: 1,048,576 tokens at Featherless, Fireworks AI and GMI Cloud; 1,000,000 tokens at Venice. MiniMax, DigitalOcean, Parasail, Together AI and SambaNova do not state one. The cheapest row is not always the one that fits a long prompt.

What does MiniMax M3.1 Flash cost in other languages?

The same text needs a different number of tokens in each language. With the MiniMax M3 tokenizer, sending 1M characters costs this much at the cheapest standard input price we found for MiniMax M3.1 Flash:

ContentInput per 1M charactersCheapest provider
EnglishUSD 0.031DigitalOcean
Arabic MSAUSD 0.046DigitalOcean
HindiUSD 0.089DigitalOcean
ChineseUSD 0.084DigitalOcean
CodeUSD 0.039DigitalOcean

From BroadRouter's real cost by language dataset, which covers 15 languages and content types for every model we could match to a measured tokenizer.

Estimate your own bill

The MiniMax models whose cheapest standard price is closest to MiniMax M3.1 Flash's (USD 0.2625 blended):

MiniMax models priced closest to MiniMax M3.1 Flash
ModelCheapest inputCheapest outputMax contextProviders
MiniMax M2.7USD 0.21USD 0.84204,8003
MiniMax M3USD 0.23USD 0.961,048,57610
MiniMax M2.5USD 0.27USD 0.95204,8006
MiniMax M2USD 0.2775USD 1.11204,8004
Minimax M2.1USD 0.30USD 1.20204,8003

Priced closest from other makers: Command R (Cohere, USD 0.2625) · GPT-4o mini (OpenAI, USD 0.2625) · Qwen3 Coder Next (Qwen, USD 0.29).

Compare MiniMax M3.1 Flash with

Also compared: vs DeepSeek V4.1 Flash · vs Qwen3.8 27B · vs MiniMax M3.

Every MiniMax M3.1 Flash price comparison · All model-vs-model price comparisons

All 428 models: API prices compared · Cheapest LLM APIs right now · LLM API price index (open data) · Download all prices (CSV, JSON) · Price change log

Questions

How much does the MiniMax M3.1 Flash API cost per token?

From USD 0.15 per 1M input tokens (USD 0.00000015 per token) and USD 0.60 per 1M output tokens (USD 0.0000006 per token) at the lowest standard prices we found. The median of 9 standard prices is USD 0.15 input and USD 0.60 output. Each price was read from the provider's own pricing page; the source is linked in its row.

Which provider is cheapest for MiniMax M3.1 Flash?

Among the 9 providers we checked (prices read 2026-11-14 to 2026-11-15), 7 are tied for the lowest price: MiniMax, DigitalOcean, Featherless, Fireworks AI, GMI Cloud, Parasail and Together AI, each USD 0.2625 per 1M on a blend of 3 input tokens to 1 output token. For input alone the lowest price is USD 0.15 (MiniMax and 6 others, tied); for output alone, USD 0.60 (MiniMax and 6 others, tied). Batch, flex, priority and fast tiers are shown in the table but not ranked.

Is MiniMax M3.1 Flash cheaper from a host than from MiniMax?

They tie. DigitalOcean and MiniMax's own API both work out at USD 0.2625 per 1M tokens on the 3:1 blend.

Does MiniMax M3.1 Flash have cached input pricing?

All 9 standard prices include one. The lowest is USD 0.015 per 1M at MiniMax; the median is USD 0.015. Providers without one bill cached input at the input price. What cached input means.

What is the MiniMax M3.1 Flash context window?

Up to 1,048,576 tokens. 1 standard price comes with less, down to 1,000,000 tokens (Venice). Check the context column before you pick the cheapest row for long prompts. Context window calculator.

How much does a coding agent cost per month on MiniMax M3.1 Flash?

For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 117.45 a month at MiniMax, USD 117.45 at the median price and USD 234.90 at SambaNova. Try your own numbers.

Is MiniMax M3.1 Flash free to use through an API?

No provider in our data lists a free price for MiniMax M3.1 Flash as of 2026-11-15. Free tiers and credits by provider (checked 2026-11-14) lists general offers that do not name a model; all free LLM API models are on one page.

Is MiniMax M3.1 Flash open source, with open weights, and what is its licence?

MiniMax publishes the weights on Hugging Face as MiniMaxAI/MiniMax-M3.1-Flash, in a public repository with no access gate. The licence, as the MiniMax model card metadata states it: Custom licence: minimax-community. Open weights means you can download and run the model yourself; what you may do with it, including commercial use, is set by that licence, so read it in full (checked 2026-11-16). These facts come from MiniMax's card and the Hugging Face model API; BroadNet did not verify them, and hosts may serve the model at a different precision.

How many parameters does MiniMax M3.1 Flash have?

Total parameters, as the MiniMax model card states them: Approximately 428B. Active parameters per token: 23B. (checked 2026-11-16; BroadNet did not verify these figures.)

How do I call MiniMax M3.1 Flash with the OpenAI SDK?

BroadNet does not serve MiniMax M3.1 Flash. Use the OpenAI-compatible base URL of a provider that lists it: create the client with OpenAI(base_url=..., api_key=...) and pass that provider's model ID. Documented base URLs for providers on this page, in alphabetical order: Fireworks AI (https://api.fireworks.ai/inference/v1, model accounts/fireworks/models/minimax-m3p1-flash) and Together AI (https://api.together.ai/v1). Each provider page quotes the provider's docs with a check date.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity