BroadRouter

MiniMax API pricing

Updated

MiniMax lists standard per-token prices on its own pricing page for 2 models. The cheapest is MiniMax M3.1 Flash at USD 0.15 input and USD 0.60 output per 1M tokens; the dearest is MiniMax M3 at USD 0.30 / USD 1.20. It publishes cached-input prices for all of them, plus priority prices (no batch or flex). Checked 2026-11-14.

MiniMax is a model maker: 2 of the 2 models here are its own. By maker: MiniMax 2. 3 prices, each read from MiniMax's own pricing page, checked 2026-11-14. BroadRouter is BroadNet's own site and does not sell MiniMax's services. Automated re-check 2026-11-16: 3 of 3 prices still matched the provider's page.

Models with a standard price
2
Median input / output
USD 0.225 / USD 0.90
Cached-input prices
2 of 2
Cheapest host for
1 of 2 shared models

Which models is MiniMax the cheapest provider for?

Of the 2 models that MiniMax and at least one other provider both price at the standard tier, MiniMax has the lowest price for 1, ranked on a blend of 3 input tokens to 1 output token (a tie with another provider at the same price; the maker's own API is listed first on a tie).

Models where MiniMax is the cheapest provider
ModelMiniMax input / outputNext cheapestSaving on 3:1 blendProviders
MiniMax M3.1 FlashUSD 0.15 / USD 0.60DigitalOcean USD 0.15 / USD 0.60tie9

The 2 models MiniMax sells that the most other providers also sell, with MiniMax's rank among them on the 3:1 blend.

MiniMax on the most widely hosted models
ModelMiniMaxRankCheapest
MiniMax M3USD 0.30 / USD 1.204 of 10CoreWeave Forge USD 0.23 / USD 0.96
MiniMax M3.1 FlashUSD 0.15 / USD 0.601 of 9MiniMax (this page)

MiniMax price list

USD per 1M tokens: 3 prices for 2 models, one row per model with any other service tiers stacked under the standard price. Sources checked 2026-11-14 unless a row says otherwise. "vs maker" compares a standard price with the model maker's own API on the 3:1 blend; a minus means MiniMax is cheaper. MiniMax is the maker of every model here, so there is no maker price to compare with.

MiniMax API prices by model
ModelTierInputCachedOutputContextvs makerSource
MiniMax M3standard
priority
USD 0.30
USD 0.45
USD 0.06
USD 0.09
USD 1.20
USD 1.80
not statedown modelsource
MiniMax M3.1 FlashstandardUSD 0.15USD 0.015USD 0.60not statedown modelsource
  • Cached "—" means MiniMax's page shows no cache price for that row; budget cached tokens at the input price.
  • Context "not stated": MiniMax's pricing page does not give context windows.

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

What service tiers does MiniMax publish?

  • priority (1 row). Across 1 model with both prices, the median priority price is 1.5× standard. MiniMax row note: “Priority tier (service_tier=priority, 1.5x standard). Prompts up to 512K input tokens, after the "Permanent 50% off" MiniMax shows on its list price (0.9 input, 3.6 output, 0.18 cache read). Prompts over 512K cost double. Cached price is the prompt-caching read price.”

Cached input: 2 of 2 standard prices include a cache-read price, a median 15% of the input price. What cached input means.

What we recorded about MiniMax's pricing page: MiniMax international platform (platform.minimax.io). MiniMax M2.7 and M2.5 are not on the price page. Video, image, speech and tool prices left out.

BroadNet Inference and MiniMax

BroadRouter is BroadNet's own site, so BroadNet is never ranked on this page. BroadNet Inference serves none of the models MiniMax prices. BroadNet Inference pricing.

More on MiniMax

Questions

How much does the MiniMax API cost per token?

MiniMax's standard prices run from USD 0.15 input and USD 0.60 output per 1M tokens (MiniMax M3.1 Flash) to USD 0.30 / USD 1.20 (MiniMax M3). The median across 2 standard prices is USD 0.225 input and USD 0.90 output per 1M, which is USD 0.000000225 per input token. Input, cached input and output are billed separately.

What is the cheapest model on MiniMax?

MiniMax M3.1 Flash, at USD 0.15 input and USD 0.60 output per 1M tokens (USD 0.2625 on a 3:1 input-to-output blend).

Is MiniMax cheaper than other providers?

It depends on the model. Of 2 models that other providers also price, MiniMax is the cheapest standard price for 1 (all of them tied with another provider), for example MiniMax M3.1 Flash; another provider is cheaper for 1; and it is the dearest for none. Its median rank is 2.5 of a median 9.5 providers, on a 3:1 input-to-output blend.

Does MiniMax have batch, cached or priority pricing?

Cached input: yes, for 2 of 2 standard prices, at a median 15% of the input price. Other tiers: priority on 1 row (median input 1.5× standard).

How much does a chatbot cost per month on MiniMax?

For 2,000 requests a day, 1,500 input tokens (60% cached), 300 output, over 30 days: USD 17.01 on MiniMax M3.1 Flash and USD 35.64 on MiniMax M3. Try your own numbers.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity