Skip to main content
Watch: Stop Building Apps. Build Tools for AI Agents

Open-weight API pricing - last verified

MiniMax-M3: where to run it and what it costs

6 offers from 6 providers list MiniMax-M3 at a per-token price. The lowest listed input price is $0.30 per 1M input tokens at MiniMax (MiniMax-M3 ≤ 512k input tokens), permanent 50% off, with output at $1.20. First-party, MiniMax lists $0.30 input and $1.20 output per 1M tokens (permanent 50% off). Prices are as listed on October 18, 2026; they change often and are not a benchmark.

427B total, 23B active, mixture of experts. Native context 1,048,576 tokens, per our local-models record (from the Hugging Face model card).

Every offerQuotesRun it yourselfAll open-weight models

Offers
6
Providers
6
Lowest listed input
$0.30
First-party input
$0.30

Per-token prices

Every MiniMax-M3 offer, sorted by input price

Each row is one build as the provider lists it, with its own model ID: dated snapshots, Fast and turbo builds and regional rows are never merged. Sorted by listed input price in USD per 1M input tokens; every price is in that same unit. Not stated means the provider's page does not say.
6 hosted offers for MiniMax-M3, sorted by listed input price in USD per 1M input tokens
Provider and model IDInputUSD per 1M tokensOutputUSD per 1M tokensCached inputUSD per 1M tokensContext servedas the provider lists itQuantizationStatusSource
MiniMax (first-party)MiniMax-M3Listed as: MiniMax-M3 ≤ 512k input tokensFirst-partyQuotes for this row$0.30Page shows "Permanent 50% off" a struck-through list price$1.20$0.06Not statedNot statedStandardplatform.minimax.io
Together AIMiniMaxAI/MiniMax-M3Listed as: MiniMax M3Quotes for this row$0.30$1.20$0.06524,288Below native 1,048,576FP4Serverless Inferencetogether.ai
Fireworks AIminimax-m3Listed as: MiniMax M3Quotes for this row$0.30$1.20$0.06Not statedNot statedStandarddocs.fireworks.ai
Novitaminimax/minimax-m3Listed as: MiniMax M3Quotes for this row$0.30$1.20$0.06977Kfp8Not statednovita.ai
Azure AI Foundry (Fireworks on Foundry)FW MiniMax 3Inferred: matched by nameQuotes for this row$0.33$1.32$0.066Not statedNot statedData Zoneazure.microsoft.com
SambaNovaMiniMax-M3Quotes for this row$0.60$2.40$0.061M tokensNot statedPreviewPreviewcloud.sambanova.ai
First-party
The model's own developer selling its API.
Peak-hour price
DeepSeek's listed price during its peak hours; off-peak is half, per its page. Alibaba's busy-hour rows work the same way.
Card shows N% off
A discount tag sits beside the price on the provider's catalog card. The number is the discounted one and may be temporary.
Inferred
Our reading, not the page's words: a name-only model match, a region taken from table order, or a context figure from an unlabelled tag.
Below native
The provider serves a shorter context than the model's native window in our local-models data.
Preview
The provider lists the model as a preview, for evaluation rather than production.

Context

Served below the native context window

MiniMax-M3's native context is 1,048,576 tokens. These offers list a shorter one.

Evidence

The quote behind every value

Each value is copied from the provider's own page; one quote that backs several values shows once.

MiniMax (first-party)

MiniMax-M3 ≤ 512k input tokens

Model ID, Cached input

“MiniMax-M3 ≤ 512k input tokens Permanent 50% off $0.60 $0.30 / M tokens $2.40 $1.20 / M tokens $0.12 $0.06 / M tokens”
platform.minimax.io

Variant

“MiniMax-M3 ≤ 512k input tokens Permanent 50% off”
platform.minimax.io

Input

“MiniMax-M3 ≤ 512k input tokens Permanent 50% off $0.60 $0.30 / M tokens”
platform.minimax.io

Output

“MiniMax-M3 ≤ 512k input tokens Permanent 50% off $0.60 $0.30 / M tokens $2.40 $1.20 / M tokens”
platform.minimax.io

Status

“LLM Recharge Now - Standard - Priority Model Input Output Prompt caching Read MiniMax-M3”
platform.minimax.io

Not stated

  • Batch: No per-model batch price listed on the pricing page.
  • Context served: Served context length not stated on the pages used.
  • Quantization: Quantization not stated on the pages used.

Source notes: Above 512k input tokens: $0.60 / $2.40 / $0.12. Priority tier is 1.5x standard.

Together AI

MiniMax M3

Model ID

“Minimax Minimax M3 MiniMaxAI/MiniMax-M3 524288 $0.30 $0.06 $1.20 FP4”
docs.together.ai

Variant, Input, Output, Cached input

“MiniMax M3 $0.30 $0.06 (cached) $1.20”
together.ai

Context served

“MiniMaxAI/MiniMax-M3 524288”
docs.together.ai

Quantization

“MiniMaxAI/MiniMax-M3 524288 $0.30 $0.06 $1.20 FP4”
docs.together.ai

Status

“Serverless Inference Most teams start with serverless inference”
together.ai

Not stated

  • Batch: No per-model batch price listed on the pricing page.

Source notes: Served context 524,288 is half the 1,048,576 native context in the repo data.

Fireworks AI

MiniMax M3

Model ID

“app.fireworks.ai/models/fireworks/minimax-m3”
docs.fireworks.ai

Variant, Input, Output, Cached input

“MiniMax M3 $0.30 / $0.06 / $1.20 $0.45 / $0.09 / $1.80”
docs.fireworks.ai

Input column, Output column, Cached input column

“prices are input / cached input / output (USD per 1M tokens), in that order”
docs.fireworks.ai

Status

“In each Standard or Priority cell, prices are input / cached input / output (USD per 1M tokens), in that order”
docs.fireworks.ai

Not stated

  • Batch: No per-model batch price listed; the page states batch inference is billed at 50% of serverless pricing.
  • Context served: Served context length not stated on the pages used.
  • Quantization: Quantization not stated on the pages used.

Source notes: Priority $0.45 / $0.09 / $1.80.

Novita

MiniMax M3

Model ID, Variant

“MiniMax M3 minimax/minimax-m3”
novita.ai

Input, Output, Cached input

“Tiered pricing Input length Input price (M tokens) Output Price (M tokens) Cache Read 1 <= tokens < 524,288 $0.3 $1.2 $0.06”
novita.ai

Context served

“MiniMax M3 977K”
novita.ai

Quantization

“Provider MiniMax Quantization fp8”
novita.ai

Not stated

  • Batch: No per-model batch price listed; the pricing page states batch inference is at an introductory 50% discount for supported models.
  • Status: No availability tier or release-stage label stated for this offer on the pages used.

Source notes: 524,288 to 1,000,000 input tokens: $0.6 / $2.4 / $0.12. The main pricing table shows only "Tiered pricing" for this model.

Azure AI Foundry (Fireworks on Foundry)

FW MiniMax 3

Model ID, Output

“FW MiniMax 3 Data Zone Input: $0.33/1M Tokens Cached Input: $0.066/1M Tokens Output: $1.32/1M Tokens”
azure.microsoft.com

Variant, Input, Status

“FW MiniMax 3 Data Zone Input: $0.33/1M Tokens”
azure.microsoft.com

Cached input

“FW MiniMax 3 Data Zone Input: $0.33/1M Tokens Cached Input: $0.066/1M Tokens”
azure.microsoft.com
  • Inferred: matched by name. Azure lists this row as "FW MiniMax 3" under its Fireworks tab; it is matched to MiniMax-M3 by name only.

Not stated

  • Batch: No per-model batch price listed on the pricing page.
  • Context served: Served context length not stated on the pages used.
  • Quantization: Quantization not stated on the pages used.

Source notes: Azure labels the row "FW MiniMax 3"; matched to MiniMax-M3 by name only.

SambaNova

MiniMax-M3

Model ID, Context served

“MiniMax MiniMax-M3 1M tokens Text”
docs.sambanova.ai

Variant, Input, Output, Cached input

“MiniMax-M3 0.06 USD 0.60 USD 2.40 USD”
cloud.sambanova.ai

Input column, Output column, Cached input column

“Model Cached Input Tokens Input (per 1M tokens) Output (per 1M tokens)”
cloud.sambanova.ai

Status

“Preview models are intended for evaluation purposes and developer experimentation only”
docs.sambanova.ai

Not stated

  • Batch: No per-model batch price listed on the pricing page.
  • Quantization: Quantization not stated on the pages used.

Source notes: Listed under Preview models; runs as a text-only deployment per the docs.

Coverage

Not listed on the pages read

  • DeepInfra: gpt-oss-120b, gpt-oss-20b, MiniMax-M3 and Llama 4 Maverick are not listed on the pages read.
  • Fireworks AI: only the headline-model price table is covered; models outside it fall under size-based pricing and are not listed on the pages read.
  • Cerebras: the pay-as-you-go Developer tier lists only GPT OSS 120B and Qwen 3.8 27B; other models are Dedicated Inference by quote.
  • Cloudflare Workers AI: no Kimi K3, DeepSeek V4.1 Flash, Gemma 4 31B, MiniMax-M3 or Nemotron 3.5 rows on the pages read.
  • Fireworks AI says batch inference is billed at 50% of serverless pricing, with no per-model batch figure.
  • Novita says batch inference is at an introductory 50% discount for supported models, with no per-model batch prices.
  • Together AI shows a Batch API price toggle but lists no per-model batch figures.

Alternatives

Run MiniMax-M3 yourself, or compare its first-party API

FAQ

How much does the MiniMax-M3 API cost?

Listed input prices run from $0.30 to $0.60 per 1M input tokens across 6 offers on October 18, 2026, and output from $1.20 to $2.40 per 1M output tokens. The lowest listed input price is at MiniMax (MiniMax-M3 ≤ 512k input tokens), permanent 50% off. First-party: MiniMax at $0.30 input.

Which providers serve MiniMax-M3?

Together AI, Fireworks AI, Novita AI, SambaNova Cloud, Azure AI Foundry and MiniMax. Each lists one build, shown under the provider's own model name.

Do all providers serve MiniMax-M3's full context window?

MiniMax-M3's native context is 1,048,576 tokens in our local-models data. Served below that: Together AI (MiniMax M3) at 524,288. Not stated by 3 offers.

Is there a batch price for MiniMax-M3?

No per-model batch price for MiniMax-M3 is listed on the pages read. Fireworks AI says batch inference is billed at 50% of serverless pricing, with no per-model batch figure. Novita says batch inference is at an introductory 50% discount for supported models, with no per-model batch prices. Together AI shows a Batch API price toggle but lists no per-model batch figures.

Sources

Last verified from each provider's own pages (8 sites). This is a directory of listed prices and what each provider states about the model it serves, not a benchmark. Prices change often; check the provider's page before you commit. Speed figures appear only where a provider states them, labelled Vendor-stated.

Newsletter

Know when open-weight API prices move

One email per week. New model releases, price changes and where to run them, and what they mean for what you build.

Read more about MiniMax-M3

Related

Run open-weight models locally

The self-host alternative: downloads, memory needs and commands for each model.

Open-weight model licenses

Which of these models you may use commercially, and on what terms.

LLM API cost levers

Prompt caching, batch discounts and service tiers by provider.

Free LLM API tiers

Which providers have a standing free tier or credits.

OpenAI-compatible endpoints

Base URLs and limits for switching providers without rewriting code.

LLM gateways and routers

Route one model across several of these providers with fallbacks.

Other open-weight models: DeepSeek V4 Pro, DeepSeek V4.1 Flash, Qwen3.8-27B, Kimi K3, GLM-5.3, gpt-oss-120b, gpt-oss-20b, Llama 4 Maverick, Gemma 4 31B, Mistral Large 3, NVIDIA Nemotron 3.5 Super VL 120B-A12B.

Providers on this page: Together AI, Fireworks AI, Novita AI, SambaNova Cloud, Azure AI Foundry, MiniMax.