MiniMax · Flagship · 1M context window

MiniMax M3 pricing for document summarization

$0.004200 per call at 10,000 input / 1,000 output tokens.

Per call

$0.004200

10K calls/mo

$42

Cache savings

80% off input

Batch savings

0% off all

Calculate your MiniMax M3 costs

Adjust token counts, volume, and discount toggles to model your document summarization spend. Prices verified daily against provider pricing pages.

Configure your usage

10,000
100100K
1,000
5050K
10,000
1001M

Estimated cost

Monthly cost
$42
10,000 calls/month
Cost per call$0.004200
Daily cost$1
Input rate$0.30/MTok
Output rate$1.20/MTok
Analyze your real spend

Quick start

Call MiniMax M3 with the OpenAI Python SDK pointed at api.minimax.chat:

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.minimax.chat/v1",
    api_key=os.environ["MINIMAX_API_KEY"],
)
response = client.chat.completions.create(
    model="minimax-m3",
    max_tokens=1000,
    messages=[{"role": "user", "content": "Your prompt here"}]
)
# Cost: ~$0.004200 per call at standard rates
# Input:  $0.30/MTok
# Output: $1.20/MTok

What drives document summarization cost

The archetypal input-heavy task: the entire source document goes in, a short summary comes back. Cost is almost entirely a function of document length, and the output rate barely registers. Long documents can cross a provider's long-context threshold, where the whole request is re-priced at a multiple. Check the threshold before feeding in a hundred-page PDF as one call.

For MiniMax M3 specifically, that means output tokens cost 4.0x more than input, at $1.20 vs $0.30 per MTok. At this use case’s 10,000/1,000 token split, output accounts for 29% of the $0.004200 per-call cost.

Complete MiniMax M3 pricing breakdown

Standard token rates

Direction$/MTokTokens per call
Input$0.3010,000
Output$1.201,000

Prompt caching: 80% off input tokens

Caching drops input cost from $0.30 to $0.06/MTok. For repeated system prompts, that saves $0.002400 per call.

Batch API: 0% off all tokens

Submit requests asynchronously and receive 0% off all token costs. This works best for offline pipelines where latency requirements are flexible.

Monthly cost projections

Monthly volumeCost per callStandard monthlyCached monthlyYou save with caching
10,000 calls$0.004200$42$18$24
50,000 calls$0.004200$210$90$120
100,000 calls$0.004200$420$180$240
500,000 calls$0.004200$2,100$900$1,200
1,000,000 calls$0.004200$4,200$1,800$2,400

MiniMax M3 quality benchmarks for document summarization

Benchmark data for document summarization is pending for MiniMax M3. Test against your own evaluation suite before moving to production.

Benchmark data is not yet available for MiniMax M3. We recommend testing against your own evaluation criteria.

Alternative models for document summarization

10 models score 80+ on document summarization benchmarks, sorted by input rate. Cheapest: Gemini 3 Flash (90% more, 83/100 quality).

ModelProviderInput $/MTokOutput $/MTokQualityPer callvs MiniMax
Gemini 3 FlashGemini$0.50$3.0083/100$0.00800090% more
Gemini 3.6 FlashGemini$0.75$3.7575/100$0.0112168% more
Gemini 3.7 FlashGemini$0.75$3.7579/100$0.0112168% more
Gemini 3.8 FlashGemini$0.75$3.7581/100$0.0112168% more
Claude Haiku 4.5Claude$1.00$5.0082/100$0.0150257% more
Gemini 3.5 FlashGemini$1.50$9.0076/100$0.0240471% more
Gemini 3.1 ProGemini$2.00$12.0080/100$0.0320662% more
Grok 4.7Grok$2.00$6.0075/100$0.0260519% more
Claude Fable 5Claude$10.00$50.0077/100$0.15003471% more
GPT 6 AstraGPT$10.00$50.0076/100$0.15003471% more

About MiniMax M3

Provider

MiniMax

Tier

Flagship

Context

1M tokens

Released

Jun 2026

Prices from platform.minimax.io/docs/pricing/overview (read 2026-10-11). Long context (>512K tokens) is billed above the listed input and output rates. Cache hit: $0.06/MTok input. No batch discount published. Not yet benchmarked, so never recommended.

Other models from MiniMax

ModelTierInput $/MTokOutput $/MTokContext
MiniMax M2Mid-tier$0.26$1.00200K

You can compare MiniMax M3 head-to-head against any other model on our model comparison pages, or track how pricing has changed over time on the pricing history tracker.

Frequently asked questions

How much does MiniMax M3 cost for document summarization per API call?

A typical document summarization call using MiniMax M3 costs about $0.004200 per call. This estimate uses 10,000 input tokens and 1,000 output tokens at standard rates. Standard rates are $0.30 per million input tokens and $1.20 per million output tokens.

Is MiniMax M3 the best model for document summarization?

Our benchmark data does not yet include a document summarization ranking for MiniMax M3. We recommend testing it against your own evaluation criteria before production usage.

What is the cheapest model for document summarization with good quality?

The most affordable model for document summarization above 80/100 quality is Gemini 3 Flash. It comes from Gemini at $0.50 per million input tokens. Output costs $3.00 per million tokens with a quality score of 83/100. Gemini 3 Flash costs more per call than MiniMax M3 but scores higher on quality benchmarks for this task type.

How can I reduce my MiniMax M3 costs for document summarization?

Three strategies lower MiniMax M3 costs for this task type effectively. Prompt caching gives a 80% discount on input tokens when reusing system prompts. The batch API gives 0% off all tokens for asynchronous processing workloads. Prompt optimization reduces token counts through more concise instructions and context windows. Combining caching with batching brings your cost from $0.004200 to about $0.000840 per call.

How does MiniMax M3 pricing compare to other MiniMax models?

MiniMax has 1 other models alongside MiniMax M3 today: MiniMax M2 at $0.26/$1.00 per million tokens (mid-tier). The right choice depends on whether your document summarization workload prioritizes quality, cost, or speed.

What context window does MiniMax M3 support?

MiniMax M3 supports a context window of 1M tokens per API call. This sets the maximum combined length of your input prompt and generated response. For document summarization, typical calls use 10,000 input and 1,000 output tokens. That is well within this limit, leaving room for longer prompts or multi-turn conversations.

Track what you spend on AI

This calculator estimates costs based on published rates only. Connect your API usage to see where your money goes and which models drive your spend.