Minimax

MiniMax M3 API Pricing 2026

Compare pricing, benchmarks, and providers for MiniMax M3. Find the best value for your use case.

8 Ways to Use Fewer Tokens
Last updated: November 21, 2026 at 08:43 AM

Overview

MiniMax M3 was released on May 31, 2026. Pricing starts at $0.230 per million input tokens and $0.960 per million output tokens. The model supports a context window of up to 1.0M tokens. API access is available through Minimax.

Context Window
1.0M
tokens
Pricing
Input$0.230
Output$0.960
Cached$0.048
per 1M tokens
Speed
Output106 tok/s
TTFT0.72s
median latency
Capabilities
VisionToolsCaching

MiniMax M3 is priced at $0.230 per million input tokens and $0.960 per million output tokens. It has a context window of 1,048,576 tokens. It is available from 9 providers, with CoreWeave the cheapest at $0.230 per million input tokens (input prices range from $0.230 to $0.600). It runs at roughly 106 tokens per second with a 0.72s time to first token. On benchmarks, MiniMax M3 scores Intelligence 18.9 (24th percentile), GPQA 92.9 (92nd percentile).

Pricing Comparison

Compare MiniMax M3 with 10 similar models by price.

Current Pricing (per 1M tokens)

11 models

Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
Provider
Model
Input $/M
Output $/M
Coding
MMLU
GPQA
Context
Actions
$0.230
$0.960
—
—
92.9
1,048,576
Try
$0.200
$0.200
—
—
—
8,192
Try
$0.200
$0.200
—
—
—
33,000
Try
$0.200
$0.200
—
—
—
32,768
Try
$0.200
$0.200
—
—
—
2,048
Try
$0.200
$0.200
—
—
—
32,768
Try
$0.200
$0.200
—
—
—
2,048
Try
$0.207
$0.828
—
—
—
256,000
Try
$0.209
$0.310
—
—
—
163,840
Try
$0.216
$0.647
—
—
—
1,048,576
Try
IB
IBM
$0.220
$0.590
—
—
—
4,096
Try

* Some models use tiered pricing based on prompt length. Displayed prices are for prompts ≤ 200k tokens.

Compare Providers

MiniMax M3 is available from multiple providers with different pricing and availability.

9
Providers
$0.230
Cheapest Input/M
$0.960
Cheapest Output/M
CoreWeave
Best Price

Provider Pricing

9 models

Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
Provider
Input $/M
Output $/M
Cache Read $/M
Cache Write $/M
Uptime
C
CoreWeave
Best Price
$0.230
$0.960
$0.050
-
100.0%
$0.240
$0.960
$0.048
-
100.0%
$0.280
$1.100
$0.056
-
100.0%
V
Venice
$0.300
$1.200
$0.060
-
70.4%
Minimax
Minimax
$0.300
$1.200
$0.060
-
100.0%
$0.300
$1.200
$0.060
-
-
$0.450
$1.800
$0.090
-
100.0%
F
Featherless
$0.550
$2.200
$0.060
-
-
M
Mara
$0.600
$2.400
-
-
-
Provider pricing data sourced from OpenRouter and Helicone

Community Rankings

How does MiniMax M3 perform? Vote based on your experience.

Cost vs. Quality

Compare MiniMax M3's benchmark performance against all models.

X-axis:
Y-axis:
Loading chart...
Other models

Detailed Benchmark Scores

Intelligence
18.9 (24th pct)
Coding
-
Math
-
MMLU Pro
-
GPQA
92.9 (92nd pct)
LiveCodeBench
-
AIME
-
Aider
-
Benchmark data from Artificial Analysis and HuggingFace Open LLM Leaderboard

Try MiniMax M3

Use our Calculator

Estimate your costs based on expected token usage.

Open Cost Calculator

Try in Playground

Test MiniMax M3 directly in your browser.

Open Playground

Frequently Asked Questions

MiniMax M3 costs $0.000230 per 1,000 input tokens and $0.000960 per 1,000 output tokens.
MiniMax M3 is available from 9 providers. CoreWeave offers the best price.
CoreWeave offers MiniMax M3 at $0.230 per million input tokens, the lowest of 9 providers (input prices range from $0.230 to $0.600 per million tokens).
MiniMax M3 scores Intelligence 18.9 (24th percentile), GPQA 92.9 (92nd percentile). Only benchmarks with published data for this model are shown.
We compare MiniMax M3 with 10 similarly-priced models. See the benchmark scatter plot above to compare quality vs cost.

All Minimax Models

See pricing for all Minimax models.

View all Minimax models →