MiniMax M3

minimax-m3 by Minimax Released June 1, 2026

ReasoningFunction callingStructured outputPrompt cachingWeb searchComputer useImage inputFile inputAudio inputVideo inputEU hostingFree endpointUp to % off

Input from

$0.28 / 1M

Output from

$1.1 / 1M

Cached input from

$0.056 / 1M

Context window

1.05M

Endpoints

from 8 providers

Regions

Monde, Asie, Europe, États-Unis

About MiniMax M3

MiniMax-M3 est un modèle de base multimodal développé par MiniMax. Il prend en charge les entrées de type texte, image et vidéo avec une sortie textuelle, dispose d’une fenêtre de contexte de 1 million de tokens et est adapté aux tâches agentiques à long terme, au codage, etc.

MiniMax M3 est un modèle conversationnel développé par Minimax, disponible sur Eden AI via 8 endpoints chez 8 fournisseurs, à partir de 0,28 $ par million de tokens en entrée et 1,1 $ par million de tokens en sortie, avec une fenêtre de contexte allant jusqu'à 1,05M tokens.

Providers and prices

8 endpoints from 8 providers, cheapest first, in USD per million tokens. Every one is called with the same Eden AI key: pin one with its endpoint ID, or let Eden AI route for you. .

Endpoint

Region

Context

Input / 1M

Output / 1M

Cached / 1M

Supports

DeepInfra (États-Unis)Official−%deepinfra/MiniMaxAI/MiniMax-M3

États-Unis

524K

$0.28$0.28

$1.1

$0.056

ReasoningToolsJSONCacheVisionWeb

Tencent Cloud (Asie)Official−%tencent/minimax-m3

Asie

$0.3$0.3

$1.2

$0.06

ReasoningToolsJSONCacheVisionWeb

Fireworks AI (États-Unis)Official−%fireworks_ai/accounts/fireworks/models/minimax-m3

États-Unis

512K

$0.3$0.3

$1.2

$0.06

ReasoningToolsJSONCacheVisionWeb

NebiusOfficial−%nebius/MiniMaxAI/MiniMax-M3

Monde

1.05M

$0.3$0.3

$1.2

$0.3

ReasoningToolsJSONCacheVisionWeb

Minimax (Asie)Official−%minimax/MiniMax-M3

Asie

524K

$0.3$0.3

$1.2

$0.06

ReasoningToolsJSONCacheVisionWeb

Together AIOfficial−%together_ai/MiniMaxAI/MiniMax-M3

Monde

524K

$0.3$0.3

$1.2

$0.06

ReasoningToolsJSONCacheVisionWeb

TensorX (Europe)Official−%tensorx/minimax/minimax-m3

Europe

1.05M

$0.4$0.4

$0.1

ReasoningToolsJSONCacheVisionWeb

GreenPT (Europe)Official−%greenpt/minimax-m3

Europe

$0.4951$0.4951

$2.4757

$0.1238

ReasoningToolsJSONCacheVisionWeb

Performance

Measured on real Eden AI traffic over the last 30 days. Endpoints with too little traffic are not shown.

Fastest first token

0.63 s

Nebius

Lowest latency

1.12 s

Fireworks AI (États-Unis)

Highest throughput

184.92 tok/s

Nebius

Best availability

100%

Fireworks AI (États-Unis)

Endpoint

First token

Latency p50

Latency p95

Throughput

Availability

Cache hits

Tool errors

JSON errors

DeepInfra (États-Unis)

0.77 s

5.19 s

48.3 s

28.27 tok/s

99.44%

39.48%

24.24%

0.37%

Tencent Cloud (Asie)

tok/s

Fireworks AI (États-Unis)

0.74 s

1.12 s

3.64 s

71.08 tok/s

100%

75.61%

0.66%

Nebius

0.63 s

1.62 s

6.13 s

184.92 tok/s

100%

28.85%

0.14%

Minimax (Asie)

1.51 s

4.3 s

68.86 s

85.31 tok/s

100%

89.01%

Together AI

tok/s

TensorX (Europe)

1.74 s

3.83 s

22.77 s

28.63 tok/s

99.83%

98.15%

0.93%

GreenPT (Europe)

tok/s

Estimate your monthly cost

Enter your expected volume to compare every endpoint at once.

Call MiniMax M3 with Eden AI

Use the model ID to let Eden AI pick an endpoint, or an endpoint ID from the table above to pin one.

import requests

response = requests.post(
    "https://api.edenai.run/v3/chat/completions",
    headers={"Authorization": "Bearer YOUR_EDENAI_API_KEY"},
    json={
        "model": "",
        "messages": [{"role": "user", "content": "Hello!"}],
    },
)
print(response.json())

curl https://api.edenai.run/v3/chat/completions \
  -H "Authorization: Bearer YOUR_EDENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "", "messages": [{"role": "user", "content": "Hello!"}]}'

const response = await fetch("https://api.edenai.run/v3/chat/completions", {
  method: "POST",
  headers: {
    Authorization: "Bearer YOUR_EDENAI_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "",
    messages: [{ role: "user", content: "Hello!" }],
  }),
});
console.log(await response.json());

Questions about MiniMax M3

How much does MiniMax M3 cost?

On Eden AI, prices for this model start at $0.28 per million input tokens and $1.1 per million output tokens. Prices differ by endpoint; the providers table lists each one. .

What is the context window of MiniMax M3?

Up to 1.05M tokens, depending on the endpoint.

Which providers serve MiniMax M3?

8 endpoints from 8 providers, available in: Monde, Asie, Europe, États-Unis. All of them are called with the same Eden AI API key.

Can I run MiniMax M3 in the EU?

Yes. At least one endpoint is hosted in Europe; pin it with its endpoint ID from the providers table to keep requests in the EU.

How fast is MiniMax M3?

Over the last 30 days, the fastest first token was 0.63 s (Nebius) and the highest throughput was 184.92 tokens per second (Nebius).

About MiniMax M3

Providers and prices

Performance

Estimate your monthly cost

Call MiniMax M3 with Eden AI

Questions about MiniMax M3

More from Minimax