minimaxCertifiedReleased 05/31/2026

MiniMax M3

MiniMax-M3 is a frontier-class foundation model that unites the three capabilities defining today's frontier: a 1M-token context window, frontier coding and agentic performance, and native multimodality — the first open-weight model to deliver all three in a single system.

View API reference ↓
Input / output priceFrom$0.24 / $0.96per 1M
24h uptime100.00%
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inferencebureau.com/v1",
  apiKey: process.env.IB_API_KEY,
});

const res = await client.chat.completions.create({
  model: "minimax/minimax-m3",
  messages: [{ role: "user", content: "Why is the sky blue?" }],
});

console.log(res.choices[0].message.content);

Providers

Dispatch routes requests across these providers and fails over between them without changing the model. Restrict or order providers with team Directives. Prices are gateway list prices before the platform fee.

ProviderContextMax outputLatencyThroughputInputOutputCacheCapabilitiesZDRNo trainingRegionsStatus
Fireworks512K512K0.7 s191 tps$0.30$1.20Read $0.060Write —6 featuresYesYesGlobalCertified
gmicloud1.05M1.05M2.5 s209 tps$0.24$0.96Read $0.048Write —6 featuresNoNoGlobalCertified
minimax1M1M0.7 s—$0.30$1.20Read $0.060Write —7 featuresNoNoGlobalCertified
nebius1.05M1.05M3.2 s344 tps$0.30$1.20Read $0.060Write —6 featuresYesYesGlobalCertified

Uptime

24 hours

Request success rate per provider.

Fireworks100.00%
gmicloud100.00%
minimax100.00%
nebius100.00%

Throughput

last hour

P50 output tokens per second.

nebius344 tps
gmicloud209 tps
Fireworks191 tps
minimax—

Latency

last hour

P50 time to first token.

minimax0.7 s
Fireworks0.7 s
gmicloud2.5 s
nebius3.2 s

Getting started

Create a key on the API Keys page and set it as IB_API_KEY. See the quickstart.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inferencebureau.com/v1",
  apiKey: process.env.IB_API_KEY,
});

const res = await client.chat.completions.create({
  model: "minimax/minimax-m3",
  messages: [{ role: "user", content: "Why is the sky blue?" }],
});

console.log(res.choices[0].message.content);

Top-level parameters

Standard Chat Completions parameters work as documented. These have model-specific behavior.

ParameterTypeRequiredDescription
modelstringYesModel ID in the form creator/model, e.g. minimax/minimax-m3. Must be allowed by your team's Directives.
max_tokensnumberNoHard cap on generated tokens, and the basis for the balance reserved per request. MiniMax M3 supports up to 1,000,000 output tokens.
reasoning{ effort: 'low' | 'medium' | 'high' }NoReasoning effort, mapped to the provider's native configuration. Reasoning tokens count toward output usage.
toolsTool[]NoFunction definitions the model can call. Tool calls are returned in choices[].message.tool_calls.
Supportedmax_tokenstemperaturestoptoolstool_choicereasoninginclude_reasoningresponse_formatstructured_outputs

Input limits

InputSourcesLimits
Text—Prompt and response share the 1M-token context window
ImageURL, base64Sent as image_url content parts; counts as input tokens
PDFURL, base64Sent as file content parts; counts as input tokens

More models by minimax

ModelContextInputOutputCacheRelease
minimax/minimax-m3.1-flash1M$0.15$0.60Read $0.015Write —10/19/2026
minimax/minimax-m2.7205K$0.30$1.20Read $0.060Write $0.3803/18/2026
minimax/minimax-m2.7-highspeed205K$0.60$2.40Read $0.060Write $0.3803/18/2026
minimax/minimax-m2.5205K$0.30$1.20Read $0.030Write $0.3802/12/2026
minimax/minimax-m2.5-highspeed205K$0.60$2.40Read $0.030Write $0.3802/12/2026
minimax/minimax-m2.1205K$0.30$1.20Read $0.030Write $0.3812/23/2025
minimax/minimax-m2.1-lightning205K$0.30$2.40Read $0.030Write $0.3812/23/2025
minimax/minimax-m2205K$0.30$1.20Read $0.030Write $0.3810/27/2025