MiniMax M3 is MiniMax's frontier model positioned as the first open-weight release to combine three frontier capabilities: coding, agentic reasoning, and native multimodal understanding.
- Input
- text image video $0.3/M
- Output
- text $1.2/M
- Cache read
- $0.06/M
- Context
- 1M
- vs GPT-4o
- ~94% cheaper
Price in context
Where the price sits among 60 comparable models
The bar shows how this model’s price compares with every other model of the same kind on Synthorai. The cheapest and the most expensive are named at each end. These are base rates; batch, region and cache-write discounts are on the pricing page.
Specs & limits
Tokens
| Context window (vendor spec) | 1,000,000 |
|---|---|
| Max output (vendor spec) | 524,288 |
Prompt caching
| How it caches | automatic |
|---|---|
| Min prefix | 512 |
Thinking
| Vendor control | thinking.type + reasoning_split |
|---|---|
| Accepted values | thinking.type adaptive · disabled; reasoning_split boolean |
| Default | adaptive: thinking on, with the model deciding when extra reasoning helps applied when the request sets nothing |
| Can be turned off | Yes |
| Thinking behaviour | reasoning_split only moves the trace. On, it returns in reasoning_content and reasoning_details; off, it stays inline in content wrapped in think tags, and the full assistant message including it must be passed back on tool-calling turns. |
| Parameter | reasoning_effort |
| Values | minimal · low · medium · high the gateway's parameter surface - the vendor mapping above applies |
Model
| Modalities | text + image + video → text |
|---|---|
| Parameters | 428B total · 23B active MoE |
| License | MiniMax Community License |
- MSA sparse attention with 1M-token context (standard billing up to 512K input)
- ~428B/~23B active MoE
- native multimodal (image + video input), computer use, adaptive thinking
- automatic prefix caching from 512+ input tokens
Use MiniMax M3 in 30 seconds
OpenAI-compatible: swap the base_url, keep your SDK. POST /v1/chat/completions
from openai import OpenAI
client = OpenAI(
base_url="https://synthorai.io/v1",
api_key="sk-syn-...",
)
resp = client.chat.completions.create(
model="minimax-m3",
messages=[{"role": "user", "content": "Summarize this diff"}],
reasoning_effort="medium",
)
print(resp.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://synthorai.io/v1",
apiKey: "sk-syn-...",
});
const resp = await client.chat.completions.create({
model: "minimax-m3",
messages: [{ role: "user", content: "Summarize this diff" }],
reasoning_effort: "medium",
});
console.log(resp.choices[0].message.content);curl https://synthorai.io/v1/chat/completions \
-H "Authorization: Bearer sk-syn-..." \
-H "Content-Type: application/json" \
-d '{
"model": "minimax-m3",
"messages": [{"role": "user", "content": "Hello"}],
"reasoning_effort": "medium"
}'package main
import (
"context"
"fmt"
"github.com/openai/openai-go/v3"
"github.com/openai/openai-go/v3/option"
)
func main() {
client := openai.NewClient(
option.WithBaseURL("https://synthorai.io/v1"),
option.WithAPIKey("sk-syn-..."),
)
resp, _ := client.Chat.Completions.New(context.TODO(), openai.ChatCompletionNewParams{
Model: "minimax-m3",
Messages: []openai.ChatCompletionMessageParamUnion{
openai.UserMessage("Summarize this diff"),
},
ReasoningEffort: openai.ReasoningEffortMedium,
})
fmt.Println(resp.Choices[0].Message.Content)
}import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.chat.completions.*;
import com.openai.models.ReasoningEffort;
OpenAIClient client = OpenAIOkHttpClient.builder()
.baseUrl("https://synthorai.io/v1")
.apiKey("sk-syn-...")
.build();
ChatCompletion resp = client.chat().completions().create(
ChatCompletionCreateParams.builder()
.model("minimax-m3")
.addUserMessage("Summarize this diff")
.reasoningEffort(ReasoningEffort.MEDIUM)
.build());
System.out.println(resp.choices().get(0).message().content().orElse(""));About MiniMax M3
- Built on the proprietary MiniMax Sparse Attention (MSA) architecture, with roughly 428B total parameters and about 23B activated, it supports a context window of up to 1M tokens with a guaranteed minimum of 512K, targeting long-horizon agent tasks and whole-codebase comprehension; MiniMax reports MSA cutting per-token compute at maximum context to a twentieth of its previous generation, whose family capped out far below 1M.
- Unlike bolt-on approaches, multimodality is trained from step zero for deep alignment between text and visual semantics, and the API accepts images and video alongside text.
- Thinking is controlled by a thinking object with enabled, adaptive and disabled settings rather than by picking a different model, and a separate reasoning_split flag decides whether the chain of thought is returned in reasoning_content and reasoning_details or left inline in the message wrapped in think tags.
- Thinking interleaves with tool calls by design, and MiniMax's tool-use guide requires the returned reasoning fields to be preserved into the next turn.
- Prefix caching starts automatically past 512 input tokens.
- Weights are published under the MiniMax Community License, which asks commercial products to credit the model.
- Synthorai serves MiniMax M3 through its OpenAI-compatible endpoint.
FAQ
Is the MiniMax M3 API free to try?
Yes: new accounts get 10 trial calls and up to $1 in free credit, no card required. At $0.3/M input tokens, that credit alone covers roughly 416 requests of ~8K tokens against MiniMax M3.
What is MiniMax M3 best at?
First open-weight combining coding, agents, multimodality; up to 1M context, 512K guaranteed minimum; multimodality trained from step zero. See the About section for the full picture from the vendor's own release notes.
How much does MiniMax M3 cost?
MiniMax M3 costs $0.3 per million input tokens and $1.2 per million output tokens on Synthorai. That is the provider's list price, with no platform markup. Cached input tokens bill at $0.06/M.
Does MiniMax M3 support prompt caching?
Yes, automatically: MiniMax-served prompts cache with no code changes. Cached input tokens bill at $0.06/M vs $0.3/M uncached; prompts need a 512-token stable prefix to cache. Prompt caching guide →
How do I get access to MiniMax M3?
Point your existing OpenAI SDK at base_url="https://synthorai.io/v1", set model="minimax-m3", and you're done. One API key covers every model on the gateway.
Is MiniMax M3 open source?
Yes: the weights are published under the MiniMax Community License (official repository linked in the About section). Or skip the GPUs: the hosted version here is pay-as-you-go with no infrastructure to run. Running open-weight models →
Related models
Compare
Every value on this page is transcribed from the vendor's own documentation, linked above, and carries the date it was checked. Prices are compared across the catalogue; specification values that vendors define differently are shown with the difference stated rather than charted. Nothing here is measured by us, and nothing is scored.