Bridge by Wekoya / Models / MiniMax / MiniMax-M3 API, priced in naira

MiniMax-M3 API, priced in naira

In short: You can use MiniMax-M3, a model by MiniMax, from Nigeria through Bridge and pay in naira, with no dollar card. It costs ₦491 per million input tokens and ₦1,931 per million output tokens. Call it with the OpenAI SDK using the model ID minimax-m3.

Updated

Price and limits

MiniMax-M3
Input, per million tokens₦491
Output, per million tokens₦1,931
Cached input, per million tokens₦98.28
Writing to the cache, per million tokens₦491
Context window524,288 tokens
Longest reply16,384 tokens
Reads picturesYes
Tool callingYes
Reasoning (thinks before it answers)Yes
Model IDminimax-m3

Prices as of 8 November 2026. They are in naira and follow the exchange rate, so the live price may differ a little. A token is roughly three quarters of a word.

What a request costs

A request that sends 1,500 tokens (instructions, the conversation so far and a question) and gets 500 back (about 375 words) costs about ₦1.70 on 8 November 2026. A thousand of them cost about ₦1,702. When 1,000 of the input tokens are instructions that stay the same, prompt caching reads them at the cached rate and the request costs about ₦1.31.

Use MiniMax-M3 from your code

Bridge speaks the OpenAI format, so the OpenAI SDK works as it is: set the base URL to https://wekoya-api.wekoya.tech/v1, use your Bridge key, and pass minimax-m3 as the model. Create a key, then:

from openai import OpenAI

client = OpenAI(api_key="wk_live_...", base_url="https://wekoya-api.wekoya.tech/v1")
reply = client.chat.completions.create(
    model="minimax-m3",
    messages=[{"role": "user", "content": "Hello"}],
)
print(reply.choices[0].message.content)

Streaming works the same way, and so does tool calling. To send a picture, add it to the message as an image. The quickstart has the same in JavaScript and curl, and the Responses API works too.

Other MiniMax models on Bridge

ModelInput / 1MOutput / 1MContext
MiniMax-M2.7₦439₦1,755196,608
MiniMax-M2₦527₦2,106204,608
MiniMax-M2.1₦527₦2,106196,608
MiniMax-M2.5₦527₦2,106196,608

Every MiniMax model on Bridge, with what each can do.

Lower-priced models that can do the same things

These cost less per request than MiniMax-M3 and can also read pictures, call tools, reason and take at least 524,288 tokens of context. Quality differs from model to model, so test on your own examples first: AI tasks compares models on your cases and tells you whether a cheaper one is good enough.

ModelInput / 1MOutput / 1MContext
Gemini 3.1 Flash Lite₦371₦2,2281,048,576
GPT-5.6 Luna₦297₦1,7821,050,000
GLM-5.3-Flash₦263₦8781,048,576
Qwen3.8 Flash₦198₦6701,000,000

Create a free account

Common questions

How much does MiniMax-M3 cost in naira?

On Bridge, MiniMax-M3 costs ₦491 per million input tokens and ₦1,931 per million output tokens, with cached input at ₦98.28 (as of 8 November 2026). A request that sends 1,500 tokens and gets 500 back costs about ₦1.70. There is no subscription and no minimum.

Can I use the MiniMax-M3 API from Nigeria without a dollar card?

Yes. Create a free Bridge account, top up your naira balance by bank transfer to your own account number, and call MiniMax-M3 with your Bridge key. A card works too, but it is not needed.

Does MiniMax-M3 on Bridge work with the OpenAI SDK?

Yes. Use the OpenAI SDK or any OpenAI-compatible client with the base URL https://wekoya-api.wekoya.tech/v1 and the model ID minimax-m3. Streaming works, and so does tool calling.

What is the context window of MiniMax-M3?

524,288 tokens, about 393,216 words of instructions, conversation and documents together. It writes up to 16,384 tokens in one reply.

Can MiniMax-M3 read pictures?

Yes. Send a picture in the message as an image_url, by link or as base64, and MiniMax-M3 reads it. Pictures are counted as input tokens.

Read next