Bridge by Wekoya / Models / Mistral / Mistral Large 3 API, priced in naira

Mistral Large 3 API, priced in naira

In short: You can use Mistral Large 3, a model by Mistral, from Nigeria through Bridge and pay in naira, with no dollar card. It costs ₦878 per million input tokens and ₦2,633 per million output tokens. Call it with the OpenAI SDK using the model ID mistral-large-3-675b.

Updated

Price and limits

Mistral Large 3
Input, per million tokens₦878
Output, per million tokens₦2,633
Cached input, per million tokens₦878
Writing to the cache, per million tokens₦878
Context window262,144 tokens
Longest reply8,192 tokens
Reads picturesYes
Tool callingYes
Reasoning (thinks before it answers)No
Model IDmistral-large-3-675b

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 ₦2.63 on 8 November 2026. A thousand of them cost about ₦2,633.

Use Mistral Large 3 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 mistral-large-3-675b 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="mistral-large-3-675b",
    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 Mistral models on Bridge

ModelInput / 1MOutput / 1MContext
Ministral 3 3B₦176₦176256,000
Ministral 3 8B₦263₦263128,000
Ministral 14B 3.0₦351₦351128,000
Magistral Small 1.2₦878₦2,633128,000
Devstral 2 123B₦702₦3,510262,144
Pixtral Large (25.02)₦3,510₦10,530128,000

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

Lower-priced models that can do the same things

These cost less per request than Mistral Large 3 and can also read pictures, call tools and take at least 262,144 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 3.5 Flash Lite₦446₦3,7131,048,576
Inkling Small₦790₦2,106524,288
Qwen3.8 27B₦263₦3,291262,144
MiMo-V2.6-Pro₦679₦1,3741,048,576

Create a free account

Common questions

How much does Mistral Large 3 cost in naira?

On Bridge, Mistral Large 3 costs ₦878 per million input tokens and ₦2,633 per million output tokens, with cached input at ₦878 (as of 8 November 2026). A request that sends 1,500 tokens and gets 500 back costs about ₦2.63. There is no subscription and no minimum.

Can I use the Mistral Large 3 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 Mistral Large 3 with your Bridge key. A card works too, but it is not needed.

Does Mistral Large 3 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 mistral-large-3-675b. Streaming works, and so does tool calling.

What is the context window of Mistral Large 3?

262,144 tokens, about 196,608 words of instructions, conversation and documents together. It writes up to 8,192 tokens in one reply.

Can Mistral Large 3 read pictures?

Yes. Send a picture in the message as an image_url, by link or as base64, and Mistral Large 3 reads it. Pictures are counted as input tokens.

Read next