Bridge by Wekoya / Models / Meta / Llama 3.3 70B Turbo API, priced in naira

Llama 3.3 70B Turbo API, priced in naira

In short: You can use Llama 3.3 70B Turbo, a model by Meta, from Nigeria through Bridge and pay in naira, with no dollar card. It costs ₦176 per million input tokens and ₦562 per million output tokens. Call it with the OpenAI SDK using the model ID llama-3.3-70b-instruct.

Updated

Price and limits

Llama 3.3 70B Turbo
Input, per million tokens₦176
Output, per million tokens₦562
Cached input, per million tokens₦176
Writing to the cache, per million tokens₦176
Context window131,072 tokens
Longest reply16,384 tokens
Reads picturesNo
Tool callingYes
Reasoning (thinks before it answers)No
Model IDllama-3.3-70b-instruct

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 ₦0.544 on 8 November 2026. A thousand of them cost about ₦544.

Use Llama 3.3 70B Turbo 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 llama-3.3-70b-instruct 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="llama-3.3-70b-instruct",
    messages=[{"role": "user", "content": "Hello"}],
)
print(reply.choices[0].message.content)

Streaming works the same way, and so does tool calling. The quickstart has the same in JavaScript and curl, and the Responses API works too.

Other Meta models on Bridge

ModelInput / 1MOutput / 1MContext
Llama 4 Scout 17B₦176₦527327,680
Llama 4 Scout 17B Instruct₦298₦1,15810,000,000
Llama 4 Maverick 17B Instruct₦421₦1,7021,000,000
Llama 3.3 70B Instruct₦1,264₦1,264128,000

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

Lower-priced models that can do the same things

These cost less per request than Llama 3.3 70B Turbo and can also call tools and take at least 131,072 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
Llama 4 Scout 17B₦176₦527327,680
Gemini 2.5 Flash-Lite₦149₦5941,048,576
DeepSeek V4.1 Flash 1017₦172₦5161,048,576
GLM-4.7-Flash₦105₦702202,752

Create a free account

Common questions

How much does Llama 3.3 70B Turbo cost in naira?

On Bridge, Llama 3.3 70B Turbo costs ₦176 per million input tokens and ₦562 per million output tokens, with cached input at ₦176 (as of 8 November 2026). A request that sends 1,500 tokens and gets 500 back costs about ₦0.544. There is no subscription and no minimum.

Can I use the Llama 3.3 70B Turbo 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 Llama 3.3 70B Turbo with your Bridge key. A card works too, but it is not needed.

Does Llama 3.3 70B Turbo 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 llama-3.3-70b-instruct. Streaming works, and so does tool calling.

What is the context window of Llama 3.3 70B Turbo?

131,072 tokens, about 98,304 words of instructions, conversation and documents together. It writes up to 16,384 tokens in one reply.

Can Llama 3.3 70B Turbo read pictures?

No. Llama 3.3 70B Turbo reads text only. For pictures, pick a model marked "Reads pictures" on the models page.

Read next