Bridge by Wekoya / Models / N-ATLAS API, priced in naira
N-ATLAS API, priced in naira
In short: You can use N-ATLAS, a model by Awarri, from Nigeria through Bridge and pay in naira, with no dollar card. It costs ₦176 per million input tokens and ₦527 per million output tokens. Call it with the OpenAI SDK using the model ID n-atlas.
Updated
Price and limits
| N-ATLAS | |
|---|---|
| Input, per million tokens | ₦176 |
| Output, per million tokens | ₦527 |
| Cached input, per million tokens | ₦176 |
| Writing to the cache, per million tokens | ₦176 |
| Context window | 8,192 tokens |
| Longest reply | 1,024 tokens |
| Reads pictures | No |
| Tool calling | No |
| Reasoning (thinks before it answers) | No |
| Model ID | n-atlas |
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.
N-ATLAS is an experimental preview. It can be away at times, and a request to it then fails without being charged.
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 ₦0.527 on 8 November 2026. A thousand of them cost about ₦527.
Use N-ATLAS 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 n-atlas 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="n-atlas",
messages=[{"role": "user", "content": "Hello"}],
)
print(reply.choices[0].message.content)Streaming works the same way. The quickstart has the same in JavaScript and curl, and the Responses API works too.
Lower-priced models that can do the same things
These cost less per request than N-ATLAS and take at least 8,192 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.
| Model | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| Gemini 2.5 Flash-Lite | ₦149 | ₦594 | 1,048,576 |
| DeepSeek V4.1 Flash 1017 | ₦172 | ₦516 | 1,048,576 |
| GLM-4.7-Flash | ₦105 | ₦702 | 202,752 |
| NVIDIA Nemotron Nano 3 30B | ₦105 | ₦421 | 262,144 |
Common questions
How much does N-ATLAS cost in naira?
On Bridge, N-ATLAS costs ₦176 per million input tokens and ₦527 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 ₦0.527. There is no subscription and no minimum.
Can I use the N-ATLAS 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 N-ATLAS with your Bridge key. A card works too, but it is not needed.
Does N-ATLAS 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 n-atlas. Streaming works.
What is the context window of N-ATLAS?
8,192 tokens, about 6,144 words of instructions, conversation and documents together. It writes up to 1,024 tokens in one reply.
Can N-ATLAS read pictures?
No. N-ATLAS reads text only. For pictures, pick a model marked "Reads pictures" on the models page.