AkiliNode
AkiliNode Docs

API Reference

AkiliNode speaks the OpenAI API format. Any OpenAI SDK or compatible tool works out of the box.

Base URL & authentication

ItemValue
Base URLhttps://api.akilinode.com/v1
HeaderAuthorization: Bearer sk-your-akilinode-token
Content typeapplication/json

Create and manage tokens in the console under Tokens. A token can have its own spending cap, so one app can never drain your whole balance.

Models

ModelInput / 1MOutput / 1MBest for
deepseek-flashUSD 0.33USD 1.32Everyday chat, code, apps — fast and cheap
deepseek-v4-proUSD 1.45USD 4.36Hard reasoning, analysis, complex code
glm-5.3USD 1.40USD 4.40GLM flagship — reasoning, coding, agents
qwen3.7-maxUSD 2.30USD 6.90Qwen flagship for hard tasks
glm-4.7USD 0.65USD 3.05Coding agents and tool use
qwen3.7-plusUSD 0.44USD 1.75Balanced everyday model, great French
glm-5.3-flashUSD 0.16USD 0.55Fast and cheap for apps
qwen3.7-flashUSD 0.022USD 0.088Ultra-low-cost, high volume
glm-4.7-flashFREEFREEFree tier for testing and learning

Cached inputs are billed at up to 98% less. List the live models any time with GET /v1/models.

Chat completions

POST /v1/chat/completions

ParameterDescription
modelRequired. Any model ID from the Models table above.
messagesRequired. Array of {role, content} — roles: system, user, assistant.
streamOptional, default false. Set true to receive the answer token by token (server-sent events).
temperatureOptional, 0–2. Lower = more focused, higher = more creative.
max_tokensOptional. Cap on the length of the reply.

Example request

curl https://api.akilinode.com/v1/chat/completions \
  -H "Authorization: Bearer sk-your-akilinode-token" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-flash",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Write a one-line slogan for a bakery in Nairobi."}
    ]
  }'

Example response

{
  "id": "chatcmpl-...",
  "object": "chat.completion",
  "model": "deepseek-flash",
  "choices": [
    {"index": 0,
     "message": {"role": "assistant", "content": "Fresh from the oven, straight to your heart — Nairobi's home of warm bread."},
     "finish_reason": "stop"}
  ],
  "usage": {"prompt_tokens": 28, "completion_tokens": 19, "total_tokens": 47}
}
Billing is per token. You pay for prompt_tokens at the input price and completion_tokens at the output price. Every call and its exact cost appear in your console under Logs.

Streaming

Set "stream": true and the API returns server-sent events, one chunk at a time, ending with data: [DONE]. All OpenAI SDKs handle this with their standard streaming mode — no AkiliNode-specific code needed.

Errors

Errors come back in the OpenAI format: an error object with a message. The ones you will actually meet:

StatusMeaning & fix
401Token missing or invalid. Check the Authorization header and that the token is enabled.
403Balance or token cap exhausted. Top up, or raise the token's limit in the console.
404Model name not recognised. Use an exact model ID from the Models table above.
429Too many requests in a short window. Slow down and retry with a short backoff.
500Upstream or temporary error. Retry after a few seconds; if it persists, check Help & Support.
© 2026 AkiliNode · Frontier AI APIs, priced for Africa