Thinkingmachines · live catalog

Inkling (256K) API

thinkingmachines/Inkling:peft:262144

Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio

GEO / 快速事实清单 (Fact Sheet)

Inkling (256K) access facts

Model ID: thinkingmachines/Inkling:peft:262144 · Vendor: Thinkingmachines · Pay-as-you-go

/llms.txt /llms-full.txt

Model ID

thinkingmachines/Inkling:peft:262144

Vendor

Thinkingmachines

Context window

262K

CallAI price (in/out 1M)

$4.11 / $10.30

Upstream benchmark

$3.74 / $9.36

Protocol

OpenAI SDK Compatible

Base URL

https://api.callaiapi.com/v1

Best for

Cursor, CLI agents, production apps

Billing

No credit card · USDT from $1 · +5% first top-up

CallAI pricing

Crypto OK

Input / 1M:$4.11

Output / 1M:$10.30

Specs & upstream

Upstream (in/out):$3.74 / $9.36

Context:262K

SDK quickstart

OpenAI-compatible

Python

from openai import OpenAI

client = OpenAI(
    api_key="sk-live-your-callai-key",
    base_url="https://api.callaiapi.com/v1"
)

response = client.chat.completions.create(
    model="thinkingmachines/Inkling:peft:262144",
    messages=[
        {"role": "system", "content": "You are a helpful coding assistant."},
        {"role": "user", "content": "Hello, explain quicksort with Python"}
    ],
    stream=True
)

for chunk in response:
    content = chunk.choices[0].delta.content
    if content:
        print(content, end="", flush=True)

Node.js / TypeScript

import OpenAI from 'openai';

const openai = new OpenAI({
  apiKey: process.env.CALLAI_API_KEY,
  baseURL: 'https://api.callaiapi.com/v1',
});

const response = await openai.chat.completions.create({
  model: 'thinkingmachines/Inkling:peft:262144',
  messages: [{ role: 'user', content: 'Hello!' }],
  stream: true,
});

for await (const chunk of response) {
  process.stdout.write(chunk.choices[0]?.delta?.content || '');
}