How much does Inkling cost?

Inkling is billed pay-as-you-go at $2.06 per 1M input tokens and $5.15 per 1M output tokens. There is no subscription — you only pay for what you use.

Inkling supports Vision, Tool calling.

Is Inkling free to use?

Inkling is a paid, pay-as-you-go model — no subscription, you are only charged for usage.

How do I use Inkling via the API?

Inkling is OpenAI-compatible. Point any OpenAI SDK at https://api.airforce/v1 and pass the model ID inkling with your Api.Airforce API key.

Inkling is Thinking Machines's chat model, served through the unified Api.Airforce gateway alongside 100+ other models.

Thinking MachinesPaidOperational

Inkling

API model name: inkling

Inkling is Thinking Machines's chat model, served on the Api.Airforce unified API. Capabilities include Vision, Tool calling. It is priced at $2.06 per million input tokens and $5.15 per million output tokens. That is below the provider's $1.87 official input rate. Access it through the OpenAI-compatible API with one key, alongside 100+ other models on Api.Airforce.

Get an API key View pricing

Pricing

Input / 1M tokens

$2.06

Output / 1M tokens

$5.15

Cache read / 1M tokens

$0.19

Cache write / 1M tokens

$2.58

Official input rate

$1.87

Official output rate

$4.68

Api.Airforce price vs. the provider's official rate.

Specifications

Provider: Thinking Machines
Type: chat model

Capabilities

VisionTool calling

Benchmarks

Independent evaluations and measured speed from Artificial Analysis.

Intelligence Index

25.0/100

Coding Index

52.1/100

GPQA Diamond87%

Humanity's Last Exam32%

SciCode47%

τ-bench Banking29%

Terminal-Bench 2.155%

LCR77%

Output speed170.9 tok/s

Time to first token1.95 s

Inkling (Xhigh)

Source: Benchmark data by Artificial Analysis (artificialanalysis.ai)

What is Inkling used for?

Chatbots & assistants — conversational AI, drafting, summarizing and Q&A.
Image understanding — analyze photos, screenshots, charts and scanned documents.
Agents & automation — function calling and tool use for multi-step workflows.

Inkling vs. similar models

Model	Intelligence	Context	Input / 1M	Output / 1M
Inkling	25.0	—	$2.06	$5.15
Llama 3.1 8B Instruct	6.9	—	$0.06	$0.09
Llama 3.2 1B Instruct	4.8	—	$0.04	$0.22
Llama 3.2 3B Instruct	5.7	—	$0.06	$0.37

Prices are Api.Airforce pay-as-you-go rates per 1M tokens. Context is the maximum input length.

Inkling — frequently asked questions

How much does Inkling cost?: Inkling is billed pay-as-you-go at $2.06 per 1M input tokens and $5.15 per 1M output tokens. There is no subscription — you only pay for what you use.
What can Inkling do?: Inkling supports Vision, Tool calling.
Is Inkling free to use?: Inkling is a paid, pay-as-you-go model — no subscription, you are only charged for usage.
How do I use Inkling via the API?: Inkling is OpenAI-compatible. Point any OpenAI SDK at https://api.airforce/v1 and pass the model ID inkling with your Api.Airforce API key.
Who makes Inkling?: Inkling is Thinking Machines's chat model, served through the unified Api.Airforce gateway alongside 100+ other models.

All models·Quickstart·Chat API reference

Use Inkling via the API

OpenAI-compatible — point any OpenAI SDK at https://api.airforce/v1 and pass inkling as the model.

cURL

curl https://api.airforce/v1/chat/completions \
  -H "Authorization: Bearer $AIRFORCE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "inkling",
    "messages": [{ "role": "user", "content": "Hello!" }]
  }'

Python

from openai import OpenAI
client = OpenAI(base_url="https://api.airforce/v1", api_key="$AIRFORCE_API_KEY")
r = client.chat.completions.create(
    model="inkling",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(r.choices[0].message.content)

JavaScript

import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.airforce/v1", apiKey: process.env.AIRFORCE_API_KEY });
const r = await client.chat.completions.create({
  model: "inkling",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(r.choices[0].message.content);