🎉 LTX 2.5 IS LIVE! 🎉 | The wait is over. We’ve just pushed LTX 2.5 to production, and it’s our best update yet.

⚡️ GPT-OSS-120b is now live | Blazing fast - better than TogetherAI

👉 Get $5 welcome credit | One API for every frontier model | Ends soon.

Inkling API

Run thinkingmachines/inkling through FastInfra's API. Pay per token, no subscription, routed to the cheapest available provider.

Pricing

Inkling pricing

Billed per token used. Prices sync automatically from wholesale providers.

Direction Price per 1M tokens
Input$1.00
Output$4.25
Availability

Served by 4 providers

Requests route to DeepInfra by default (cheapest). Pin a specific provider with the :provider suffix.

Provider Upstream model ID
deepinfra thinkingmachines/Inkling
openrouter thinkingmachines/inkling
together thinkingmachines/Inkling
fireworks accounts/fireworks/models/inkling
Quickstart

Call Inkling in 30 seconds

Works with any OpenAI SDK — change the base URL and API key only.

Python

from openai import OpenAI

client = OpenAI(api_key="YOUR_API_KEY", base_url="https://api.fastinfra.ai/v1")

response = client.chat.completions.create(
    model="thinkingmachines/inkling",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

curl

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

Inkling — common questions

How much does the thinkingmachines/inkling API cost?

On FastInfra, thinkingmachines/inkling costs $0.9975/1M input, $4.2525/1M output tokens. Billing is per token used, with no subscription.

Is thinkingmachines/inkling compatible with the OpenAI SDK?

Yes. FastInfra exposes thinkingmachines/inkling through an OpenAI-compatible endpoint at https://api.fastinfra.ai/v1 — point any OpenAI SDK at that base URL with a FastInfra API key and keep your existing code.

Which providers serve thinkingmachines/inkling?

thinkingmachines/inkling is available from 4 provider(s): deepinfra, openrouter, together, fireworks. Requests route to DeepInfra by default (cheapest); append ":provider" to the model ID to pin one.