2 min

to switch from your current provider

~10x

cheaper than AWS/Azure

Verified outputs

without blind trust

Latency-focused

for interactive workloads

2 min

to switch from your current provider

Verified outputs

without blind trust

~10x

cheaper than AWS/Azure

Latency-focused

for interactive workloads

Built for products that cannot wait on slow infra

Agents and tool use

Support multi-step workflows with retries, orchestration, and real task execution inside production systems.

RAG and assistants

Run retrieval-heavy experiences without building and maintaining a full GPU operations layer in-house.

Run retrieval-heavy experiences without building and maintaining a full GPU operations layer in-house.

Game AI and live systems

Power NPCs, companions, and gameplay support features where delays quickly break immersion.

Power NPCs, companions, and gameplay support features where delays quickly break immersion.

Already on another provider?

Two lines. Done.

from openai import OpenAI
 
# Change base_url and api_key. Everything else stays.
client = OpenAI(
base_url="https://api.farlabs.ai/v1",
api_key="far-xxxxxxxxxxxx"
)
 
response = client.chat.completions.create(
model="qwen3-8b",
messages=[{"role": "user", "content": "Hello"}]
)

Open-weight models served at scale

Production-ready LLMs on the network today. More added based on demand from early users.

Qwen3-32B
Input:$0,13
Output:$0,14
Text
DeepSeek-R1-Distill-Llama-70B
Input:$0,23
Output:$0,24
Text
Llama-3.3-Swallow-70B-Instruct-v0.4
Input:$0,21
Output:$0,22
Text, Image
Meta-Llama-3.1-8B-Instruct
Input:$0,15
Output:$0,16
Text
Mistral-7B
Input:$0,17
Output:$0,18
Text, Video
Gemini Pro 1.5
Input:$0,19
Output:$0,20
Text, Audio, Image, Video
Goliath-120M
Input:$0,13
Output:$0,14
Text, Audio, Image, Video

how it works

Join the wait list and get early access to reliable, lower-cost inference

01
Join the whitelist
Share your use case, current setup, and monthly token volume
02
Get access
We review your use case and send the right access path
03
Start building
Start building with AI by testing models in the playground, or connect to the API and scale when you're ready.

Building with AI? Claim 1M free tokens and start building on FAR AI

Tell us what you're building, what provider you use today, and what would need to be true for a real switch to make sense.

By submitting, you agree to our Terms of Service & Privacy Policy

Frequently asked questions

In the news