Get an API key: Modular

new

Modular gives Big-AGI two connections in one vendor: Modular Cloud, the pay-per-token API from the MAX and Mojo company (now part of Qualcomm), or a free MAX server you run on your own machine. You can add one of each, side by side.

Modular Cloud account

A Modular Cloud account is created with a work email and bills from prepaid credit: money loaded at the console that each request draws down. Current rates per model live on Modular's pricing page.

Creating a key

1. Open console.modular.com/api_tokens - the empty key field links there as API tokens.
2. Create a Personal key with Model access enabled; a key scoped without it authenticates and still reaches no models.
3. Copy the value at creation - it is shown once, and a key is never regenerated later, only deleted and recreated.

Every key carries a hard expiration date, so a connection that dies months from now may have outlived its key.

Add it to Big-AGI

Open Models (Ctrl + Shift + M) and press More Services if the Setup AI Models wizard appears. Then Add -> Modular, paste into Modular API Key, and press Models - the list filling in below is your confirmation (add and manage your keys).

An Endpoint selector switches between Modular Cloud (just the sk-mod- key) and MAX self-hosted (a MAX Server URL such as http://localhost:8000, key optional). The MAX server is a free download that runs on NVIDIA, AMD and Apple Silicon and serves the same API.

When the key works, the model list fills in. It tracks Modular's catalog live, so new models appear on refresh.

What we measured, August 2026

Everything in this section is a snapshot of 2026-08-13, taken from a US connection as single-day spot checks - best of two streaming runs of about 200 tokens each, not benchmarks. Prices move; the pricing page is the source of record.

Model	Context	$/1M in	$/1M out	Input
MiniMax M3	1M	$0.30 (cache hits $0.06)	$1.20	text + images
Gemma 4 31B	256K	$0.25	$0.65	text + images
Gemma 4 26B A4B	256K	$0.15	$0.60	text + images
Kimi K2.7 Code	256K	$0.60* (cache $0.12*)	$3.00*	text + images

*Modular publishes no rate for Kimi K2.7 Code; shown is its published Kimi K2.5 rate, the closest figure. The app itself shows no price for this model as of 2026-08-17. Modular has since added a fifth shared model, GLM 5.2 (160K context as served).

Model	On Modular	Same model elsewhere, same day
MiniMax M3	~238 tok/s, first token in 257 ms	64 tok/s (MiniMax API), 138 tok/s (OpenRouter)
Gemma 4 31B	~199 tok/s, first token in 231 ms	37-132 tok/s across three other hosts
Kimi K2.7 Code	~170 tok/s	57 tok/s (Moonshot API)

Models are served as NVIDIA NVFP4 4-bit quantized builds, disclosed in the response's model field; our small checks found no quality difference. Two of the four models think before answering; Big-AGI renders the reasoning stream. Accounts start at 60 requests and 600K tokens per minute, rising to 180 and 1.8M once a payment method is on file.

Direct Connection

Not available yet: Modular's API does not answer browser-direct (CORS) requests, so every request travels through the Big-AGI fast edge servers. The Direct Connection toggle does not render in Modular's setup panel.

Using a server-side key

Self-hosters can set MODULAR_API_KEY in the server environment: no green check appears and the field stays empty, but the server supplies the key on every request. Add the service by hand, leave Modular API Key empty and press Models - the list fills from the server's key (keys held by a server you operate).

Troubleshooting Modular

What you see	What it means	What to do
A 401 after the key worked before	The prepaid balance hit zero, or the key passed its expiration date.	Top up or recreate the key at the console: key and access errors
The key is accepted and no models arrive	The key was created without Model access, so it authenticates and reaches nothing.	Recreate the key with the scope enabled: key and access errors
Requests stall or fail in bursts	The rate tier is shared by every key in the account, so parallel use trips it together.	Add a payment method for the higher tier, or pace requests: key and access errors

Related

• Connect an AI service
• Direct Connection
• What your provider does with your text
• Keys held by a server you operate