Aperture

Chat with open models · billed per token · pay only for what you use

Open models, one meter

live catalog · prices per 1M tokens · the meter shows every token

gpt-oss 20BOpenAI OSS

OpenAI's open-weight 20B — quick and capable.

$0.05/M in$0.20/M out128k ctx

Qwen3 Coder 480BQwen

Agentic coding across a 256K-token window.

$0.60/M in$2.40/M out256k ctx

DeepSeek V3DeepSeek

Frontier-class general model with step-by-step reasoning.

$0.28/M in$1.10/M out128k ctx

Gemma 4 31BGemma

Google's open Gemma 4 instruct, 31B.

$0.05/M in$0.15/M out256k ctx

GLM 4.6GLM

200K context, tool use, and switchable deep reasoning.

$0.60/M in$2.20/M out200k ctx

Nemotron 3 Super 120BNemotron

NVIDIA's large open reasoning model.

$0.30/M in$0.60/M out256k ctx

Kimi K2Moonshot

A trillion-parameter agent that finishes multi-step tasks.

$0.60/M in$2.50/M out128k ctx

Nemotron 3 Ultra 550BNemotron

NVIDIA's flagship — 1M context, slower.

$0.50/M in$1.50/M out1M ctx

Llama 4 MaverickMeta

Sees images and reads up to a million tokens at once.

$0.27/M in$0.85/M out1M ctx

North Mini CodeCohere

Cohere's coding-focused open model.

$0.10/M in$0.30/M out256k ctx

Mistral Small 3Mistral

Small, quick, and cheap — the fast default.

$0.14/M in$0.28/M out128k ctx

Nemotron Nano 9BNemotron

Small and fast Nemotron Nano.

$0.02/M in$0.08/M out128k ctx

Qwen3 235BQwen

Frontier open reasoning across a 256K-token window.

$0.70/M in$2.80/M out256k ctx

Start with $0.20 of free credit

Aperture · pay per token · openai-compatible API