Frontier models, one private account

35 models from Google, OpenAI, Alibaba, Moonshot AI, Paper Instruments, DeepSeek, Meta, xAI, Z.ai, Perplexity - an optional paid service, billed per use, with the price of every conversation shown as you go. You sign in with your Flowsta Identity: an identity you create and keep yourself, in your own Flowsta Vault with 24 words as the key - the most private way to use frontier models. No provider accounts, and everything local stays local.

Gemini 4 Neon

Google · Nov 2026

Google's newest Gemini 4 model, with a huge context. Reads images as well as text.

$3.90 in · $19.50 out /Mcached $0.201M contextreads imagesGoogle

GPT-6.2 Astra

OpenAI · Nov 2026

OpenAI's newest flagship - the strongest model for hard problems, coding, and research, at a fifth less than GPT-6 Astra.

36 of 36 right on our questions · 3 s an answer · 15 cents for all 36

$10.40 in · $52 out /Mcached $0.521.05M contextreads imagesOpenAI

GPT-6.2 Sol

OpenAI · Nov 2026

OpenAI's flagship for most work - close to GPT-6.2 Astra on coding and hard problems, at a quarter of Astra's price.

36 of 36 right on our questions · 2 s an answer · 4 cents for all 36

$2.60 in · $13 out /Mcached $0.131.05M contextreads imagesOpenAI

Qwen4 Max

Alibaba · Nov 2026

Alibaba's newest flagship - a strong all-rounder with vision and 1M context.

36 of 36 right on our questions · 4 s an answer · 5 cents for all 36

$1.95 in · $5.85 out /Mcached $0.101M contextreads imagesQwen

Kimi K3.1 Pro

Moonshot AI · Oct 2026

Moonshot's newest flagship - always thinks things through, huge context, strong with images.

36 of 36 right on our questions · 7 s an answer · 15 cents for all 36

$2.60 in · $13 out /Mcached $0.261M contextreads imagesMoonshot AI

Kimi K3.1 Pro Highspeed

Moonshot AI · Oct 2026

Kimi K3.1 Pro at two to three times the speed.

36 of 36 right on our questions · 4 s an answer · 28 cents for all 36

$5.20 in · $26 out /Mcached $0.261M contextreads imagesMoonshot AI

Ultramarine 1 Flash

Paper Instruments · Oct 2026

A model tuned for finance, law and consulting work, served from US data centers by Fireworks. Chat only.

36 of 36 right on our questions · 2 s an answer · 1 cents for all 36

$0.29 in · $0.97 out /Mcached $0.061M contextreads imagesopen weights

DeepSeek V4.1 Flash

DeepSeek · Oct 2026

The fast, ultra-cheap lane - quick answers for everyday questions, now with images.

36 of 36 right on our questions · 2 s an answer · 1 cents for all 36

$0.39 in · $1.56 out /Mcached $0.011M contextreads imagesopen weightsDeepSeek

DeepSeek V4.1 Flash (US)

DeepSeek · Oct 2026

DeepSeek's fast, low-cost model, served from US data centers by Fireworks - quick everyday answers, with images.

36 of 36 right on our questions · 1 s an answer · 2 cents for all 36

$0.58 in · $2.34 out /Mcached $0.011M contextreads imagesopen weightsDeepSeek

Gemini 4 Argon

Google · Oct 2026

Google's frontier model - complex coding, agents, math and science, with a huge context.

36 of 36 right on our questions · 18 s an answer · 16 cents for all 36

$2.60 in · $13 out /Mcached $0.131M contextGoogle

GPT-6.1 Terra

OpenAI · Oct 2026

OpenAI's fast, efficient middle model - strong at visual reasoning and clear writing, at half GPT-6.1 Sol's price.

36 of 36 right on our questions · 2 s an answer · 2 cents for all 36

$1.30 in · $6.50 out /Mcached $0.071.05M contextreads imagesOpenAI

Muse Wonder 1.0

Meta · Oct 2026

Meta's frontier agent model - long tasks, tools in parallel, and documents, pictures and video as input.

36 of 36 right on our questions · 4 s an answer · 44 cents for all 36

$5.20 in · $26 out /Mcached $0.261M contextreads imagesMeta

Qwen3.8 Omni Flash

Alibaba · Oct 2026

Alibaba's very low-cost model - quick answers, good with images.

36 of 36 right on our questions · 5 s an answer · under 1 cent for all 36

$0.20 in · $0.61 out /Mcached $0.021M contextreads imagesQwen

GPT-6 Luna

OpenAI · Sep 2026

OpenAI's fast, low-cost tier - great for everyday questions, at half the price of GPT-5.6 Luna.

36 of 36 right on our questions · 2 s an answer · under 1 cent for all 36

$0.13 in · $0.65 out /Mcached $0.011.05M contextreads imagesOpenAI

Grok 4.7

xAI · Sep 2026

xAI's newest frontier model - top-tier coding, agent work, and chat, at the same price as before.

36 of 36 right on our questions · 10 s an answer · 31 cents for all 36

$2.60 in · $7.80 out /Mcached $0.65500K contextreads imagesxAI

Grok 4.7 (Web)

xAI · Sep 2026

xAI's newest frontier model with live web search - current info, cited sources.

36 of 36 right on our questions · 10 s an answer · 31 cents for all 36

$2.60 in · $7.80 out /Mcached $0.65500K contextxAI

Muse Spark Open

Meta · Sep 2026

Meta's open-weights model for coding and agents, served from US data centers by Fireworks.

36 of 36 right on our questions · 4 s an answer · 20 cents for all 36

$1.63 in · $5.53 out /Mcached $0.201M contextreads imagesopen weightsMeta

GPT-6 Astra

OpenAI · Sep 2026

OpenAI's earlier flagship for hard problems, coding, and research. GPT-6.2 Astra follows it at a fifth less.

36 of 36 right on our questions · 3 s an answer · 25 cents for all 36

$13 in · $65 out /Mcached $1.301.05M contextreads imagesOpenAI

Muse Spark 1.3

Meta · Sep 2026

Meta's frontier model - long tasks, coding, and agents at a fraction of flagship prices.

36 of 36 right on our questions · 9 s an answer · 18 cents for all 36

$1.63 in · $5.53 out /Mcached $0.201M contextreads imagesMeta

Gemini 3.8 Flash

Google · Sep 2026

Google's fast, low-cost model - quick everyday answers, strong with images and long documents.

36 of 36 right on our questions · 4 s an answer · 5 cents for all 36

$0.97 in · $4.88 out /Mcached $0.101M contextreads imagesGoogle

GLM-5.3 Flash (US)

Z.ai · Aug 2026

Z.ai's fast, low-cost model with images, served from US data centers by Fireworks.

36 of 36 right on our questions · 1 s an answer · 1 cents for all 36

$0.29 in · $0.97 out /Mcached $0.061M contextreads imagesopen weightsZhipu AI

GLM-5.3

Z.ai · Aug 2026

Z.ai's newest flagship - a step up in coding and agent work, 1M context.

36 of 36 right on our questions · 4 s an answer · 7 cents for all 36

$1.82 in · $5.72 out /Mcached $0.341M contextopen weightsZhipu AI

GLM-5.3 (US)

Z.ai · Aug 2026

Z.ai's flagship, served from US data centers by Fireworks - strong at coding and long agent work, 1M context.

36 of 36 right on our questions · 2 s an answer · 10 cents for all 36

$2.73 in · $8.58 out /Mcached $0.511M contextopen weightsZhipu AI

GLM-5.3 Flash

Z.ai · Aug 2026

Z.ai's fast, low-cost model with images, 1M context.

35 of 36 right on our questions · 6 s an answer · under 1 cent for all 36

$0.20 in · $0.65 out /Mcached $0.041M contextreads imagesopen weightsZhipu AI

GLM-5.3 FlashX

Z.ai · Aug 2026

Z.ai's FlashX tier of GLM-5.3 - low cost, with images and 1M context.

36 of 36 right on our questions · 3 s an answer · 2 cents for all 36

$0.48 in · $1.63 out /Mcached $0.101M contextreads imagesZhipu AI

DeepSeek V4

DeepSeek · Aug 2026

Frontier-level reasoning and coding at a low price.

36 of 36 right on our questions · 4 s an answer · 6 cents for all 36

$1.72 in · $5.15 out /Mcached $0.061M contextopen weightsDeepSeek

Kimi K3

Moonshot AI · Jul 2026

Moonshot's flagship - deep reasoning and top-tier coding, huge context, strong with images.

36 of 36 right on our questions · 7 s an answer · 24 cents for all 36

$3.90 in · $19.50 out /Mcached $0.391M contextreads imagesopen weightsMoonshot AI

Kimi K3 (US)

Moonshot AI · Jul 2026

Moonshot's flagship, served from US data centers by Fireworks - deep reasoning, top-tier coding, huge context.

36 of 36 right on our questions · 3 s an answer · 27 cents for all 36

$5.85 in · $29.25 out /Mcached $0.581M contextreads imagesopen weightsMoonshot AI

GPT-5.6 (Web)

OpenAI · Jul 2026

GPT-5.6 with live web search - up-to-date, cited answers.

35 of 36 right on our questions · 2 s an answer · 6 cents for all 36

$2.60 in · $15.60 out /Mcached $0.261.05M contextOpenAI

Kimi K2.7 Code

Moonshot AI · Jun 2026

Moonshot's dedicated coding model - long-context programming, low cost.

36 of 36 right on our questions · 4 s an answer · 4 cents for all 36

$1.24 in · $5.20 out /Mcached $0.25256K contextreads imagesopen weightsMoonshot AI

Grok Build 0.1

xAI · May 2026

xAI's fast, low-cost coding agent model.

36 of 36 right on our questions · 5 s an answer · 10 cents for all 36

$1.30 in · $2.60 out /Mcached $0.26256K contextxAI

Qwen3.7 Plus

Alibaba · May 2026

Alibaba's balanced Qwen - strong everyday quality at a low price, with images.

36 of 36 right on our questions · 11 s an answer · 5 cents for all 36

$0.52 in · $2.08 out /Mcached $0.101M contextreads imagesQwen

Qwen3.6 Flash

Alibaba · Apr 2026

Alibaba's fastest, cheapest Qwen - quick answers, with images.

36 of 36 right on our questions · 13 s an answer · 11 cents for all 36

$0.33 in · $1.95 out /Mcached $0.071M contextreads imagesQwen

Perplexity Sonar Pro

Perplexity · Mar 2025

Deeper web research for harder questions.

35 of 36 right on our questions · 2 s an answer · 34 cents for all 36

$3.90 in · $19.50 out /M200K contextPerplexity

Perplexity Sonar

Perplexity · Jan 2025

Web-grounded answers with citations.

36 of 36 right on our questions · 2 s an answer · 24 cents for all 36

$1.30 in · $1.30 out /M128K contextPerplexity

"Our questions" are the same set for every model, each with one answer that can be checked. The time and the cost are for answering all of them at our price, with the model's thinking counted: that is what separates models whose answers are equally right.

Prices are per million tokens, straight from the live catalog the app bills against. Nothing goes online without your consent: an AI set to Online and Offline uses these models, one set to Offline Only never does, and attachments ask first.

Prefer models that never leave your machine? Browse the offline catalog - 50 downloads, fully private.