Plans & Pricing
One workspace. Your choice of models.
Every plan includes one shared SwitchNext token balance. Lower-cost models stretch it further, while higher-cost models use it faster, so you can spend your full allowance on any model included in your plan.
No credit card required to start
Secure checkout by Stripe
Cancel anytime
Compare plans
Starter
Increased AI capacity for Chat + Code.
$10
USD / month
Monthly SwitchNext Tokens
8M across included models
More saved Chats and Code workspaces
@workspace context for whole-project requests
More files per workspace and unlimited file selection
Premium
Higher-capacity models for deeper, more demanding work.
$25
USD / month
Monthly SwitchNext Tokens
20M across included models
Everything in Starter
Higher-capacity Claude, Gemini, and GPT models
Increase workspace capacity
Pro
Frontier models with larger token usage across included models.
$50
USD / month
Monthly SwitchNext Tokens
40M across included models
Everything in Premium
Frontier-model access
Larger workspace capacity
Pro+
Maximum token capacity for sustained frontier-model workloads.
$100
USD / month
Monthly SwitchNext Tokens
80M across included models
Everything in Pro
2x Pro token capacity
Maximum workspace capacity
Secure checkout powered by Stripe. Shared SwitchNext token allowances do not roll over.
Starter, Premium, Pro, and Pro+ expand model access, the shared SwitchNext token balance, and workspace capacity.
Input and output tokens count toward usage. Model availability and SwitchNext burn rates vary by plan and model.
Not ready to upgrade?
Start free and upgrade when your workflows need more capacity.
Free — $0
50K one-time courtesy SwitchNext tokens
Agent Mode + Compare Mode + Saved conversations and workspaces
No credit card required
Workspace capacity
Workspace Limits by Plan
Compare the workspace capabilities, saved work, project capacity, and context available at every tier.
AI & Workspace Capabilities
Free Save your work | Selected Starter More room to build |
Premium Larger workflows |
Pro Maximum capacity |
Pro+ 2x token capacity | |
|---|---|---|---|---|---|
Monthly SwitchNext tokens One shared balance across every model included in the plan | 50K | 8M | 20M | 40M | 80M |
Agent Mode Have Agent Mode modify workspace files | ✓ | ✓ | ✓ | ✓ | ✓ |
Compare Mode Compare model responses side by side | ✓ | ✓ | ✓ | ✓ | ✓ |
@workspace context Include the entire workspace in context. | - | ✓ | ✓ | ✓ | ✓ |
Saved conversations Chat threads shared by Chat and Code | 3 | 10 | 20 | 50 | 50 |
|---|---|---|---|---|---|
Exchanges per conversation Completed question-and-response exchanges stored in each chat | 20 | 75 | 150 | 250 | 500 |
Code workspace Your coding workspaces | 2 | 5 | 10 | 50 | 50 |
Files per Code workspace The file limit is applied independently to every project | 10 | 20 | 50 | 100 | 100 |
@file context per request Project files selectable with @fileName | 5 | ✓ | ✓ | ✓ | ✓ |
Model Access & SwitchNext Rates
Every model you have access to draws from the same SwitchNext token balance. Each model consumes that balance at its own input and output rates.
SwitchNext tokens used per 1K provider tokens: IN = input rateOUT = output rate
Free
50K total across models
Starter
$10/month | 8M total across models
Premium
$25/month | 20M total across models
Pro
$50/month | 40M total across models
Pro+
$100/month | 80M total across models
Claude-Fable-5.2
Context window = 1,000,000 tokens
—
—
—
Access
Access
Claude-Opus-5.5
Context window = 1,000,000 tokens
—
—
—
Access
Access
Claude-Sonnet-5.5
Context window = 1,000,000 tokens
—
—
Access
Access
Access
Claude-Haiku-5.5
Context window = 1,000,000 tokens
Access
Access
Access
Access
Access
DeepSeek-V4-Pro
Context window = 1,000,000 tokens
—
—
Access
Access
Access
DeepSeek-V4.1-Flash
Context window = 1,000,000 tokens
Access
Access
Access
Access
Access
Gemini-4-Argon
Context window = 1,048,576 tokens
—
—
—
Access
Access
Gemini-4-Carbon
Context window = 1,048,576 tokens
—
—
—
Access
Access
Gemini-3.8-Flash
Context window = 1,048,576 tokens
—
—
—
Access
Access
Gemini-3.5-Flash-Lite
Context window = 1,048,576 tokens
Access
Access
Access
Access
Access
GPT-6.2-Astra
Context window = 1,050,000 tokens
—
—
—
Access
Access
GPT-6.2-Sol
Context window = 1,050,000 tokens
—
—
—
Access
Access
GPT-6-Luna
Context window = 1,050,000 tokens
Access
Access
Access
Access
Access
Muse Spark 1.3
Context window = 1,048,576 tokens
—
—
Access
Access
Access