Skip to content

Simple pricing for open models

Pick the way that fits how you work.

Pay as you go

Hosted Model APIs, per token, on one prepaid balance.

No subscription
$

$5 minimum top-up. Pay per token.

What's included

  • OpenAI-compatible chat completions and Anthropic-compatible Messages
  • Per-token pricing with cached input discounts on supported models
  • Session-aware routing keeps agent replays warm
  • One prepaid balance, no seats, no per-user fees

New accounts start with $1 free to test the Model APIs.

Add credits

Enterprise

Dedicated infrastructure, compliance, and custom volume.

Custom pricing

Everything self-serve includes, plus

  • Audit logs and role-based access control (RBAC)
  • Custom volume and contract terms
  • Custom SLAs up to 99.99%
  • SOC 2 Type II attestation
  • Dedicated CSM and private Slack
Request a demo

Model APIs

Pay for model tokens, not idle capacity

Price per 1M tokens

Limits and modality-specific capabilities are listed on each model page.

Compare Pay as you go and Enterprise

Pay as you go is self-serve, funded by credit top-ups. Enterprise adds private infrastructure, reserved capacity, compliance, and custom terms.

Pay as you go
from a $5 top-up
Pricing modelCredit top-ups from $5, pay for what you run
BalanceOne balance for Model APIs
SeatsNo per-seat fees
OpenAI- and Anthropic-compatible APIsIncluded
Audit logs and RBACFree with a Business account (Settings)
SOC 2 Type IINot included
SLANo contractual SLA
SupportPriority email
Enterprise
Custom
Pricing modelCustom volume and terms
BalanceOne shared balance with custom controls
SeatsNo per-seat fees
OpenAI- and Anthropic-compatible APIsIncluded
Audit logs and RBACIncluded
SOC 2 Type IIIncluded
SLAUp to 99.99%
SupportDedicated CSM and private Slack

Compare pay-as-you-go API costs with renting GPUs. Compare GPU fit, rental costs, idle time and API costs for your model and traffic.

Common questions

Can't find what you're looking for? Get in touch

How does the balance work?

You add credits with one-time top-ups, starting at $5, and spend from one balance, in dollars. Optional auto-recharge adds credits automatically when your balance runs low. Top-ups stay valid for one year. Use your balance for Model APIs.

Start building on open models

One API key for the OpenAI and Anthropic SDKs.

TLS in transit, AES-256 at rest
Workspace isolation
No training on your data
SOC 2 Type II

Starter

$10 a month

About $12 of usage a month

5-hour limit
$1.11
Weekly limit
$2.77
Free Standby
Up to $0.20 of chat a day
Requests at once per model, when busy
4 to 32

Pro

$29 a month

About $35 of usage a month

5-hour limit
$3.23
Weekly limit
$8.08
Free Standby
Up to $0.58 of chat a day
Requests at once per model, when busy
5 to 32

Team

$99 a month

About $119 of usage a month

5-hour limit
$10.98
Weekly limit
$27.46
Free Standby
Up to $1.98 of chat a day
Requests at once per model, when busy
8 to 32

Cached context

Up to 99.5% cache hit rate, last 24 hours. From $0.01 per 1M cached input tokens, so your plan goes further.

Every plan is shared by its workspace, not per member.

Limits

Limits that reset every 5 hours and every week

Limits reset

Every 5 hours

Every week

What happens at a limit

  1. Plan

  2. Credits

    Your choice: a cap, or no limit

  3. Standby

    Free, slower chat

  4. Stop

    Until a reset

Setup

Connect your coding agents

Review each connection before it is applied.

Let your coding agent set it up

  1. 1Paste the prompt into your coding agent
  2. 2Approve the sign-in in your browser
  3. 3Say yes to the setup plan

Set up with your coding agent

19 agents ready

  • Claude Code
  • Codex
  • OpenCode
  • Pi
  • Aider
  • Qwen Code
  • Kilo Code
  • Goose
  • Continue
  • Cline
  • Droid
  • Grok Build
  • Hermes Agent
  • OpenClaw
  • Crush
  • Kimi CLI
  • Mistral Vibe
  • Forge
  • Nanocoder

Preview

  • Zed
  • Oh My Pi
  • gptme
  • Tabby
  • Octofriend
  • Command Code
  • Junie CLI
  • VS Code Copilot Chat
  • Theia AI
  • OpenHands CLI
  • Copilot CLI

Preview agents may need extra setup. Each connection makes one small test request.

Common questions

Can't find what you're looking for? Get in touch

What happens at a limit?

If you turned on Keep full speed on credits, credits pay with your choice of a cap per billing period or no limit. When credits cannot pay, free Standby serves chat. Choose at checkout and change it in Coding plan. If neither can serve a request, it stops with the reason, reset time and next step.

Choose a plan

TLS in transit, AES-256 at rest
Workspace isolation
No training on your data
SOC 2 Type II