| What it does | AI coding agent in your terminal with dedicated GPU and flat pricing per developer
| Multi-model desktop workspace with cost optimization through agent routing
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | 2023
| Not given
|
|---|
| Based in | BR
| Not given
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | Lite: $20/month (limited use, weekly allowance); Pro: $69/month (10 million free tokens); Max: $129/month (10 million free tokens); Ultra: $269/month (10 million free tokens); Enterprise: custom pricing with dedicated GPU cluster; Usage-based API: from $0.12 per 1M tokens prepaid balance with no mon
| Desktop app: Free and open source (Apache 2.0). Halv Cloud: US$10 per month.
|
|---|
| Key features | - Works with Cursor, VS Code, JetBrains, OpenCode, Hermes, Pi and other OpenAI-compatible clients
- Nine AI models available including DeepSeek V4 Pro, GLM 5.3, Qwen, and others
- Switch between models mid-conversation without losing context
- Unlimited tokens on Pro, Max, Ultra plans with transparent rate limits
- Code never trained on or shared with third-party providers
- 10 million free tokens with all paid plans for trial
- Referral program with credits and Pix payouts
- Community of 200+ active developers on WhatsApp and Discord
- Context windows up to 1 million tokens on most models
- Data export available during subscription and up to 30 days after termination
| - JEV agent routing for automatic model and reasoning selection
- Support for Claude Code, Codex, Kimi, and GLM models
- Synced savings dashboard
- History across machines
- Automatic account rotation
- Code navigation via Crux
- Command output filtering via RTK
- Model context processing via Headroom
- Cross-platform support for macOS, Windows, Linux
|
|---|
| What makes it different | - Dedicated GPU allocation per plan with no resource sharing
- Fixed flat monthly pricing with no surprise token overages
- Brazilian infrastructure with code isolation from US-based AI providers
- Transparent usage limits and model pricing shown before subscription
| - 57.1% lower recorded model costs compared to vanilla Codex on benchmark runs
- Free and open source desktop app under Apache 2.0 license
- Agent routing included with Halv Cloud at no additional fee
- Single workspace for multiple AI coding models
- Matched vanilla Codex pass rates with lower cost
|
|---|
| Free plan | Not given
| Not given
|
|---|
| Open source | Not given
| Not given
|
|---|
| Platforms | Not given
| Not given
|
|---|
| Public API | Not given
| Not given
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 40 ▲ +1 (up) since last check | 19 ● no change since last check |
|---|
| Trust Flow (Majestic) | 17 | 3 |
|---|
| Citation Flow (Majestic) | 27 | 24 |
|---|
| Referring domains (Majestic) | 48 | 57 |
|---|
Verboo Code
Halv