Gemini CLI, without the token bill.
Point Gemini CLI at Piramyd and read whole repositories, long docs and huge logs in one go — the context you use doesn't show up on a bill.
3 days on Solo · card required · cancel before day 4 and you pay nothing
- Tokens this session
- 0
- Per-token price*
- $0.00
- Billed on Piramyd
- $0.00
*Illustrative session, at $3 per 1M tokens. On Piramyd it's covered by your flat plan.
Gemini CLI on Piramyd in three steps.
- 01
Start a plan and copy your key
Solo starts with a 3-day trial. Your API key is in the dashboard.
- 02
Run the installer
Paste the key and pick Gemini CLI.
$ npx piramyd - 03
Use Gemini CLI as usual
The installer sets the key in ~/.gemini/settings.json. Keep running the same command.
$ gemini
- Whole-repo reads without trimming
- Same command, same workflow
- Every model in the catalog
54 frontier models. Every plan gets all of them.
Switch models per task without switching tools or bills. One API key speaks both the OpenAI and Anthropic formats.
Claude Opus 5
Anthropic
Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work.
- Reasoning
- Image input
- File input
- Tool calling
- Context
- 1M
- Output
- 128K
- Input
- Text, Images, Files
GPT-5.6 Luna
OpenAI
GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series.
- Reasoning
- Image input
- File input
- Tool calling
- Context
- 1.1M
- Output
- 128K
- Input
- Files, Images, Text
GPT-5.3-Codex
OpenAI
GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2.
- Reasoning
- Image input
- File input
- Tool calling
- Context
- 400K
- Output
- 128K
- Input
- Text, Images, Files
Gemini 3.8 Flash
Google
Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.
- Reasoning
- Image input
- File input
- Tool calling
- Context
- 1M
- Output
- 66K
- Input
- Text, Images, Video, Files, Audio
Kimi K3
MoonshotAI
Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.
- Reasoning
- Image input
- Tool calling
- JSON output
- Context
- 1M
- Output
- 944K
- Input
- Text, Images, Video
DeepSeek V4 Pro 0813
DeepSeek
DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.
- Reasoning
- Tool calling
- JSON output
- Context
- 1M
- Output
- 393K
- Input
- Text
One flat price. Unlimited tokens.
Pick a plan by how many agents you run at once. Every plan has every model and no per-token charges.
Solo
One developer and their agents.
$30/month
- Unlimited tokens, no overage
- All 54 models
- 10 requests per minute
- About 2 agents working at once
- Community support
Card required · cancel before day 4
Growth
Most popularHeavy daily use, or a small team.
$50/month
- Unlimited tokens, no overage
- All 54 models
- 25 requests per minute
- About 5 agents working at once
- Priority support
Cancel anytime
Scale
Teams running agents in parallel all day.
$90/month
- Unlimited tokens, no overage
- All 54 models
- 50 requests per minute
- About 10 agents working at once
- Dedicated support
Cancel anytime
3-day trial on Solo · Card required · Cancel before day 4 and pay nothing
Stop rationing your agents.
Let them finish the job.
The agents you already use, every frontier model, and a bill that doesn’t move when they work harder.
3-day trial on Solo · Card required · Cancel before day 4 and pay nothing
For AI agents
Give this link to any agent: it describes the whole API.