Piramyd

Your coding agents,
without the meter.

Claude Code, Codex, Gemini CLI and more on 54 frontier models. Unlimited tokens for one flat monthly price — so your agents finish the job instead of stopping at a budget.

Start 3-day trial

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.

Set up in one command for

  • Claude Code
  • Codex CLI
  • Gemini CLI
  • OpenCode
  • Kimi Code
  • Qwen CLI
  • OpenClaw

Tokens our users didn’t have to count.

Every token developers’ agents have used through Piramyd, updated as it happens. None of it billed per token.

Input
—
Output
—

Read from the public API every 30 seconds; between reads it moves at the rate last measured.

Most-used models

Models in today’s catalog, by tokens served

A meter makes you stop your agent halfway.

Same agent, same task, two ways to pay. When every token is billed, the rational move is to cut the run short. When it isn't, the rational move is to finish.

Billed per token

List price, ~$3 per 1M tokens

This task

$0.00

Task progress0%

0.0M tokens

Agent working…

Piramyd

Flat monthly plan, unlimited tokens

Extra for this task

$0.00

Task progress0%

0.0M tokens

Agent working…
With a meter, youOn Piramyd, you
  • Trim the context it neededGive it the whole repo
  • Stop the run at 80%Let it finish and verify
  • One agent at a timeReview, docs and tests in parallel
  • Skip the big refactorShip the refactor

Illustrative: a 22.4M-token refactor at $3 per 1M tokens with a $40 budget alert.

From install to unlimited in about a minute.

Keep the agents you already use. Piramyd replaces the bill, not your workflow.

  1. 01

    Start your plan

    Subscribe in the dashboard and copy your API key. Solo starts with a 3-day trial.

  2. 02

    Run npx piramyd

    Paste the key, pick your agents. Each gets its own Piramyd profile; your usual setup, CLAUDE.md, hooks and memory stay as they are.

  3. 03

    Let them work

    Long refactors, parallel agents, research that reads everything. No token counter, no overage, one monthly price.

Configured for you

Anything else that speaks the OpenAI or Anthropic API works too: set the base URL to https://api.piramyd.cloud/v1.

  • Claude Codeclaude-piramyd
  • Codex CLIcodex-piramyd
  • Gemini CLI
  • OpenCode
  • Kimi Code
  • Qwen CLI
  • OpenClaw

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.

More than chat. One API key.

The same key and base URL also give you embeddings, speech and the web.

  • Embeddings

    Turn text into vectors for search and RAG. Multilingual models included.

    POST /v1/embeddings
  • Speech-to-text

    Whisper transcription for files up to 25 MB, with JSON, text, SRT or VTT output.

    POST /v1/audio/transcriptions
  • Coming soon

    Text-to-speech

    Natural voices from text. Models are being added.

    POST /v1/audio/speech
  • Web search

    Multi-engine search results your agents can cite.

    POST /v1/search
  • Scrape & crawl

    Clean content from one page or a whole site, ready for an LLM.

    POST /v1/scrape · /v1/crawl

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
Start 3-day trial

Card required · cancel before day 4

Growth

Most popular

Heavy 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
Choose Growth

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
Choose Scale

Cancel anytime

3-day trial on Solo · Card required · Cancel before day 4 and pay nothing

What would this cost per token?

An estimate with your numbers. Agents resend the conversation on every step, so a working hour adds up fast. Defaults are on the low side; change any of them.

4 h
22 days
1M
$3.00

88M tokens a month

Billed per token
$264
On Piramyd Solo
$30

About $234 a month less, and no reason to stop an agent early.

Compare plans

Plan comparison
FeatureSoloGrowthScale
Monthly price$30$50$90
TokensUnlimitedUnlimitedUnlimited
Per-token chargesNoneNoneNone
ModelsAll 54All 54All 54
Requests per minute102550
Agents working at once*≈ 2≈ 5≈ 10
Extra throughput+5 RPM for $15, one-time+5 RPM for $15, one-time+5 RPM for $15, one-time
Trial3 days——
SupportCommunityPriorityDedicated

* A coding agent in an active loop sends about 5 requests a minute. Short bursts over your limit wait in line for a few seconds instead of failing.

Questions

Is it really unlimited?

Yes. There is no token quota, no monthly cap and no overage bill. The only limit is how many requests you send per minute, which is what each plan sets.

What happens when I hit my requests-per-minute limit?

Short bursts wait in line for a few seconds and then go through, so your agent doesn't see an error. If you keep sending above your limit, requests get a “retry in 5 seconds” answer, which every major agent handles on its own. You can add 5 RPM for a one-time $15 from the dashboard at any time; it stays on your account.

How does the 3-day trial work?

Start Solo with a card. You get the full plan for 3 days and aren't charged until day 4. Cancel from the dashboard before then and you pay nothing.

Which models do I get?

Every plan includes the full catalog, including new models as they're added. Plans differ only in throughput.

Will my agent's setup change?

No. npx piramyd gives each agent its own Piramyd profile and leaves your default configuration, instructions, hooks and memory untouched.

How is my data handled?

We don't store your prompts or outputs. Requests are processed securely and encrypted in transit. Your data is yours.

Can I cancel anytime?

Yes, from the dashboard. There is no contract and no cancellation fee.

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.

Start 3-day trial

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.