Compare · Alternative · Checked on 27 October 2026

Hopper and Petrova.

Hopper hosts fast, cheap open models and is live. Petrova is one balance with spend rules across suppliers, and is not live. This is Hopper Inference, not the travel app.

Hopper is live. Petrova is a preview.Petrova runs on test data only. It has no real supplier, and you cannot buy it today.

How Hopper works

Fast, cheap open models for real-time voice agents.

  1. You make a key in its console, or your coding agent gets a trial key itself and you keep it with a short code.
  2. Your agent measures speed on your own prompts and shows you a table before changing any code.
  3. You switch your LLM to its OpenAI-format API. It gives tested code for voice frameworks.
  4. It hosts open models, plus speech-to-text and text-to-speech.
  5. You pay from prepaid credits. Each answer shows the cost and the balance in its headers. At zero balance, calls stop.

How Petrova works

The account your agent calls. Today this all runs on test data.

  1. Your agent keeps running where it runs today. Petrova does not run it.
  2. You change two settings: the base URL and the key. Anthropic and OpenAI formats both work.
  3. Before each call, Petrova holds the most that call could cost.
  4. A supplier answers. If one fails before the first word, the call moves to another.
  5. You are charged what the call used, plus a 5.5% fee. The rest comes back. Never above the hold.
Side by sideChecked on 27 October 2026
HopperPetrova
Live todayYesNo. Preview on test data
Runs its own modelsYesNo. Petrova owns no GPUs
Open-model price, per million in / outGemma 4 31B: $0.30 / $0.40. DeepSeek V4.1 Flash: $0.09 / $0.85No open models. Cheapest: Haiku 5.5 at $0.1055 / $0.5275 (not on sale)
SpeechText-to-speech, speech-to-text, voice cloningNo
Agent gets a trial key by itselfYes, liveA key at $0 in one call, test mode only. No trial money
Cost and balance on every answerYes, in headersPlanned. Today, read the receipt
MCP connector with tools that need no accountYes, liveMCP server on test data; cost tools need no key
API formatsOpenAIAnthropic and OpenAI (test data)
Claude modelsNot foundYes (test data)
Spend limitsStops at zero balance. Caps: not foundAccount, project, key, agent, session (test data)
Charge never above a hold set before the callNot foundYes (test data)
Failover to another companyNot foundYes (test data)
Tools and memory on one balanceNot foundYes (test data)

Green marks the stronger answer in a row, red the weaker. "Test data" means Petrova's code does it in tests, not as a service. "Not found" means we did not find it on their public pages on the check date. It may still exist.

Where Hopper is ahead

  • Live today
  • Runs its own models
  • Open-model price, per million in / out
  • Speech
  • Agent gets a trial key by itself
  • Cost and balance on every answer
  • MCP connector with tools that need no account

What we could not check

  • Its speed claims under real load.
  • Whether every model runs on its own GPUs.
  • Its customers. None are named.

Read on 27 October 2026, on their public pages: withhopper.com · withhopper.com/skill.md · docs.withhopper.com · its MCP model list. Things may have changed since. Each claim of theirs is their own statement.