AI inference & GPU cloud
offrec
Zero-retention inference for frontier models
- 0community votes
- 0DR by Ahrefs no change since last check
Ahrefs Domain Rating signal 13 Nov 2026, signal shifted 9 Nov 2026.
API and chat for running frontier AI models with zero-retention guarantees, returning a signed receipt for every call.
What it is
offrec provides API and chat access to frontier AI models from labs including Anthropic, Google, DeepSeek, Alibaba and others. Every prompt is processed under zero-data-retention terms and never stored by offrec. The service runs models on managed providers including Google Cloud Vertex AI, Amazon Bedrock and Fireworks AI.
Every API call returns a cryptographically signed receipt that records how the call was handled, including the retention basis, model used, token counts, cost and provider—but carries no prompt or answer. Users can verify receipts against offrec's published public key.
The service offers both a web chat interface and an OpenAI-compatible API. Accounts can pay per call or subscribe to monthly plans with recurring credit allowances. No GPUs are owned by offrec; the company negotiates zero-retention agreements with providers on behalf of users.
Systems
- Zero-retention guarantees with signed cryptographic receipts for every API call
- OpenAI-compatible API endpoint
- Web-based chat interface with encrypted conversations
- Access to 15+ frontier models including Claude, Gemini, Qwen, DeepSeek
- Python SDK and R package support
- Receipts show token usage, cost, model, provider and retention basis
- No data storage on offrec infrastructure
- Models run on managed third-party providers
Pricing
Pricing model: Freemium
Pay as you go from $10. Monthly subscriptions: Run $19/month, Run Plus $99/month (5× allowance), Run Max $199/month (10× allowance). Model pricing per million tokens varies: qwen3.8-max $2.00 input/$6.00 output, claude-haiku-5-5 $0.10 input/$0.50 output, claude-sonnet-5 $2.00 input/$10.00 output, cl
Want to see what offrec does next? Follow them for milestones, new products and stories by email.
offrec metrics
Signal readout for offrec.ai: Ahrefs Domain Rating and Majestic link signals, arrows for the change since the last scan.
- 0 Domain Rating no change since last check
- 0 Trust Flow no change since last check
- 0 Citation Flow no change since last check
- 0 Referring domains no change since last check
- 0 External backlinks no change since last check
Ahrefs Domain Rating signal 13 Nov 2026, signal shifted 9 Nov 2026. Majestic signal 9 Nov 2026, signal shifted 9 Nov 2026. Link signals from Majestic. Trust Flow, Citation Flow and Topical Trust Flow are trademarks of Majestic-12 Ltd.
offrec domain signal
Show the signal details
Public RDAP record, last read 13 Nov 2026, 02:45 UTC.
- Domain age 5 days
- Registered
- Expires
- Registrar HOSTINGER operations, UAB
- DNSSEC Not signed
offrec post-launch signal
The record for offrec after its launch on Nexora Launch (9 November 2026), from the readings we keep.
- 0 Domain Rating (Ahrefs) no change since launch
at launch: 0 (9 Nov 2026); latest: 13 Nov 2026 - 0 Trust Flow (Majestic)
first measured 9 Nov 2026 - 0 Referring domains (Majestic)
first measured 9 Nov 2026
Day 3 since launch. Next receipt: day 30, 9 Dec 2026. A change here is a reading, not a claim about its cause; lots of things move these figures. Anything we do not measure is not shown.
Got a launch coming up?
Plan your launch with our free playbook, from preparing your listing to choosing more launch directories.
Quick answers
- How does zero retention work on the API?
- offrec never stores your prompts. Each model call runs under zero-data-retention terms with its provider, and offrec holds these agreements on behalf of users so they don't have to negotiate them individually.
- What information does a receipt contain?
- The receipt records the retention basis, model used, token counts (input and output), cost, provider, and timestamp, but carries no prompt or answer data. Each receipt is signed with Ed25519 for cryptographic verification.
- Which providers host the models?
- Gemini and Gemma models run on Google Cloud Vertex AI, Claude models run on Amazon Bedrock, and DeepSeek, Kimi and Qwen models run on Fireworks AI. Every receipt names the provider that served each call.
- What are the subscription options?
- Users can pay per call starting from $10, or subscribe to monthly plans: Run at $19/month with a base credit allowance, Run Plus at $99/month with 5× the allowance, or Run Max at $199/month with 10× the allowance.
offrec has a free listing. The owner can unlock the full profile with a paid launch for $5:
- Founder story (locked)
- Milestones (locked)
- Demo video (locked)
- Dofollow website link (locked)
Also on the frontier
-
Rank 1: BitsRun
Deploy any open model from Ollama or Hugging Face as a private, OpenAI-compatible API
AI inference & GPU cloudUnited States
-
DR 0 no change since last check 0 votes. Log in to send Anona Compute a vote -
Rank 3: Dory
Persistent Linux computers for AI agents, from about $0.03 an hour
DR 0 no change since last check 0 votes. Log in to send Dory a vote -
DR 12 +2 (up) since last check 0 votes. Log in to send condense a vote