A verdict here is not a fixed property of the vendor. A one-off pricing event demotes a vendor while its recorded date falls in the last 180 days and then lapses on its own, with nothing about the vendor having changed; a standing condition — a free tier withdrawn and not restored, a product retired — does not lapse with time. This one rests on a record effective 2026-10-06, so it lapses on 2027-04-05 unless we record something new first.
Fast LLM inference on Groq's LPU hardware. Free plan: gpt-oss-20b, gpt-oss-120b and Qwen3.8 27B, each at 30 requests a minute, 1,000 requests and 200,000 tokens a day, plus Whisper speech-to-text at 2,000 requests a day. Each of the three free models is also limited to 8,000 tokens a minute, and Groq applies whichever limit is reached first. Whisper is also limited to 20 requests a minute, 7,200 audio seconds an hour and 28,800 audio seconds (8 hours of audio) a day. On the free plan, gpt-oss-safeguard-20b is limited to 3 requests a minute, 1,000 requests a day, 2,000 tokens a minute and 200,000 tokens a day. Qwen3.8 27B, gpt-oss-safeguard-20b, Orpheus Arabic Saudi and Orpheus V1 English are Preview models. Groq says Preview models "are intended for evaluation purposes only and should not be used in production environments as they may be discontinued at short notice". Llama 3.3 70B and Llama 3.1 8B left the free and developer plans on 2026-08-16 and are Enterprise-only. Orpheus text-to-speech (English and Saudi Arabic) is also on the free plan, at 10 requests a minute, 100 requests and 3,600 tokens a day. Developer plan prices per 1M tokens: gpt-oss-120b $0.15/$0.60; gpt-oss-20b $0.075/$0.30; Qwen3.8 27B $0.80/$4.00. The Batch API costs 50% less and returns results within 24 hours to 7 days, without impacting standard rate limits. When requests to gpt-oss-20b, gpt-oss-120b or gpt-oss-safeguard-20b start with the same text as a recent request, Groq caches that part automatically and bills those input tokens 50% less. The batch discount does not stack with prompt caching discounts; all batch tokens are billed at the batch rate regardless of cache status. Orpheus text-to-speech costs $22 per 1M characters in English and $40 in Saudi Arabic. Groq's API is OpenAI-compatible at the base URL https://api.groq.com/openai/v1. The free models' API model IDs are openai/gpt-oss-120b, openai/gpt-oss-20b and qwen/qwen3.8-27b.
- Groq rate limits apply to the whole organization, not per user or API key. A request over the limit returns a 429 Too Many Requests error. Cached tokens do not count toward rate limits. (From console.groq.com/docs/rate-limits, read 2026-11-04.)
- You are billed only after you add a payment method and move to the paid Developer tier. (From console.groq.com/docs/billing-faqs, read 2026-10-05.)
- Groq does not charge at upgrade. It invoices at the end of each monthly billing cycle, and also when cumulative usage first reaches $1, $10, $100, $500, or $1,000. For India customers, the thresholds are $1, $10, and then $100 recurring. Groq bills only when usage reaches at least $0.50. Groq accepts credit cards, United States bank accounts, and SEPA debit accounts. (From console.groq.com/docs/billing-faqs, read 2026-11-04.)
- You can downgrade to Groq's Free tier at any time. You must pay a final invoice for any outstanding usage before the downgrade completes. (From console.groq.com/docs/billing-faqs, read 2026-11-04.)
- Organization owners on Groq's paid tiers can set a monthly spend limit. It applies across all API keys. At the limit, API calls return a 400 with code blocked_api_access. Current spend updates every 10-15 minutes, so you might exceed the limit slightly. Limits reset on the 1st of each month. Email alerts can be set before the limit. (From console.groq.com/docs/spend-limits, read 2026-11-04.)
- Groq's flex processing is for paid customers only. It has 10x higher rate limits than on-demand processing. Pricing matches the on-demand tier. Set the service_tier parameter to flex. If flex capacity is unavailable, requests fail with status 498 and error capacity_exceeded. (From console.groq.com/docs/flex-processing, read 2026-11-04.)
- Groq's Performance tier provides a 99.9% availability SLA and 99% latency guarantee. It is available only on enterprise plans. Billing is based on provisioned throughput, not per-token usage. Uncached context length must be under 8,192 tokens. (From console.groq.com/docs/performance-tier, read 2026-11-04.)
- Groq's Services Agreement does not permit it to train or fine-tune models on your inputs or outputs unless you give permission. (From console.groq.com/docs/legal/services-agreement, read 2026-10-05.)
- Groq's Services Agreement grants use of Groq APIs to integrate its services into customer applications for end users. Its restrictions do not prohibit commercial use. (From console.groq.com/docs/legal/services-agreement, read 2026-10-29.)
- Customers may not resell access to their Groq account. Groq's Services Agreement prohibits selling, reselling, or transferring its services except with Groq's express approval. (From console.groq.com/docs/legal/services-agreement, read 2026-10-29.)
- Groq does not retain inference requests by default. Batch input and output files are kept for 30 days unless deleted earlier. Fine-tuning data is kept until deleted. Groq may log inference inputs and outputs for up to 30 days to troubleshoot errors or investigate abuse. Zero Data Retention stops this logging and disables the Batch API and fine-tuning. (From console.groq.com/docs/your-data, read 2026-11-04.)
- Data Groq retains is stored in Google Cloud buckets in the United States. (From console.groq.com/docs/your-data, read 2026-10-05.)