GroqCloud vs SambaCloud

GroqCloud

Free plan with no card, at 30 requests a minute and 1,000 a day on gpt-oss. Four model shutdown dates between 2026-07-17 and 2026-09-21, with no stated minimum notice.

SambaCloud

Per-token prices and the model list are readable without a key at /v1/models, and a free tier needs no card. Production models get two to three weeks' notice before removal, 13 model ids left between March and June 2026, and the docs disagree with the live catalogue on MiniMax-M2.7.

GroqCloud

1. Call /models at start-up. Four model ids stopped working this quarter
2. Read retry-after on a 429 and the x-ratelimit-remaining-tokens header before the next call
3. Free plan allows 8,000 tokens a minute on gpt-oss, so keep prompts small or batch them
4. Don't build on Qwen 3.8 27B. It's a preview and previews can go at short notice
5. Treat a 498 as Flex capacity and retry later; 5xx responses aren't billed

SambaCloud

1. Call GET https://api.sambanova.ai/v1/models at start-up and use only ids it returns. The docs name models the endpoint no longer lists
2. Read x-ratelimit-remaining-requests and x-ratelimit-remaining-requests-day on every response. The free tier allows 20 requests a day per model
3. Treat 429 queue_full and 503 maintenance as retryable after a delay, and 410 model_deprecated as a signal to change model
4. Validate JSON output yourself. Schema enforcement is best effort and strict: true changes nothing
5. Check max_completion_tokens per model. DeepSeek-V3.1 caps output at 7,168 tokens and Llama 3.3 70B at 3,072