CrofAI OpenAI-compatible
Aggregator that resells open-source models behind one cheap key.
⚠️Heads up: Subscriptions are being reworked (announced 2026-05-31) — likely off the weekly bench from 2026-W23. CrofAI says flat-rate subs are no longer sustainable. Either subs convert to credit-based plans worth 1.15× their PAYG value (a $5 Hobby sub becomes $5.75 of credit/month) or they are removed entirely in favour of rock-bottom PAYG. Existing subs keep working until they end or renew; the change rolls out 2026-05-31 through ~06-03. The flat, unlimited $5 Hobby plan that made CrofAI our volume daily driver is going away, so under metered PAYG we expect to stop running the full weekly suite against it. Historical data stays on this page for context.
CrofAI is an inference aggregator: one API key, many open-source models (DeepSeek, GLM, Kimi, Qwen, MiniMax, Gemma). Two of its models are completely free, and the paid ones are positioned as the cheapest places to run their respective open weights.
Strengths
- One key, many open-source models
- Two fully free models (Qwen3.5-9B, GLM-4.7-Flash)
- Standard OpenAI endpoint — works with any compatible client
When to use it
- Trying many open-source models under one key
- Exploration before committing to a single provider
- Quick MVPs and prototypes
Subscription plans
| Plan | Price | Quota | Available |
|---|---|---|---|
| Free / PAYG | $0/mo | Pay-per-token, no recurring charge | yes |
| Hobby | $5/mo | 500 daily requests · access to all models | yes |
| Pro | $10/mo | 1,000 daily requests · priority support | yes |
| Intermediate | $20/mo | 2,500 daily requests | yes |
| Scale | $50/mo | 7,500 daily requests | yes |
| Max | $100/mo | 15,000 daily requests | yes |
Notes: Subscription tiers add daily request quotas on top of the PAYG endpoint; all tiers see the same model catalogue. See crof.ai/pricing for current rates.
Models tested on CrofAI
Speed numbers below are specific to CrofAI's routing and hardware. The same model may appear on other providers' pages with different throughput.
| Model | Best tok/s | Avg tok/s | Runs | Success | Longest output (chars) |
|---|---|---|---|---|---|
| kimi-k2.5-lightning | 614.4 | 558.4 | 3 | 100% | 5,196 |
| qwen3.5-9b | 174.7 | 156.9 | 3 | 100% | 2,592 |
| qwen3.5-9b-chat | 158.0 | 148.9 | 3 | 100% | 3,644 |
| qwen3.6-27b | 150.7 | 127.2 | 3 | 100% | 2,895 |
| kimi-k2.5 | 114.0 | 92.4 | 3 | 100% | 5,467 |
| glm-4.7-flash | 113.2 | 113.2 | 3 | 33% | 3,245 |
| glm-5.1 | 108.0 | 74.5 | 3 | 100% | 4,600 |
| kimi-k2.6 | 105.8 | 73.7 | 3 | 100% | 5,201 |
| glm-5 | 105.1 | 105.1 | 3 | 33% | 2,255 |
| greg | 103.8 | 103.8 | 3 | 33% | 4,380 |
| minimax-m2.5 | 102.8 | 83.5 | 3 | 100% | 3,352 |
| gemma-4-31b-it | 101.2 | 50.2 | 3 | 100% | 3,469 |
| deepseek-v3.2 | 93.0 | 68.6 | 3 | 100% | 3,232 |
| kimi-k2.6-precision | 80.7 | 65.1 | 3 | 100% | 3,901 |
| glm-5.1-precision | 72.2 | 64.2 | 3 | 100% | 4,217 |
| deepseek-v4-pro | 59.6 | 58.1 | 3 | 100% | 4,699 |
| glm-4.7 | 57.8 | 50.2 | 3 | 100% | 3,521 |
| qwen3.5-397b-a17b | 52.7 | 52.7 | 3 | 33% | 3,018 |