# CrofAI

CrofAI (ai.nahcrof.com) is a hosted LLM inference provider that markets itself as "the cheapest inference provider for large models." It serves a curated catalog of open-weights models — DeepSeek V4, GLM 5 / 5.1, Kimi K2.5 / K2.6, Mimo V2.5, Qwen 3.5 / 3.6, Gemma 4, MiniMax M2.5, and a model called `greg` — over what looks like an OpenAI-compatible API (the public pricing page is the only documented surface at ingest time; auth-gated endpoints handle requests). Three things make it interesting versus the bigger providers:

1. **Quantization is disclosed.** Every model in the table lists its weight format: `Q4_0`, `Q4_K_M`, `Q6_K`, `Q8_0`, `int4`, `fp8`, `awq`. Most large providers hide this detail. CrofAI exposes it as a first-class column. See [[llm-quantization]] for why Q4_0 vs Q4_K_M vs UD-Q4_K_XL matters.
2. **Two billing modes, not stacked.** The Free tier is pure pay-as-you-go at the listed per-token rates ("Pay only for usage. No recurring monthly charge"). The paid tiers ($5–$100/mo) are flat subscriptions that buy a daily *request* quota (500–15,000 requests/day), with no further token charge implied — the per-token rates appear to be the PAYG / overage price, not an additional charge to subscribers within their quota. Some "precision" variants count as 2 requests against the daily quota. The page doesn't explicitly say what happens past the daily cap.
3. **Q4_0 is the baseline.** Most models use the more aggressive `Q4_0` quantization rather than `Q4_K_M`. That's measurably worse quality on MoE architectures (see [[llm-quantization]]). The "precision" variants — `deepseek-v4-pro-precision`, `mimo-v2.5-pro-precision`, `glm-5.1-precision`, `kimi-k2.6-precision` — bump to `Q8_0` or `int4` at 2-3× the price.

## Pricing snapshot (2026-05-13)

| Model | Quant | Context | $/M in | $/M cache | $/M out | Speed |
|---|---|---|---|---|---|---|
| deepseek-v4-pro | Q4_0 | 1M | $0.40 | $0.003 | $0.85 | ~70 t/s |
| deepseek-v4-pro-precision | Q8_0 | 1M | $1.25 | $0.10 | $2.50 | ~73 t/s |
| deepseek-v4-flash | Q4_0 | 1M | $0.12 | $0.02 | $0.21 | ~77 t/s |
| kimi-k2.6 | Q3_K_L | 262k | $0.50 | $0.10 | $1.99 | ~82 t/s |
| kimi-k2.5-lightning | 530b-int4 | 131k | $1.00 | $0.20 | $3.00 | ~1890 t/s |
| glm-5.1 | Q6_K | 202k | $0.45 | $0.09 | $2.10 | ~171 t/s |
| qwen3.5-9b | fp8 | 262k | $0.04 | $0.008 | $0.15 | ~210 t/s |
| gemma-4-31b-it | Q4_0 | 262k | $0.10 | $0.02 | $0.30 | ~90 t/s |

Full table in the [[crofai-pricing|source page]]. Some entries flag `vision` (multimodal image input), `BETA`, or `2x requests`.

`kimi-k2.5-lightning` reporting ~1890 t/s is the standout — that's roughly 10–25× the throughput of comparable Kimi K2 deployments at other providers, almost certainly via heavy [[speculative-decoding]] or batched draft tokens. The price ($1.00 / $3.00) reflects the speed tier.

## Plans

| Plan | Price | Daily requests | Notes |
|---|---|---|---|
| Free / PAYG | $0/mo | — | Token billing only |
| Hobby | $5/mo | 500 | All models |
| Pro | $10/mo | 1,000 | + Priority support |
| Intermediate | $20/mo | 2,500 | |
| Scale | $50/mo | 7,500 | |
| Max | $100/mo | 15,000 | |

The subscription tier is a daily-request quota at flat monthly cost — unusual for an LLM API provider, closer to a ChatGPT-style "$X/mo for N messages a day" model. PAYG sits alongside as the per-token alternative. Cost predictability is the obvious upside for high-volume small-prompt traffic (chatbots, classification); long-context workflows are worse off, since each request burns one quota slot regardless of size. The "precision" `2x requests` flag is the lever they use to keep heavyweight runs from exhausting low-tier quotas. What the page doesn't explain: whether token billing still applies inside the quota, what happens at overage, and whether the per-token rates change for subscribers versus PAYG.

## How it compares

CrofAI is closer to DeepInfra / Together / Fireworks (a direct host of open-weights models) than to [[toolbox/routing-run|routing.run]] / [[toolbox/gomodel|gomodel]] / [[toolbox/claude-code-router|claude-code-router]] (which route to other providers). It does not aggregate — the catalog is whatever ai.nahcrof.com physically runs.

The Q4_0 baseline is the catch. For coding-agent workloads where Q4_K_M is already considered the floor (see [[local-llm-16gb-vram-tests]] and [[habr-local-llm-quantization-deep-dive]]), Q4_0 may not match the quality you'd get from DeepSeek's own API at similar cost. For experimentation, vision, or low-cost batch work, the prices are genuinely low.

## Limitations / open questions

- Closed-source backend; quantization is disclosed but routing, batching, and KV-cache handling are not
- The `/pricing_api` endpoint requires auth — public pricing requires browser scrape
- No published track record, customer references, or uptime numbers on the marketing page
- Q4_0 quants on production models (especially MoE) may underperform what's advertised — see [[llm-quantization]]
- "Speed" numbers are throughput, not first-token latency
- No public docs page about API shape, auth, rate-limit headers (the pricing page links to a "Documentation" tab requiring sign-in)
- Single-domain operation (ai.nahcrof.com) — no public team, no SOC2 / privacy posture, no SLA

## Watchlist reason

On [[toolbox/watchlist]]: small provider with no observable track record, aggressive baseline quantization, single-domain operation. Re-check in 90 days for: third-party usage reports, sustained model catalog updates, whether quality complaints surface on Q4_0 baselines, and whether the "cheapest" pricing holds against DeepInfra / Fireworks / Together repricing rounds.

## Cross-references

- [[llm-quantization]] — why Q4_0 vs Q4_K_M is a real quality difference
- [[deepseek]] — three CrofAI models are DeepSeek-line (V4 Pro, V4 Flash, V3.2)
- [[mixture-of-experts]] — most catalog entries are MoE; quant sensitivity is worse for MoE
- [[speculative-decoding]] — likely mechanism behind the kimi-k2.5-lightning ~1890 t/s
- [[toolbox/routing-run|routing.run]] — different shape (router, not host)
- [[toolbox/gomodel|gomodel]] — gateway over many providers
- [[toolbox/claude-code-router|claude-code-router]] — could plausibly target CrofAI as one provider
- [[crofai-pricing]] — source snapshot