> Cerebras API
Cerebras Inference offers ultra-fast AI inference powered by its Wafer-Scale Engine (WSE-3) technology, achieving record-breaking speeds up to 3000 tokens/s. The official API is OpenAI-compatible and features a generous free tier alongside professional pay-as-you-go access.
// pros
- Custom hardware delivers extreme inference speed (~2600 tokens/sec measured on Llama 4 Scout)
- Free tier is instant, needs no credit card and no waitlist; 1M tokens/day is enough for prototyping
- Legitimate vendor with OpenAI-compatible /v1 endpoint; not a relay, no key-theft/downgrade risk
// cons
- Free tier rate limit is tight (30 RPM); fast inference easily bursts past it and hits 429
- Free-tier context is temporarily capped at 8,192 tokens, limiting long-document use
- The '1M tokens/day' is token-based; a single 128K prompt burns through it fast
- api.cerebras.ai is Cloudflare-protected (403); sign up at cloud.cerebras.ai to get a key
Worth using for speed-focused developers doing prototypes or small tools; watch concurrency and context length, and upgrade to paid for real high-concurrency production.
community_reputation
Cerebras has a positive reputation, widely recommended as a top free option for speed-critical use (alongside Groq); complaints center on the tight free-tier rate limit causing 429s on bursts.
imported analysis — independent third party, not Uprouter editorial · verify before relying on it
How we estimated this: the free allowance is converted to a dollar value using the provider’s own pay-as-you-go rates for the models a typical developer would reach for. When the allowance is metered in requests, tokens or minutes rather than dollars, we assume median usage of the cheapest capable model. Because assumptions are involved, the figure carries the est. flag — treat it as an order of magnitude, not a quote.
note: Free tier ≈1M tokens/day (resets UTC 00:00, no card, no waitlist) → ≈$30/mo blended at $1/1M; 8K context cap; RPM reported 5–30 by different sources. Paid dev tier from $10.
| Plan | Type | Monthly | Input /1M | Output /1M | Note |
|---|---|---|---|---|---|
| Free tier (source-reported) | free | — | — | — | Free tier: ~30 requests/minute, 1M tokens/day, context temporarily capped at 8,192 tokens; over-quota returns 429, resets at UTC 00:00. No credit card, no waitlist. |
| Free Tier | free | — | — | — | 1 million tokens daily; access to all models; community support. |
| Developer (PAYG) | payg | — | $0.100 | $0.100 | Llama 3.1 8B rate; self-serve payment starting at $10; higher priority. |
| Developer (PAYG) - Llama 70B | payg | — | $0.600 | $0.600 | Llama 3.3 70B rate. |
| Developer (PAYG) - GPT OSS | payg | — | $0.350 | $0.750 | GPT OSS 120B rate. |
Pricing normalized from public sources — always verify with the provider.
// model prices
| Model | Input /1M | Output /1M | Context |
|---|---|---|---|
| Llama 3.1/3.3 family | — | — | — |
| Qwen 3 family (per official model list) | — | — | — |
| Llama 4 Scout | — | — | 1.3M |
| gpt-oss-120b | — | — | 131k |
$ Does Cerebras API have a free tier?
Yes — Cerebras API offers a free tier that we value at roughly $30.00 in free credits (estimate — derived from rate-limited usage at pay-as-you-go prices). Always confirm current limits on Cerebras API's official pricing page — free tiers change without notice.
$ How much does Cerebras API cost per 1M tokens?
Cerebras API does not publish simple per-1M-token pricing (it may bill per request, per output, or via a subscription plan). Check their official pricing page for exact figures.
$ Is Cerebras API safe to use?
Uprouter rates Cerebras API as low risk. Rated low risk. an official provider with a free tier with pricing, authentication and terms documented on its own site. The model coverage is consistent with a real upstream, so data and reliability risk are modest. Risk ratings are editorial, evidence-based, and never influenced by affiliate relationships.
Raw community sentiment, shown unblended. Votes never feed into objective data fields like price, risk, or status — and never into sort order.
No published reviews yet — be the first.
// more_informationprice history · live status · risk & confidence · code snippets
price_history
No recorded changes yet.
live_status
full history →best-effort probes · not a guarantee · last 15h ago
| Checked | Status | Latency |
|---|---|---|
| 15h ago | up | 67ms |
| 1d ago | up | 40ms |
| 3d ago | up | 43ms |
| 4d ago | up | 64ms |
| 6d ago | up | 49ms |
| 7d ago | up | 44ms |
| 9d ago | up | 45ms |
| 11d ago | up | 103ms |
| 12d ago | up | 70ms |
| 13d ago | up | 41ms |
| 14d ago | up | 41ms |
| 15d ago | up | 58ms |
| 15d ago | up | 55ms |
| 16d ago | up | 39ms |
| 17d ago | up | 43ms |
| 18d ago | up | 38ms |
| 19d ago | up | 46ms |
| 19d ago | up | 33ms |
| 20d ago | up | 41ms |
| 21d ago | up | 42ms |
| 22d ago | up | 34ms |
| 22d ago | up | 52ms |
| 23d ago | up | 43ms |
| 24d ago | up | 42ms |
| 25d ago | up | 32ms |
| 26d ago | up | 72ms |
| 27d ago | up | 34ms |
| 27d ago | up | 55ms |
| 28d ago | up | 43ms |
| 29d ago | up | 72ms |
Uprouter runs its own probes; best-effort, not a guarantee. Probe results depend on our network location and cadence — for production, always use the provider’s own status page.
risk_&_confidence
Rated low risk. an official provider with a free tier with pricing, authentication and terms documented on its own site. The model coverage is consistent with a real upstream, so data and reliability risk are modest.
Confidence reflects how much verifiable evidence (official docs, probe history, community reports) backs this entry. Risk is our editorial assessment of operator reliability and terms — not financial advice.
code_snippets
# Cerebras API's own API — get a key from their dashboard
curl https://YOUR-PROVIDER-ENDPOINT/chat/completions \
-H "Authorization: Bearer THEIR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "llama-3-1-3-3-family",
"messages": [{ "role": "user", "content": "Hello" }]
}'Direct to the provider — Uprouter receives nothing; verify their current pricing before purchasing.
Ranked by neutral similarity signals only — live status, free-tier shape and free-credit proximity. Commercial relationships never influence this list.