> Cerebras
Cerebras Inference serves open-weight models on wafer-scale CS-4 hardware — gpt-oss-120b at ~3,000 tokens/s for $0.35/$0.75 per 1M in/out, Qwen 3.8 27B at $0.99/$1.49. The self-serve developer tier is pay-as-you-go with $5 of free credit to start; the enterprise tier (production capacity, priority limits, fine-tuning) is quote-based. Also available via AWS Marketplace, OpenRouter, Hugging Face and Vercel.
// pros
- Wafer-scale CS-4 hardware delivers among the fastest open-model inference available — ~3,000 tokens/s on gpt-oss-120b.
- Self-serve developer tier: pay-as-you-go with $5 free credit to start, no contract.
- Aggressive per-token pricing: gpt-oss-120b $0.35 in / $0.75 out per 1M; Qwen 3.8 27B $0.99 / $1.49.
- Reachable through existing billing relationships — AWS Marketplace, OpenRouter, Hugging Face and Vercel all front Cerebras endpoints.
- Enterprise tier adds production-ready capacity, priority rate limits, custom weights and fine-tuning services.
// cons
- The developer catalog is tiny — effectively gpt-oss-120b and Qwen 3.8 27B; it's a speed showcase as much as a platform.
- The published free grant is $5; larger figures from older posts no longer match the current pricing page.
- Production capacity, priority limits and fine-tuning are quote-only — there is no self-serve path to production SLAs.
- The lineup churns (the tier table and pricing table currently list different models) — verify the current catalog before integrating.
A tool for a specific job: if you need the lowest latency on gpt-oss-120b or Qwen 3.8 27B, this is where it is. Don't build a general stack on it — pair it with a broader provider for everything else.
written by Mike Fleming, Uprouter editorial · verified against official sources September 16, 2026
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: Self-serve developer tier includes $5 free credit to start (pricing page, checked 2026-09-16). Replaces an older $30 figure that no longer matches the official page.
| Plan | Type | Monthly | Input /1M | Output /1M | Note |
|---|---|---|---|---|---|
| Free tier (source-reported) | free | — | — | — | Free developer tier: 1 million tokens per day (resets daily, not a one-time credit), no credit card, rate limits around 30 RPM / 60K TPM, with the free-tier context once capped near 8K; register at cloud.cerebras.ai to generate an API key. Beyond that it becomes paid pay-as-you-go. |
| Free tier | free | — | Free | Free | 1M tokens/day, no card |
| Subscription | subscription | — | $0.850 | $1.20 | llama-3.3-70b; higher limits |
| GPT OSS 120B | payg | — | $0.350 | $0.750 | — |
Pricing normalized from public sources — always verify with the provider.
// model prices
| Model | Input /1M | Output /1M | Context |
|---|---|---|---|
| gpt-oss-120b | — | — | 131k |
| Qwen3 32B | — | — | 131k |
| Llama 4 Scout | — | — | 1.3M |
| zai-glm-4.7 | — | — | 205k |
$ Does Cerebras have a free tier?
Yes — Cerebras offers a free tier that we value at roughly $5.00 in free credits (estimate — derived from rate-limited usage at pay-as-you-go prices). Always confirm current limits on Cerebras's official pricing page — free tiers change without notice.
$ How much does Cerebras cost per 1M tokens?
Cerebras 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 safe to use?
Uprouter rates Cerebras as low risk. Low risk: first-party API from a named infrastructure company with published developer pricing, a public status page and a trust center. The commercial risk is the thin free tier — $5 of credit and a two-model developer catalog — so its free value is a speed benchmark, not sustained free workload. 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
current: upNo probes recorded yet.
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
Low risk: first-party API from a named infrastructure company with published developer pricing, a public status page and a trust center. The commercial risk is the thin free tier — $5 of credit and a two-model developer catalog — so its free value is a speed benchmark, not sustained free workload.
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'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": "gpt-oss-120b",
"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.