Cerebras Token Cost Calculator
Estimate Cerebras Shared Inference (PayGo) spend from model and input/output tokens. Rates match GET https://api.cerebras.ai/public/v1/models (pricing.prompt/completion × 1e6): gpt-oss-120b $0.35/$0.75, qwen-3.8-27b $0.99/$1.49 per 1M. Dedicated Inference is out of scope for v1. Estimates only; official Cerebras pricing prevails.
Math runs in your browser. Nothing is uploaded.
Input cost
—
Output cost
—
Estimated USD cost
—
Monthly USD
—
Estimates only; official vendor pricing prevails (2026-10-30). Shared PayGo: in÷1M×prompt + out÷1M×completion. From public models API: $0.35/$0.75 (gpt-oss-120b), $0.99/$1.49 (qwen-3.8-27b). Dedicated out of scope for v1.Official pricing: Cerebras pricing · public models API
Groq Token Cost Calculator · Fireworks Token Cost Calculator · Together AI Token Cost Calculator · SambaNova Cloud Cost Calculator
More in this group
- Groq Token Cost Calculator Groq tokens + optional Whisper hours.
- Fireworks Token Cost Calculator Fireworks in/cached/out + Standard/Priority/Batch.
- Together AI Token Cost Calculator Together serverless tokens + optional US-only.
- SambaNova Cloud Cost Calculator SambaNova Cloud in/cached/out tokens.
- LLM API Cost Calculator Generic token cost from any $/1M rates.
How it works
- How is Cerebras Shared Inference priced?
- USD = (input ÷ 1M × prompt $/1M) + (output ÷ 1M × completion $/1M). Rates verified from the public models API (USD/token × 1e6): gpt-oss-120b $0.35/$0.75, qwen-3.8-27b $0.99/$1.49.
- Is Dedicated included?
- No. Dedicated Inference is out of scope for v1 — contact Cerebras for dedicated pricing. This page covers Shared PayGo only.
- Are results invoices?
- No. Estimates only; cerebras.ai/pricing and the public models API prevail.
- Is any data uploaded?
- No. These calculators and QR codes run in your browser.
- Can these AI prices change?
- Yes. Vendors change list prices often. Edit the $/1M or plan fields, and confirm on the official pricing page before you budget.