AI API price index · open-model host · read 17 Nov 2026
Cerebras API pricing
3 prices as Cerebras publishes them — 2 text models, 1 plans — read on its own pricing page on 17 Nov 2026. Its current text models cost $0.75 to $1.49 per million output tokens.
Free tier Developer tier: "Self-serve pay-as-you-go with free $5 credit to start". Add a valid payment method to receive "a one-time $5 promotional credit. The credit expires 30 days after activation. You will not be charged or automatically enrolled in paid usage." Access pauses when it expires or runs out unless you buy PayGo credits.
What to know before you build on Cerebras
- Only two models have a public price, both on the Developer tier: GPT OSS 120B at $0.35 in and $0.75 out per 1M tokens, and Qwen 3.8 27B at $0.99 and $1.49.
- Cerebras says the Developer tier is "for development, evaluation, and experimentation; not intended for production use". Production runs on the Enterprise tier, priced by quote.
- Speeds it states: about 3,000 tokens a second on GPT OSS 120B and about 1,850 on Qwen 3.8 27B.
- A new account gets a one-time $5 credit after adding a payment method; it expires 30 days after activation.
- Other model families are available only through Dedicated Inference, with no public price.
Against the other 31
Across the index, 390 current text models run from $0.03 to $50.00 per million output tokens — 1667×. Cerebras’s cheapest, GPT OSS 120B at $0.75, has 133 cheaper text models elsewhere; its dearest, Qwen 3.8 27B, costs $1.49. A cheaper model is a different model, not the same one for less — compare capability before price.
The same model elsewhere
Open-weight models Cerebras sells that other hosts price too — the only like-for-like comparison in the index.
- gpt-oss-120b — Novita AI $0.05 / $0.25 · Google Vertex AI (Agent Platform) $0.09 / $0.36 · SambaNova Cloud $0.22 / $0.59 · Amazon Bedrock $0.15 / $0.60 · Fireworks AI $0.15 / $0.60 · Groq $0.15 / $0.60 · Nebius Token Factory $0.15 / $0.60 · Together AI $0.15 / $0.60 · Cerebras $0.35 / $0.75 · Cloudflare Workers AI $0.35 / $0.75 — 3.0× apart
- Qwen3.8 27B — Cerebras $0.99 / $1.49 · DeepInfra $0.20 / $2.50 · Alibaba Cloud Model Studio (Qwen) $0.50 / $3.00 · Nebius Token Factory $0.45 / $3.00 · Novita AI $0.42 / $3.00 · Cloudflare Workers AI $0.45 / $3.20 · Groq $0.80 / $4.00 — 2.7× apart
Input / output per 1M tokens, standard tier.
Text models
| Model | Input | Cached input | Output | Note |
|---|---|---|---|---|
| GPT OSS 120Bdeveloper | $0.35 | — | $0.75 | Developer tier: "For development, evaluation, and experimentation; not intended for production use." About 3,000 tokens a second; context 65k on the free trial, 131k paid |
| Qwen 3.8 27Bdeveloper | $0.99 | — | $1.49 | Developer tier: "For development, evaluation, and experimentation; not intended for production use." About 1,850 tokens a second; context 64k free, 128k paid |
Plans
| Model | Price | Note |
|---|---|---|
| Enterprisecustom | — | Production workloads, all supported models: Contact us for a quote |
2 of these 3 prices are ranked in the index; the rest say why in their note. Text and embeddings per 1M tokens unless the row says otherwise.
Discounts and surcharges, as published
- Enterprise tier: "Contact us for a quote" — production capacity, priority, higher rate limits and lower-latency options; custom weights, fine-tuning and training "available by agreement".
Where these numbers come from
Read on cerebras.ai/pricing on 17 Nov 2026, checked against 1 more of Cerebras’s own pages. Macrostack measures nothing and is paid by no provider on this index. Prices change; the date is the claim.
The other providers in the index
- The AI API price index — every provider, cheapest first, and the download
- Free LLM APIs — which providers let you use a model free, and the catch with each
- OpenAI API pricing — model maker
- Anthropic API pricing — model maker
- Google Gemini API pricing — model maker
- Mistral AI API pricing — model maker
- Cohere API pricing — model maker
- Groq API pricing — open-model host
- Together AI API pricing — open-model host
- Fireworks AI API pricing — open-model host
- Replicate API pricing — open-model host
- Deepgram API pricing — voice
- ElevenLabs API pricing — voice
- DeepSeek API pricing — model maker
- xAI API pricing — model maker
- Azure OpenAI API pricing — cloud platform
- Amazon Bedrock API pricing — cloud platform
- Voyage AI API pricing — model maker
- AssemblyAI API pricing — voice
- Speechmatics API pricing — voice
- Cartesia API pricing — voice
- MiniMax API pricing — model maker
- Z.ai API pricing — model maker
- Novita AI API pricing — open-model host
- Moonshot AI (Kimi) API pricing — model maker
- Alibaba Cloud Model Studio (Qwen) API pricing — model maker
- Perplexity API pricing — model maker
- DeepInfra API pricing — open-model host
- Cloudflare Workers AI API pricing — open-model host
- Nebius Token Factory API pricing — open-model host
- SambaNova Cloud API pricing — open-model host
- Google Vertex AI (Agent Platform) API pricing — cloud platform
- Azure AI Foundry Models API pricing — cloud platform
Questions
- How much does the Cerebras API cost?
- On 17 Nov 2026, Cerebras's current text models cost $0.75 to $1.49 per million output tokens at the standard tier (GPT OSS 120B to Qwen 3.8 27B). The full list, with input and cached-input prices, is on this page.
- Does Cerebras have a free tier?
- What Cerebras's own pages say: Developer tier: "Self-serve pay-as-you-go with free $5 credit to start". Add a valid payment method to receive "a one-time $5 promotional credit. The credit expires 30 days after activation. You will not be charged or automatically enrolled in paid usage." Access pauses when it expires or runs out unless you buy PayGo credits.
- Does Cerebras offer discounts?
- Enterprise tier: "Contact us for a quote" — production capacity, priority, higher rate limits and lower-latency options; custom weights, fine-tuning and training "available by agreement".