OpenModelsHQ

Cerebras

Cerebras serves 2 open models from 2 labs on OpenRouter, in 2 offers. Of the 2 models it shares with other providers, it has the lowest blended price on 0. Its median blended price is $0.7825 (₹74) per million tokens, blended 3:1 input to output. Its most common precision is 16-bit (2 of 2 offers).

Models served
2
2 labs · 2 offers
Median blended / 1M
$0.7825
₹74 · 3:1 input to output
Lowest price, shared models
0%
0 of 2
Max context
131,072
16-bit 2

Company and policies

Headquarters listed by OpenRouter
United States
Datacenter countries listed by OpenRouter
Not listed

Provider-level locations do not guarantee where a particular request is processed. Check the provider's terms for data handling. Directory source, checked 14 Nov 2026.

Precision and price rank

Precision mix
Precision as the provider lists it on OpenRouter. 4-bit covers FP4, NVFP4, MXFP4 and INT4; 16-bit covers BF16 and FP16.
Precision mix: data
Offers16-bitTotal
Offers22
Price rank on shared models
One entry per model that two or more providers serve, using Cerebras's cheapest offer. A tie for the lowest price counts as lowest.
Price rank on shared models: data
RankModels
Lowest or tied0
2nd0
3rd0
4th or lower2

Every model Cerebras serves 2

USD and INR per million tokens
PrecisionLabPricing
$0.45₹42$0.35₹33$0.75₹7122 of 22131,072FP16OpenAIAll providers
$1.115₹105$0.99₹93$1.49₹14020 of 2365,536FP16Alibaba QwenAll providers
Rank is this offer's position among the model's providers by blended price (3 parts input to 1 part output). 1 is the lowest. Equal prices are ordered by provider name and marked "Ties for lowest".

Where Cerebras is cheapest

0 of 2 models shared with other providers

Cerebras does not have the lowest blended price on any model that other providers also serve.

Cerebras questions

Which open models does Cerebras serve?

Cerebras serves 2 open models from 2 labs on OpenRouter. The most downloaded on Hugging Face are Qwen3.8-27B and gpt-oss-120b. Prices were fetched 14 Nov 2026.

Is Cerebras the cheapest provider for any open model?

No. Its best position is 20th of 23 providers, for Qwen3.8-27B at $1.115 (₹105) per million tokens, blended 3:1 input to output.

What precision does Cerebras serve models at?

Of its 2 offers, Cerebras lists 16-bit for 2. Prices are in US dollars; we show rupees at ₹94.29 per $1.

About this data

Every number on this page comes from the endpoints OpenRouter lists for each model, fetched 14 Nov 2026. INR is shown beside USD at ₹94.29 per $1. Prices change, so check the provider before you build on a number.