Cerebras

Cerebras

static

Access Cerebras models through Everstack's OpenAI-compatible gateway with routing, fallback, retries, and observability.

https://api.cerebras.ai/v1
Models
9
Max context
131.1K
Input range
$0.10 - $2.25
Discovery
static

Activity

Managed-cloud usage across this serving provider.

Daily period usage
Aggregated managed Everstack traffic. Buckets below 5 tenants or 100 requests are withheld.

Cerebras models

9 shown
Cerebras: Gemma 4 31B ITbeta

Gemma 4 31B IT supports Chat, Function Calling, Vision, Reasoning workloads through Everstack.

by cerebrasApr 2, 2026131.1K context$0.99 input$1.49 output
ChatFunction CallingVision
Cerebras: Z.AI GLM-4.7stable

Z.AI GLM-4.7 supports Chat, Function Calling workloads through Everstack.

by cerebrasJan 7, 2026131.1K context$2.25 input$2.75 output
ChatFunction Calling
Cerebras: GPT OSS 120Bstable

GPT OSS 120B supports Chat, Function Calling, Reasoning workloads through Everstack.

by cerebrasAug 5, 2025131.1K context$0.35 input$0.75 output
ChatFunction CallingReasoning
Cerebras: DeepSeek R1 Distill Llama 70Bdeprecated

DeepSeek R1 Distill Llama 70B supports Chat, Function Calling workloads through Everstack.

by cerebras131.1K context$0.80 input$1.00 output
ChatFunction Calling
Cerebras: Llama 3.1 8Bstable

Llama 3.1 8B supports Chat, Function Calling workloads through Everstack.

by cerebras32K context$0.10 input$0.10 output
ChatFunction Calling
Cerebras: Llama 3.3 70Bdeprecated

Llama 3.3 70B supports Chat, Function Calling workloads through Everstack.

by cerebras131.1K context$0.60 input$0.80 output
ChatFunction Calling
Cerebras: Llama 4 Scout 17B 16E Instructdeprecated

Llama 4 Scout 17B 16E Instruct supports Chat, Function Calling workloads through Everstack.

by cerebras128K context$0.80 input$1.20 output
ChatFunction Calling
Cerebras: Qwen 3 235B Instructstable

Qwen 3 235B Instruct supports Chat, Function Calling workloads through Everstack.

by cerebras131K context$0.60 input$1.20 output
ChatFunction Calling
Cerebras: Qwen 3 32Bdeprecated

Qwen 3 32B supports Chat, Function Calling workloads through Everstack.

by cerebras131.1K context$0.50 input$0.70 output
ChatFunction Calling