7
Models Available
$0.10
Cheapest Input / 1M
131K
Largest Context
What is Cerebras?
Cerebras is an AI model provider offering 7 large language models for developers. Their cheapest model starts at $0.10 per 1M input tokens, and their largest context window reaches 131K. Cerebras provides 7 AI models accessible via API.
Cerebras Strengths
All Cerebras Models
| Model | Input $/1M | Output $/1M | Context | Max Output | Released |
|---|---|---|---|---|---|
| Llama3.1 8b | $0.10 | $0.10 | 128K | 128,000 | — |
| Gpt Oss 120b | $0.35 | $0.75 | 131K | 32,768 | — |
| Qwen 3 32b | $0.40 | $0.80 | 128K | 128,000 | — |
| Llama3.1 70b | $0.60 | $0.60 | 128K | 128,000 | — |
| Llama 3.3 70b | $0.85 | $1.20 | 128K | 128,000 | — |
| Zai Glm 4.6 | $2.25 | $2.75 | 128K | 128,000 | — |
| Zai Glm 4.7 | $2.25 | $2.75 | 128K | 128,000 | — |
Model Details
Llama3.1 8b
Llama3.1 8b is available via Cerebras with a 128K context window and up to 128,000 output tokens. Pricing: $0.1000/1M input tokens, $0.1000/1M output tokens.
Gpt Oss 120b
Gpt Oss 120b is available via Cerebras with a 131K context window and up to 32,768 output tokens. Pricing: $0.3500/1M input tokens, $0.7500/1M output tokens.
Qwen 3 32b
Qwen 3 32b is available via Cerebras with a 128K context window and up to 128,000 output tokens. Pricing: $0.4000/1M input tokens, $0.8000/1M output tokens.
Llama3.1 70b
Llama3.1 70b is available via Cerebras with a 128K context window and up to 128,000 output tokens. Pricing: $0.6000/1M input tokens, $0.6000/1M output tokens.
Llama 3.3 70b
Llama 3.3 70b is available via Cerebras with a 128K context window and up to 128,000 output tokens. Pricing: $0.8500/1M input tokens, $1.20/1M output tokens.
Zai Glm 4.6
Zai Glm 4.6 is available via Cerebras with a 128K context window and up to 128,000 output tokens. Pricing: $2.25/1M input tokens, $2.75/1M output tokens.
Zai Glm 4.7
Zai Glm 4.7 is available via Cerebras with a 128K context window and up to 128,000 output tokens. Pricing: $2.25/1M input tokens, $2.75/1M output tokens.
Compare Cerebras model pricing
Use our pricing calculator to find the cheapest Cerebras model for your workload.