Provider
Cerebras
Use this page to inspect prices within one provider and, when reviewed route identity exists, compare the same model across other providers.
Listed models 7
Chat
Chat models 7
Rows with mode=chat
Lowest input $0.1000 / 1M tokens
Vs global median: 0.2x
Lowest output $0.1000 / 1M tokens
Vs global median: 0.1x
Model pricing
4 rows include direct source URLs. Real invoices can still vary by discounts, regions, and cache rules.
| Model | Mode | Input | Output | Context | Other routes | Lowest elsewhere |
|---|---|---|---|---|---|---|
| gpt-oss-120b Source linked | Chat | $0.3500 / 1M tokens | $0.7500 / 1M tokens | 32.8K | N/A | N/A |
| llama-3.3-70b No direct source | Chat | $0.8500 / 1M tokens | $1.2000 / 1M tokens | 128.0K | N/A | N/A |
| llama3.1-70b No direct source | Chat | $0.6000 / 1M tokens | $0.6000 / 1M tokens | 128.0K | N/A | N/A |
| llama3.1-8b No direct source | Chat | $0.1000 / 1M tokens | $0.1000 / 1M tokens | 128.0K | N/A | N/A |
| qwen-3-32b Source linked | Chat | $0.4000 / 1M tokens | $0.8000 / 1M tokens | 128.0K | N/A | N/A |
| zai-glm-4.6 Source linked | Chat | $2.2500 / 1M tokens | $2.7500 / 1M tokens | 128.0K | N/A | N/A |
| zai-glm-4.7 Source linked | Chat | $2.2500 / 1M tokens | $2.7500 / 1M tokens | 128.0K | N/A | N/A |