← Back to all models

Grok 3 Mini Beta

grok-3-mini

xAI's lightweight model that thinks before responding. Great for simple or logic-based tasks that do not require deep domain knowledge. The raw thinking traces are accessible.

Available at 9 Providers

Provider Source Input Price ($/1M) Output Price ($/1M) Description Free
vercel vercel Input: $0.30 Output: $0.50 xAI's lightweight model that thinks before responding. Great for simple or logic-based tasks that do not require deep domain knowledge. The raw thinking traces are accessible.
poe poe Input: - Output: - xAI's February 2025 release with strong performance across many domains but at a more affordable price point. Supports reasoning with a configurable reasoning effort level, and 131k tokens of context; doesn't have access to the X data feed. To instruct the bot to use more reasoning effort, add --reasoning_effort to the end of your message with one of "low" or "high".
xai models-dev Input: $0.30 Output: $0.50 Provider: xAI, Context: 131072, Output Limit: 8192
githubmodels models-dev Input: $0.00 Output: $0.00 Provider: GitHub Models, Context: 128000, Output Limit: 8192
azure models-dev Input: $0.30 Output: $0.50 Provider: Azure, Context: 131072, Output Limit: 8192
helicone models-dev Input: $0.30 Output: $0.50 Provider: Helicone, Context: 131072, Output Limit: 131072
azurecognitiveservices models-dev Input: $0.30 Output: $0.50 Provider: Azure Cognitive Services, Context: 131072, Output Limit: 8192
azureai litellm Input: $0.25 Output: $1.27 Source: azure_ai, Context: 131072
openrouter openrouter Input: $0.30 Output: $0.50 A lightweight model that thinks before responding. Fast, smart, and great for logic-based tasks that do not require deep domain knowledge. The raw thinking traces are accessible. Context: 131072