Grok 4 Fast Models: Flagship and Fast Variants Now Available
Added support for Grok 4 Fast Reasoning, and Grok 4 Fast Non-Reasoning models via xAI provider.
We're excited to announce support for the latest Grok 4 Fast models through our xAI provider.
⚡ New Model: Grok 4 Fast Reasoning
Optimized for fast reasoning tasks with excellent performance:
Model Identifiers:
Context Window: 256K tokens
Max Output: 256K tokens
Pricing:
We're working on dynamic pricing, so these will be the prices by then:
- Input tokens (<128k): $0.20 per 1M tokens
- Input tokens (≥128k): $0.40 per 1M tokens
- Output tokens (<128k): $0.50 per 1M tokens
- Output tokens (≥128k): $1.00 per 1M tokens
- Cached input tokens: $0.05 per 1M tokens
Features: Vision support, streaming, tool usage, JSON output
Ideal for applications requiring quick reasoning with cost efficiency.
🔥 New Model: Grok 4 Fast Non-Reasoning
High-speed model optimized for general tasks without complex reasoning:
Model Identifiers:
Context Window: 256K tokens
Max Output: 256K tokens
Pricing:
We're working on dynamic pricing, so these will be the prices by then:
- Input tokens (<128k): $0.20 per 1M tokens
- Input tokens (≥128k): $0.40 per 1M tokens
- Output tokens (<128k): $0.50 per 1M tokens
- Output tokens (≥128k): $1.00 per 1M tokens
- Cached input tokens: $0.05 per 1M tokens
Features: Vision support, streaming, tool usage, JSON output
Perfect for fast responses and general tasks where reasoning complexity is not required.