Grok 4 Fast (Non-Reasoning)
View website
Non-reasoning mode of Grok 4 Fast, released September 2025. Unified weights with reasoning variant, prompt-steered for instant low-latency responses.
At a glance
- Context window
- 2M tokens
- Max output
- 2M tokens
- Modalities
- Text Text Image Image → Text Text
Capabilities
Structured output
Structured output
Return responses in structured formats like JSON.
Function calling
Function calling
Connect to external tools, APIs, and systems.
Pricing by provider
| Provider | Input / 1M tokens | Output / 1M tokens | |
|---|---|---|---|
|
xAI
|
$0.20 | $0.50 |
Heads up: We do our best to keep these specs & prices accurate. However, cloud costs may fluctuate based on region, usage, and other factors not listed here. These are estimates based on common setups and are for informational purposes only. Always verify current rates & exact specs with the provider before provisioning.
Compare with other models
Estimated prices shown. Actual costs may vary based on context length, batch size, caching, and provider-specific pricing tiers.