Grok 4.20 0309 Reasoning
AvailableA dated reasoning model on the xAI API.
Access details: xAI API
A pinned version. Requests to this ID always get the same model.
grok-4.20-0309-reasoningUpdated Sep 23, 2026
Capabilities & limits
- Context window
- 1M
- Maximum output
- Not published
- Image input
- Supported
- Tool calling
- Supported
- Structured output
- Supported
Pricing
USD / 1M tokens- Input
- $1.25
- Output
- $2.50
Standard rates per million tokens. Discounts and long-context rates, where offered, are on xAI's pricing page.
Full rate card 6 rates
All prices in USD.
Short-context input
$1.25 USD per 1M tokens- prompt below 200k tokens
Short-context cache read
$0.20 USD per 1M tokens- prompt below 200k tokens
- cache hit
Short-context output
$2.50 USD per 1M tokens- prompt below 200k tokens
Long-context input
$2.50 USD per 1M tokens- prompt at or above 200k tokens
- rate applies to all tokens in request
Long-context cache read
$0.40 USD per 1M tokens- prompt at or above 200k tokens
- rate applies to all tokens in request
- cache hit
Long-context output
$5.00 USD per 1M tokens- prompt at or above 200k tokens
- rate applies to all tokens in request
Standard global Text API rates. Batch API requests are billed at a 20% discount to standard rates. Priority Processing is billed at 2x standard rates.
Price history
Sep 13, 2026
Input $1.25 per million tokens
Sep 13, 2026
Output $2.50 per million tokens
Technical details
- Parameters
- Not published
- Active parameters
- Not published
- Architecture
- Not published
- Training / knowledge cutoff
- Not published
- Input modalities
- Text, image
- Output modalities
- Text
Release & lifecycle
- First available
- —
- available
- As of Sep 13, 2026