SylphxModels

xAI

Grok family · v4.20

Grok 4.20

Retiring in 26d
x-ai/grok-4.20

Grok 4.20 on Sylphx Models · 2.0M of context. One Responses contract, with list prices published per million tokens.

Released
Mar 31, 2026 · 179 days old
Retires
Oct 21, 2026 · 26 days left
Provider
xAI
Context
2,000,000 tokens
Get an API keySee a request sampleRead the docs
Input $1.444 / MOutput $2.888 / MCached input $0.231 / MFull rate sheet
Context window2,000,000tokens per request
Max output1,800,000tokens per response
Input$1.444 / Mper million tokens
Output$2.888 / Mper million tokens
Cached input$0.231 / M84% off input
ReleasedMar 31, 2026179 days old

Pricing

USD per million tokens
Input
$1.444
Output
$2.888
Cached input
$0.231

$1.80 for 750,000 input and 250,000 output tokens.

Assumption: one batch of 750,000 input plus 250,000 output tokens at the published list prices — recompute for your own mix. Blended $1.805 per million at a 3:1 mix.

Chat replies · 3:1 input:output
$1.805 / M
Long documents · 9:1 input:output
$1.588 / M
Heavy output · 1:1 input:output
$2.166 / M
Cache write
$1.444 / M
Currency and unit
USD / million tokens

Cached input reads cost 84% less than fresh input tokens.

Full rate sheet and billing rules.

Specification

Context window
2,000,000 tokens
Max output
1,800,000 tokens
Input modalities
Not published
Output modalities
Not published
Family
Grok
Version
v4.20
Provider
xAI
Released
Mar 31, 2026 · 179 days old
Model id
x-ai/grok-4.20

Data posture

Standard

By default, prompts and outputs sent to this model are not used to train models.

Training on what you send · default
No
Zero Data Retention · default
Yes
curl https://api.sylphx.ai/v1/responses \
  -H "Authorization: Bearer $SYLPHX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "x-ai/grok-4.20",
    "input": "Summarise this incident report in three bullets.",
    "stream": false
  }'

How to call it

Send the official Responses document to the base URL above with your Sylphx API key and this exact model id. Streaming arrives as ordered events with one terminal event.

  • Retries: send an Idempotency-Key and a retry replays the original response instead of billing twice.
  • Errors: typed envelopes tell you whether to retry, wait, or fix the request.
  • Keys: create and revoke Sylphx API keys in the Sylphx console.
QuickstartResponses APIErrors and retries

Related models

Derived from this catalog: same provider first, then the same family, then the nearest neighbours by input price and context window.

More from xAI

Same provider

Elsewhere in Grok

Same family slug

Similar price and context

Nearest by input price and context window

Independent evaluation

We do not publish benchmark scores for this model — we have not verified any. These external leaderboards run their own tests, so check them against your own workload.

Not our numbers
Every xAI model →