xAI Grok pricing for enrichment
All 5 xAI models OpenClay supports, listed most capable first, with what 1,000 enriched rows cost on each once search fees are included.
Updated August 2026
xAI · 5 models · keys start with xai-
Most capable
Grok 4.5
$6.34 per 1,000 rows
Lowest cost per row
Grok Build 0.1
$5.53 per 1,000 rows
How xAI bills web search
xAI does not publish a per-search rate for the server-side web search tool. OpenClay estimates $5 per 1,000 and labels it as an estimate everywhere it appears, rather than presenting a guess as a quoted price.
Worth knowing
Grok has the cheapest output tokens of any flagship-class model here, which matters when your output columns are verbose.
Every Grok model
| Model | Input | Output | Context | Per 1k rows |
|---|---|---|---|---|
Grok 4.5 grok-4.5 xAI's strongest model, with live X and web search | $2 | $6 | 500k | $6.34 |
Grok 4.3 grok-4.3 Cheapest output tokens of any flagship-class model here | $1.25 | $2.5 | 1000k | $5.66 |
Grok 4.20 (reasoning) grok-4.20-0309-reasoning Same price as non-reasoning, with step-by-step inference | $1.25 | $2.5 | 1000k | $5.66 |
Grok 4.20 (fast) grok-4.20-0309-non-reasoning Skips reasoning for lower latency on simple extractions | $1.25 | $2.5 | 1000k | $5.66 |
Grok Build 0.1 grok-build-0.1 Cheapest xAI option; smaller context window | $1 | $2 | 256k | $5.53 |
Using your xAI key
- Get a key from xAI Console. Keys start with
xai-. - Paste it into OpenClay. It stays in browser memory for the tab, never written to disk, a database, a log or a cookie.
- Test five rows for an exact per-row cost before running the batch.
- If you hit rate limits, lower the parallel-requests slider. Failed rows retry automatically with exponential backoff.
Compare against other providers
No account, no card, no platform fee.
Bring your own API key and pay the model provider directly.
Try Grok on your data