Back to Models
Grok 4.20
xaixai/grok-4.20-non-reasoning
How TheRouter serves this differently from the vendor
As the vendor operates it
xAI exposes grok-4.20-0309-non-reasoning as a native xAI API model with xAI pricing tiers, xAI rate limits, and the documented caveat that logprobs/top_logprobs are silently ignored for Grok 4.20 and newer.
On TheRouter
TheRouter serves the pinned xai/grok-4.20-non-reasoning route through its OpenAI-compatible chat endpoint with TheRouter pricing and routing metadata; unsupported media-generation, audio, and embeddings endpoints are not exposed for this model.
API guide
Chat completion
cURL
curl https://api.therouter.ai/v1/chat/completions \
-H "Authorization: Bearer $THEROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "xai/grok-4.20-non-reasoning",
"messages": [{"role": "user", "content": "Summarise the key points in the following document:"}]
}'Function calling
cURL
curl https://api.therouter.ai/v1/chat/completions \
-H "Authorization: Bearer $THEROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "xai/grok-4.20-non-reasoning",
"messages": [{"role": "user", "content": "Look up the order status for order #12345."}],
"tools": [{"type": "function", "function": {"name": "get_order_status", "description": "Get order status by ID", "parameters": {"type": "object", "properties": {"order_id": {"type": "string"}}, "required": ["order_id"]}}}],
"tool_choice": "auto"
}'Vision β image + text
cURL
curl https://api.therouter.ai/v1/chat/completions \
-H "Authorization: Bearer $THEROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "xai/grok-4.20-non-reasoning",
"messages": [{
"role": "user",
"content": [
{"type": "image_url", "image_url": {"url": "https://therouter.ai/assets/vision-sample.png"}},
{"type": "text", "text": "Extract all line items from this invoice as JSON."}
]
}]
}'Fact ledger β every claim on this page traces here
| source | URL | retrieved | |
|---|---|---|---|
| Release date (public API) | β | β | unknown |
| API model slug (pinned) | docs.x.ai β | 2026-06-09 | verified |
| Reasoning mode | β | β | verified |
| Context window | docs.x.ai β | 2026-06-09 | verified |
| Max completion tokens | β | β | verified |
| Input modalities | docs.x.ai β | 2026-06-09 | verified |
| Output modalities | β | β | verified |
| xAI API pricing (current) | docs.x.ai β | 2026-06-09 | verified |
| Function calling / tools | β | β | verified |
| Structured outputs (response_format) | β | β | verified |
| logprobs / top_logprobs | docs.x.ai β | 2026-06-09 | verified |
| Knowledge cutoff | β | β | unknown |
| License | β | β | verified |
| Rate limits (xAI API) | docs.x.ai β | 2026-06-09 | verified |
| AA Intelligence Index | docs.x.ai β | 2026-08-01 | unknown |
| AA Coding Index | docs.x.ai β | 2026-08-01 | unknown |
| AA Agentic Index | docs.x.ai β | 2026-08-01 | unknown |
| GPQA Diamond | docs.x.ai β | 2026-08-01 | unknown |
| HLE (Humanity's Last Exam) | docs.x.ai β | 2026-08-01 | unknown |
| SciCode | docs.x.ai β | 2026-08-01 | unknown |
| ΟΒ²-Bench (Telecom) | docs.x.ai β | 2026-08-01 | unknown |
| IFBench (Instruction Following) | docs.x.ai β | 2026-08-01 | unknown |
| AA-LCR (Long-Context Reasoning) | docs.x.ai β | 2026-08-01 | unknown |
| TerminalBench Hard | docs.x.ai β | 2026-08-01 | unknown |
| Grok 4.20 Beta launches with four API variants including non-reasoning mode | grokipedia.com β | 2026-06-09 | verified |