Grok 4.20 (Non-Reasoning)
azure/grok-4-20-non-reasoning · family grok · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools text.
$3.00
Blended $/1M (3:1)
$2
Input $/1M
$6
Output $/1M
$8.00
1M in + 1M out
—
Cache read $/1M
#5662 of 7,708
Cheapest rank
- Provider
- Azure (
azure) - Kind
- text (outputs text)
- Context
- 262,000 tokens
- Max output
- 8,192 tokens
- Capabilities
- tools text
Same model, other providers
“Grok 4.20 (Non-Reasoning)” is offered by 8 providers — cheapest-effective first. Impossibl is the cheapest at $1.56 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Impossibl | $1.25 | $2.5 | $1.56 | 1M |
| OCI Generative AI | $1.25 | $2.5 | $1.56 | 1M |
| xAI | $1.25 | $2.5 | $1.56 | 1M |
| Eden AI | $1.25 | $2.5 | $1.56 | 1M |
| DevPass (LLM Gateway) | $1.25 | $2.5 | $1.56 | 2M |
| Vertex | $1.25 | $2.5 | $1.56 | 2M |
| Azure (this) | $2 | $6 | $3.00 | 262k |
| Cloudflare AI Gateway | $2 | $6 | $3.00 | 2M |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Azure and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"grok-4-20-non-reasoning","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):