Grok 4.6
azure/grok-4.6 · family grok · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image.
This is a text model — providers price it per unit, not per token, so models.dev carries no token price (fields read “—”). See Azure’s docs for per-unit rates.
- Provider
- Azure (
azure) - Kind
- text (outputs text)
- Context
- 200,000 tokens
- Max output
- 128,000 tokens
- Capabilities
- tools reasoning text image
Same model, other providers
“Grok 4.6” is offered by 29 providers — cheapest-effective first. Kenari is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Kenari | free | free | $0.00 | 500k |
| Perplexity Agent | $2 | $6 | $3.00 | 500k |
| NanoGPT | $2 | $6 | $3.00 | 500k |
| Kilo Gateway | $2 | $6 | $3.00 | 500k |
| Abacus | $2 | $6 | $3.00 | 500k |
| 302.AI | $2 | $6 | $3.00 | 500k |
| OpenRouter | $2 | $6 | $3.00 | 500k |
| ZenMux | $2 | $6 | $3.00 | 500k |
| OCI Generative AI | $2 | $6 | $3.00 | 500k |
| Cloudflare AI Gateway | $2 | $6 | $3.00 | 500k |
| xAI | $2 | $6 | $3.00 | 500k |
| Vercel AI Gateway | $2 | $6 | $3.00 | 500k |
| Azure (this) | — | — | — | 200k |
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-4.6","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):