Grok 4.7
steadyrouter/grok-4.7 · family grok · in: text, image, pdf → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image pdf.
This is a text model — providers price it per unit, not per token, so models.dev carries no token price (fields read “—”). See SteadyRouter’s docs for per-unit rates.
- Provider
- SteadyRouter (
steadyrouter) - Kind
- text (outputs text)
- Context
- 500,000 tokens
- Max output
- 500,000 tokens
- Capabilities
- tools reasoning text image pdf
Same model, other providers
“Grok 4.7” is offered by 32 providers — cheapest-effective first. cheapaimodel is the cheapest at $0.30 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| cheapaimodel | $0.1996 | $0.5988 | $0.30 | 500k |
| AIGROW | $0.5 | $1.5 | $0.75 | 500k |
| JZSTOKEN | $0.3892 | $1.95 | $0.78 | 500k |
| Prime Inference | $1.6 | $4.8 | $2.40 | 500k |
| CheapestToken | $2 | $4.5 | $2.63 | 500k |
| NanoGPT | $2 | $6 | $3.00 | 500k |
| 302.AI | $2 | $6 | $3.00 | 500k |
| Cloudflare AI Gateway | $2 | $6 | $3.00 | 500k |
| OpenRouter | $2 | $6 | $3.00 | 500k |
| Merge Gateway | $2 | $6 | $3.00 | 500k |
| xAI | $2 | $6 | $3.00 | 500k |
| Vercel AI Gateway | $2 | $6 | $3.00 | 500k |
| SteadyRouter (this) | — | — | — | 500k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at SteadyRouter and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"grok-4.7","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):