Grok 4.20 Multi-Agent
nano-gpt/x-ai/grok-4.20-multi-agent · family grok · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image.
$3.00
Blended $/1M (3:1)
$2
Input $/1M
$6
Output $/1M
$8.00
1M in + 1M out
$1 −50%
Cache read $/1M
#5671 of 7,708
Cheapest rank
- Provider
- NanoGPT (
nano-gpt) - Kind
- text (outputs text)
- Context
- 2,000,000 tokens
- Max output
- 131,072 tokens
- Capabilities
- tools reasoning text image
Same model, other providers
“Grok 4.20 Multi-Agent” is offered by 5 providers — cheapest-effective first. OpenRouter is the cheapest at $1.56 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| OpenRouter | $1.25 | $2.5 | $1.56 | 2M |
| xAI | $1.25 | $2.5 | $1.56 | 1M |
| Vercel AI Gateway | $1.25 | $2.5 | $1.56 | 2M |
| Venice AI | $1.42 | $2.83 | $1.77 | 2M |
| NanoGPT (this) | $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 NanoGPT and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"x-ai/grok-4.20-multi-agent","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):