Grok-4-Fast-Non-Reasoning
poe/xai/grok-4-fast-non-reasoning · family grok · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools text image.
$0.28
Blended $/1M (3:1)
$0.2
Input $/1M
$0.5
Output $/1M
$0.70
1M in + 1M out
$0.05 −75%
Cache read $/1M
#2132 of 7,712
Cheapest rank
- Provider
- Poe (
poe) - Kind
- text (outputs text)
- Context
- 2,000,000 tokens
- Max output
- 128,000 tokens
- Capabilities
- tools text image
Same model, other providers
“Grok-4-Fast-Non-Reasoning” is offered by 3 providers — cheapest-effective first. Jiekou.AI is the cheapest at $0.25 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Jiekou.AI | $0.18 | $0.45 | $0.25 | 2M |
| Poe (this) | $0.2 | $0.5 | $0.28 | 2M |
| 302.AI | $0.2 | $0.5 | $0.28 | 2M |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Poe and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"xai/grok-4-fast-non-reasoning","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):