Grok Code Fast 1
poe/xai/grok-code-fast-1 · family grok · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$0.53
Blended $/1M (3:1)
$0.2
Input $/1M
$1.5
Output $/1M
$1.70
1M in + 1M out
$0.02 −90%
Cache read $/1M
#3018 of 7,708
Cheapest rank
- Provider
- Poe (
poe) - Kind
- text (outputs text)
- Context
- 256,000 tokens
- Max output
- 128,000 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“Grok Code Fast 1” is offered by 3 providers — cheapest-effective first. OpenCode Zen is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| OpenCode Zen | free | free | $0.00 | 256k |
| Poe (this) | $0.2 | $1.5 | $0.53 | 256k |
| Abacus | $0.2 | $1.5 | $0.53 | 256k |
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-code-fast-1","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):