Ox Alpha
nano-gpt/stealth/ox-alpha · family alpha · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image.
$0.05
Blended $/1M (3:1)
$0.05
Input $/1M
$0.05
Output $/1M
$0.10
1M in + 1M out
$0.025 −50%
Cache read $/1M
#587 of 6,782
Cheapest rank
- Provider
- NanoGPT (
nano-gpt) - Kind
- text (outputs text)
- Context
- 1,000,000 tokens
- Max output
- 32,768 tokens
- Capabilities
- tools reasoning text image
Same model, other providers
“Ox Alpha” is offered by 4 providers — cheapest-effective first. OpenRouter is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| OpenRouter | free | free | $0.00 | 1M |
| Kilo Gateway | free | free | $0.00 | 1M |
| Venice AI | free | free | $0.00 | 1M |
| NanoGPT (this) | $0.05 | $0.05 | $0.05 | 1M |
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":"stealth/ox-alpha","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):