Jev
vivgrid/jev · in: text → out: text · price provider-declared (via models.dev). Capabilities: text.
$0.03
Blended $/1M (3:1)
$0.042
Input $/1M
free
Output $/1M
$0.04
1M in + 1M out
—
Cache read $/1M
#638 of 7,394
Cheapest rank
- Provider
- Vivgrid (
vivgrid) - Kind
- text (outputs text)
- Context
- 64,000 tokens
- Max output
- 0 tokens
- Capabilities
- text
Same model, other providers
“Jev” is offered by 4 providers — cheapest-effective first. This one (Vivgrid) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Vivgrid (this) | $0.042 | free | $0.03 | 64k |
| Vercel AI Gateway | $0.042 | free | $0.03 | 64k |
| Cloudflare AI Gateway | $0.042 | free | $0.03 | 32k |
| OpenCode Zen | $0.042 | free | $0.03 | 64k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Vivgrid and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"jev","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):