Agnes 3.0 Flash
agnes/agnes-3.0-flash · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image.
free
Blended $/1M (3:1)
free
Input $/1M
free
Output $/1M
free
1M in + 1M out
—
Cache read $/1M
#35 of 8,373
Cheapest rank
- Provider
- Agnes AI (
agnes) - Kind
- text (outputs text)
- Context
- 512,000 tokens
- Max output
- 65,536 tokens
- Capabilities
- tools reasoning text image
Same model, other providers
“Agnes 3.0 Flash” is offered by 2 providers — cheapest-effective first. This one (Agnes AI) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Agnes AI (this) | free | free | $0.00 | 512k |
| NanoGPT | $0.05 | $0.15 | $0.08 | 524k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Agnes AI and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"agnes-3.0-flash","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):