Prism Flash
hyper/prism-flash · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools text image.
$0.57
Blended $/1M (3:1)
$0.33
Input $/1M
$1.31
Output $/1M
$1.64
1M in + 1M out
$0.03 −91%
Cache read $/1M
#3450 of 8,511
Cheapest rank
- Provider
- Charm Hyper (
hyper) - Kind
- text (outputs text)
- Context
- 1,000,000 tokens
- Max output
- 131,072 tokens
- Capabilities
- tools text image
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Charm Hyper and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"prism-flash","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):