Qwen3.8 Flash Next
aipg/qwen38-flash-next-nvfp4 · family qwen · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image.
$0.13
Blended $/1M (3:1)
$0.075
Input $/1M
$0.3
Output $/1M
$0.38
1M in + 1M out
—
Cache read $/1M
#1192 of 9,232
Cheapest rank
- Provider
- AI Power Grid (
aipg) - Kind
- text (outputs text)
- Context
- 40,000 tokens
- Max output
- 32,768 tokens
- Capabilities
- tools reasoning text image
Same model, other providers
“Qwen3.8 Flash Next” is offered by 6 providers — cheapest-effective first. AMD is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| AMD | free | free | $0.00 | 262k |
| Vultr | $0.1 | $0.2 | $0.13 | 262k |
| AI Power Grid (this) | $0.075 | $0.3 | $0.13 | 40k |
| TensorX | $0.2 | $0.5 | $0.28 | 262k |
| Requesty | $0.2 | $0.5 | $0.28 | 262k |
| Augure | $1.42 | $2.85 | $1.78 | 262k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at AI Power Grid and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"qwen38-flash-next-nvfp4","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):