Qwen3.8 Max
adzuki/qwen3.8-max · family qwen · in: text, image, video, pdf → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image video pdf.
$5.14
Blended $/1M (3:1)
$3.43
Input $/1M
$10.29
Output $/1M
$13.71
1M in + 1M out
$0.4286 −87%
Cache read $/1M
#7847 of 9,232
Cheapest rank
- Provider
- Adzuki AI (
adzuki) - Kind
- text (outputs text)
- Context
- 1,000,000 tokens
- Max output
- 131,072 tokens
- Capabilities
- tools reasoning text image video pdf
Same model, other providers
“Qwen3.8 Max” is offered by 36 providers — cheapest-effective first. Alibaba Token Plan is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Alibaba Token Plan | free | free | $0.00 | 1M |
| Alibaba Token Plan (China) | free | free | $0.00 | 1M |
| SCNet Token Plan | free | free | $0.00 | 1M |
| Zenifra | $1.54 | $4.64 | $2.32 | 1M |
| JZSTOKEN | $1.56 | $4.67 | $2.34 | 1M |
| Vancine | $1.6 | $4.8 | $2.40 | 1M |
| Deep Infra | $1.65 | $4.95 | $2.48 | 256k |
| AIHubMix | $1.69 | $5.07 | $2.54 | 991k |
| Ofox | $1.71 | $5.14 | $2.57 | 1M |
| TeamoRouter | $1.71 | $5.14 | $2.57 | 1M |
| Alibaba (China) | $1.78 | $5.33 | $2.67 | 1M |
| AbliteratedLLM | $1.8 | $5.4 | $2.70 | 262k |
| Adzuki AI (this) | $3.43 | $10.29 | $5.14 | 1M |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Adzuki AI and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"qwen3.8-max","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):