Qwen3.6 Max Preview
ofox/qwen/qwen3.6-max-preview · family qwen · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$4.83
Blended $/1M (3:1)
$2.15
Input $/1M
$12.86
Output $/1M
$15.01
1M in + 1M out
$0.2 −91%
Cache read $/1M
#7259 of 8,504
Cheapest rank
- Provider
- Ofox (
ofox) - Kind
- text (outputs text)
- Context
- 256,000 tokens
- Max output
- 64,000 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“Qwen3.6 Max Preview” is offered by 6 providers — cheapest-effective first. NanoGPT is the cheapest at $2.34 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| NanoGPT | $1.04 | $6.24 | $2.34 | 246k |
| AIHubMix | $1.27 | $7.61 | $2.85 | 240k |
| Alibaba | $1.3 | $7.8 | $2.92 | 262k |
| Merge Gateway | $1.31 | $7.88 | $2.95 | 256k |
| Alibaba (China) | $1.32 | $7.9 | $2.96 | 246k |
| Ofox (this) | $2.15 | $12.86 | $4.83 | 256k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Ofox and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"qwen/qwen3.6-max-preview","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):