Qwen3.5 397B-A17B
thinkingmachines/Qwen/Qwen3.5-397B-A17B:peft:262144 · family qwen · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image.
$3.11
Blended $/1M (3:1)
$1.65
Input $/1M
$7.5
Output $/1M
$9.15
1M in + 1M out
$0.33 −80%
Cache read $/1M
#6319 of 8,512
Cheapest rank
- Provider
- Thinking Machines (
thinkingmachines) - Kind
- text (outputs text)
- Context
- 262,144 tokens
- Max output
- 262,144 tokens
- Capabilities
- tools reasoning text image
Same model, other providers
“Qwen3.5 397B-A17B” is offered by 20 providers — cheapest-effective first. UnoRouter is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| UnoRouter | free | free | $0.00 | 262k |
| AIHubMix | $0.1644 | $0.9864 | $0.37 | 262k |
| EmpirioLabs AI | $0.172 | $1.03 | $0.39 | 258k |
| OrcaRouter | $0.172 | $1.03 | $0.39 | 262k |
| Alibaba (China) | $0.172 | $1.03 | $0.39 | 262k |
| Kilo Gateway | $0.39 | $2.34 | $0.88 | 256k |
| SiliconFlow | $0.39 | $2.34 | $0.88 | 262k |
| TokenGo | $0.4 | $2.65 | $0.96 | 262k |
| NEAR AI Cloud | $0.5 | $3.3 | $1.20 | 262k |
| Ofox | $0.55 | $3.5 | $1.29 | 256k |
| Alibaba | $0.6 | $3.6 | $1.35 | 262k |
| Jalapeno Cloud | $0.6 | $3.6 | $1.35 | 262k |
| Thinking Machines (this) | $1.65 | $7.5 | $3.11 | 262k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Thinking Machines and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"Qwen/Qwen3.5-397B-A17B:peft:262144","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):