Qwen3.5 122B-A10B
huggingface/Qwen/Qwen3.5-122B-A10B · family qwen · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image.
$1.10
Blended $/1M (3:1)
$0.4
Input $/1M
$3.2
Output $/1M
$3.60
1M in + 1M out
—
Cache read $/1M
#4222 of 7,708
Cheapest rank
- Provider
- Hugging Face (
huggingface) - Kind
- text (outputs text)
- Context
- 262,144 tokens
- Max output
- 65,536 tokens
- Capabilities
- tools reasoning text image
Same model, other providers
“Qwen3.5 122B-A10B” is offered by 14 providers — cheapest-effective first. Nvidia is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Nvidia | free | free | $0.00 | 262k |
| EmpirioLabs AI | $0.115 | $0.917 | $0.32 | 256k |
| OrcaRouter | $0.115 | $0.917 | $0.32 | 262k |
| SiliconFlow | $0.26 | $2.08 | $0.72 | 262k |
| Kilo Gateway | $0.26 | $2.08 | $0.72 | 262k |
| OpenRouter | $0.26 | $2.08 | $0.72 | 262k |
| Neon | $0.22 | $2.2 | $0.72 | 262k |
| Ofox | $0.29 | $2.29 | $0.79 | 256k |
| Deep Infra | $0.29 | $2.4 | $0.82 | 262k |
| Hugging Face (this) | $0.4 | $3.2 | $1.10 | 262k |
| Alibaba | $0.4 | $3.2 | $1.10 | 262k |
| Jalapeno Cloud | $0.4 | $3.2 | $1.10 | 262k |
| Cortecs | $0.495 | $3.46 | $1.24 | 262k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Hugging Face and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"Qwen/Qwen3.5-122B-A10B","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):