Qwen3.5 9B
huggingface/Qwen/Qwen3.5-9B · family qwen · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image.
$0.19
Blended $/1M (3:1)
$0.17
Input $/1M
$0.25
Output $/1M
$0.42
1M in + 1M out
—
Cache read $/1M
#1628 of 8,512
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 9B” is offered by 15 providers — cheapest-effective first. QVAC is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| QVAC | free | free | $0.00 | 33k |
| NanoGPT | $0.05 | $0.15 | $0.08 | 262k |
| Merge Gateway | $0.09 | $0.13 | $0.10 | 262k |
| EmpirioLabs AI | $0.09 | $0.13 | $0.10 | 262k |
| Deep Infra | $0.1 | $0.15 | $0.11 | 262k |
| DevPass (LLM Gateway) | $0.1 | $0.15 | $0.11 | 262k |
| Cortecs | $0.111 | $0.167 | $0.13 | 262k |
| TensorX | $0.15 | $0.2 | $0.16 | 262k |
| Mixlayer | $0.1 | $0.4 | $0.18 | 262k |
| Hugging Face (this) | $0.17 | $0.25 | $0.19 | 262k |
| Kilo Gateway | $0.17 | $0.25 | $0.19 | 262k |
| OpenRouter | $0.17 | $0.25 | $0.19 | 262k |
| Together AI | $0.17 | $0.25 | $0.19 | 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/Qwen3.5-9B","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):