Qwen3.5 27B
nano-gpt/qwen/qwen3.5-27b · family qwen · in: text, image, video → out: text · price provider-declared (via models.dev). Capabilities: tools text image video.
$0.74
Blended $/1M (3:1)
$0.27
Input $/1M
$2.16
Output $/1M
$2.43
1M in + 1M out
$0.135 −50%
Cache read $/1M
#3557 of 7,708
Cheapest rank
- Provider
- NanoGPT (
nano-gpt) - Kind
- text (outputs text)
- Context
- 260,096 tokens
- Max output
- 65,536 tokens
- Capabilities
- tools text image video
Same model, other providers
“Qwen3.5 27B” is offered by 14 providers — cheapest-effective first. EmpirioLabs AI is the cheapest at $0.24 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| EmpirioLabs AI | $0.086 | $0.688 | $0.24 | 256k |
| OrcaRouter | $0.086 | $0.688 | $0.24 | 262k |
| Merge Gateway | $0.086 | $0.688 | $0.24 | 131k |
| Kilo Gateway | $0.195 | $1.56 | $0.54 | 262k |
| OpenRouter | $0.195 | $1.56 | $0.54 | 262k |
| SiliconFlow | $0.25 | $2 | $0.69 | 262k |
| Ofox | $0.29 | $2.05 | $0.73 | 262k |
| NanoGPT (this) | $0.27 | $2.16 | $0.74 | 260k |
| Alibaba | $0.3 | $2.4 | $0.82 | 262k |
| Hugging Face | $0.3 | $2.4 | $0.82 | 262k |
| Mixlayer | $0.3 | $2.4 | $0.82 | 262k |
| Jalapeno Cloud | $0.3 | $2.4 | $0.82 | 262k |
| Deep Infra | $0.26 | $2.6 | $0.84 | 262k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at NanoGPT and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"qwen/qwen3.5-27b","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):