Qwen3.6 35B A3B
nano-gpt/qwen/qwen3.6-35b-a3b · family qwen · in: text, image, video → out: text · price provider-declared (via models.dev). Capabilities: tools text image video.
$0.28
Blended $/1M (3:1)
$0.112
Input $/1M
$0.8
Output $/1M
$0.91
1M in + 1M out
$0.056 −50%
Cache read $/1M
#2049 of 7,322
Cheapest rank
- Provider
- NanoGPT (
nano-gpt) - Kind
- text (outputs text)
- Context
- 262,144 tokens
- Max output
- 16,384 tokens
- Capabilities
- tools text image video
Same model, other providers
“Qwen3.6 35B A3B” is offered by 7 providers — cheapest-effective first. Umans AI Coding Plan is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Umans AI Coding Plan | free | free | $0.00 | 262k |
| EmpirioLabs AI | $0.07 | $0.42 | $0.16 | 131k |
| NanoGPT (this) | $0.112 | $0.8 | $0.28 | 262k |
| Deep Infra | $0.1 | $0.95 | $0.31 | 262k |
| Weights & Biases | $0.25 | $1.25 | $0.50 | 262k |
| Merge Gateway | $0.248 | $1.49 | $0.56 | 262k |
| Scaleway | $0.25 | $1.5 | $0.56 | 128k |
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/qwen3.6-35b-a3b","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):