Qwen3.5 397B A17B
nano-gpt/qwen/qwen3.5-397b-a17b · family qwen · in: text, image, video → out: text · price provider-declared (via models.dev). Capabilities: tools text image video.
$1.35
Blended $/1M (3:1)
$0.6
Input $/1M
$3.6
Output $/1M
$4.20
1M in + 1M out
$0.3 −50%
Cache read $/1M
#4495 of 7,708
Cheapest rank
- Provider
- NanoGPT (
nano-gpt) - Kind
- text (outputs text)
- Context
- 258,048 tokens
- Max output
- 65,536 tokens
- Capabilities
- tools text image video
Same model, other providers
“Qwen3.5 397B A17B” is offered by 5 providers — cheapest-effective first. Merge Gateway is the cheapest at $0.39 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Merge Gateway | $0.172 | $1.03 | $0.39 | 131k |
| NanoGPT (this) | $0.6 | $3.6 | $1.35 | 258k |
| Scaleway | $0.6 | $3.6 | $1.35 | 256k |
| Mixlayer | $0.6 | $3.6 | $1.35 | 262k |
| Together AI | $0.6 | $3.6 | $1.35 | 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/qwen3.5-397b-a17b","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):