Qwen3.7 Flash
nano-gpt/qwen/qwen3.7-flash · family qwen · in: text, image, video → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image video.
$0.06
Blended $/1M (3:1)
$0.03
Input $/1M
$0.13
Output $/1M
$0.16
1M in + 1M out
$0.006 −80%
Cache read $/1M
#695 of 7,322
Cheapest rank
- Provider
- NanoGPT (
nano-gpt) - Kind
- text (outputs text)
- Context
- 991,808 tokens
- Max output
- 65,536 tokens
- Capabilities
- tools reasoning text image video
Same model, other providers
“Qwen3.7 Flash” is offered by 10 providers — cheapest-effective first. AIHubMix is the cheapest at $0.05 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| AIHubMix | $0.0282 | $0.1128 | $0.05 | 991k |
| Alibaba (China) | $0.0296 | $0.1185 | $0.05 | 1M |
| NanoGPT (this) | $0.03 | $0.13 | $0.06 | 992k |
| OrcaRouter | $0.03 | $0.13 | $0.06 | 1M |
| DevPass (LLM Gateway) | $0.03 | $0.13 | $0.06 | 1M |
| EmpirioLabs AI | $0.03 | $0.13 | $0.06 | 1M |
| Kilo Gateway | $0.03 | $0.13 | $0.06 | 1M |
| OpenRouter | $0.03 | $0.13 | $0.06 | 1M |
| CrossModel | $0.04 | $0.13 | $0.06 | 1M |
| Charm Hyper | $0.2 | $0.8 | $0.35 | 1M |
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/qwen3.7-flash","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):