jishie

Qwen3.7 Flash

openrouter/qwen/qwen3.7-flash · family qwen · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtextimagevideo.

$0.06Blended $/1M (3:1)
$0.03Input $/1M
$0.13Output $/1M
$0.161M in + 1M out
$0.006 −80%Cache read $/1M
#600 of 5,000Cheapest rank
Provider
OpenRouter (openrouter)
Context
1,000,000 tokens
Max output
65,536 tokens
Capabilities
toolsreasoningtextimagevideo

Same model, other providers

“Qwen3.7 Flash” is offered by 8 providers — cheapest-effective first. Alibaba (China) is the cheapest at $0.05 blended.

ProviderInputOutputBlendedContext
Alibaba (China)$0.02962$0.1185$0.051000k
OpenRouter (this)$0.03$0.13$0.061000k
NanoGPT$0.03$0.13$0.06992k
LLM Gateway$0.03$0.13$0.061000k
EmpirioLabs AI$0.03$0.13$0.061000k
Kilo Gateway$0.03$0.13$0.061000k
CrossModel$0.04$0.13$0.061000k
Charm Hyper$0.2$0.8$0.351000k

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at OpenRouter 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):