Qwen Flash

ofox/bailian/qwen-flash · family qwen · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtext.

$0.07Blended $/1M (3:1)

$0.022Input $/1M

$0.22Output $/1M

$0.241M in + 1M out

$0.0043 −80%Cache read $/1M

#669 of 5,000Cheapest rank

Provider: Ofox (ofox)
Context: 1,000,000 tokens
Max output: 32,768 tokens
Capabilities: toolsreasoningtext

Same model, other providers

“Qwen Flash” is offered by 5 providers — cheapest-effective first. Merge Gateway is the cheapest at $0.07 blended.

Provider	Input	Output	Blended	Context
Merge Gateway	$0.022	$0.216	$0.07	1000k
Alibaba (China)	$0.022	$0.216	$0.07	1000k
Ofox (this)	$0.022	$0.22	$0.07	1000k
LLM Gateway	$0.05	$0.4	$0.14	1000k
Alibaba	$0.05	$0.4	$0.14	1000k

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at Ofox and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"bailian/qwen-flash","messages":[{"role":"user","content":"hello"}]}'

Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):