jishie

Qwen3 Coder Flash

alibaba-cn/qwen3-coder-flash · family qwen · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools text.

$0.25
Blended $/1M (3:1)
$0.144
Input $/1M
$0.574
Output $/1M
$0.72
1M in + 1M out
—
Cache read $/1M
#1963 of 7,708
Cheapest rank
Provider
Alibaba (China) (alibaba-cn)
Kind
text (outputs text)
Context
1,000,000 tokens
Max output
65,536 tokens
Capabilities
tools text

Same model, other providers

“Qwen3 Coder Flash” is offered by 11 providers — cheapest-effective first. This one (Alibaba (China)) is the cheapest.

ProviderInputOutputBlendedContext
Alibaba (China) (this)$0.144$0.574$0.251M
Merge Gateway$0.144$0.574$0.251M
Kilo Gateway$0.195$0.975$0.391M
OpenRouter$0.195$0.975$0.391M
NanoGPT$0.3$1.5$0.60128k
LLMTR$0.3$1.5$0.601M
Alibaba$0.3$1.5$0.601M
Eden AI$0.3$1.5$0.601M
DevPass (LLM Gateway)$0.3$1.5$0.601M
DigitalOcean$0.45$1.7$0.76262k
Ofox$0.5$2.5$1.001M

Call it

jishie indexes & prices models; it does not proxy inference.

Most providers are OpenAI-compatible — point base_url at Alibaba (China) and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"qwen3-coder-flash","messages":[{"role":"user","content":"hello"}]}'

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

← all Alibaba (China) models · model index · JSON