jishie

Qwen3 Coder Flash

ofox/bailian/qwen3-coder-flash · family qwen · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolstext.

$1.00Blended $/1M (3:1)
$0.5Input $/1M
$2.5Output $/1M
$3.001M in + 1M out
$0.06 −88%Cache read $/1M
#3158 of 5,000Cheapest rank
Provider
Ofox (ofox)
Context
1,000,000 tokens
Max output
65,536 tokens
Capabilities
toolstext

Same model, other providers

“Qwen3 Coder Flash” is offered by 9 providers — cheapest-effective first. Merge Gateway is the cheapest at $0.25 blended.

ProviderInputOutputBlendedContext
Merge Gateway$0.144$0.574$0.251000k
Alibaba (China)$0.144$0.574$0.251000k
Kilo Gateway$0.195$0.975$0.391000k
OpenRouter$0.195$0.975$0.391000k
NanoGPT$0.3$1.5$0.60128k
LLM Gateway$0.3$1.5$0.601000k
Alibaba$0.3$1.5$0.601000k
DigitalOcean$0.45$1.7$0.76262k
Ofox (this)$0.5$2.5$1.001000k

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/qwen3-coder-flash","messages":[{"role":"user","content":"hello"}]}'

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