Qwen3-Coder 30B-A3B Instruct

greenpt/qwen3-coder-30b-a3b-instruct · family qwen · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolstext.

$0.48Blended $/1M (3:1)

$0.285Input $/1M

$1.083Output $/1M

$1.371M in + 1M out

—Cache read $/1M

#2169 of 5,000Cheapest rank

Provider: GreenPT (greenpt)
Context: 128,000 tokens
Max output: 32,768 tokens
Capabilities: toolstext

Same model, other providers

“Qwen3-Coder 30B-A3B Instruct” is offered by 9 providers — cheapest-effective first. TensorX is the cheapest at $0.11 blended.

Provider	Input	Output	Blended	Context
TensorX	$0.06	$0.25	$0.11	262k
Cortecs	$0.067	$0.245	$0.11	262k
Hugging Face	$0.07	$0.26	$0.12	262k
LLM Gateway	$0.07	$0.27	$0.12	262k
OpenRouter	$0.07	$0.28	$0.12	262k
Scaleway	$0.2	$0.8	$0.35	128k
Alibaba (China)	$0.216	$0.861	$0.38	262k
GreenPT (this)	$0.285	$1.083	$0.48	128k
Kilo Gateway	$0.2925	$1.4625	$0.58	262k

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at GreenPT 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-30b-a3b-instruct","messages":[{"role":"user","content":"hello"}]}'

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