jishie

Qwen3 Coder 30B A3B Instruct

modelscope/Qwen/Qwen3-Coder-30B-A3B-Instruct · family qwen · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools text.

free
Blended $/1M (3:1)
free
Input $/1M
free
Output $/1M
free
1M in + 1M out
—
Cache read $/1M
#488 of 7,712
Cheapest rank
Provider
ModelScope (modelscope)
Kind
text (outputs text)
Context
262,144 tokens
Max output
65,536 tokens
Capabilities
tools text

Same model, other providers

“Qwen3 Coder 30B A3B Instruct” is offered by 5 providers — cheapest-effective first. This one (ModelScope) is the cheapest.

ProviderInputOutputBlendedContext
ModelScope (this)freefree$0.00262k
NovitaAI$0.07$0.27$0.12160k
Helicone$0.1$0.3$0.15262k
NanoGPT$0.1$0.4$0.18128k
Clarifai$0.1146$0.7481$0.27262k

Call it

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

Most providers are OpenAI-compatible — point base_url at ModelScope 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-Coder-30B-A3B-Instruct","messages":[{"role":"user","content":"hello"}]}'

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

← all ModelScope models · model index · JSON