jishie

Qwen3 30B A3B

nano-gpt/qwen/qwen3-30b-a3b · family qwen · in: text → out: text · price provider-declared (via models.dev). Capabilities: text.

$0.15
Blended $/1M (3:1)
$0.1
Input $/1M
$0.3
Output $/1M
$0.40
1M in + 1M out
$0.05 −50%
Cache read $/1M
#1318 of 7,708
Cheapest rank
Provider
NanoGPT (nano-gpt)
Kind
text (outputs text)
Context
41,000 tokens
Max output
32,768 tokens
Capabilities
text

Same model, other providers

“Qwen3 30B A3B” is offered by 9 providers — cheapest-effective first. Helicone is the cheapest at $0.13 blended.

ProviderInputOutputBlendedContext
Helicone$0.08$0.29$0.1341k
NanoGPT (this)$0.1$0.3$0.1541k
NovitaAI$0.09$0.45$0.1841k
Jiekou.AI$0.09$0.45$0.1841k
Deep Infra$0.12$0.5$0.2141k
OpenRouter$0.12$0.5$0.21131k
Hugging Face$0.12$0.5$0.2141k
Kilo Gateway$0.13$0.52$0.2341k
Merge Gateway$0.108$1.08$0.35131k

Call it

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

Most providers are OpenAI-compatible — point base_url at NanoGPT and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"qwen/qwen3-30b-a3b","messages":[{"role":"user","content":"hello"}]}'

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

← all NanoGPT models · model index · JSON