Qwen3 Coder 30B A3B Instruct
nano-gpt/qwen/qwen3-coder-30b-a3b-instruct · family qwen · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools text.
$0.18
Blended $/1M (3:1)
$0.1
Input $/1M
$0.4
Output $/1M
$0.50
1M in + 1M out
$0.05 −50%
Cache read $/1M
#1525 of 7,322
Cheapest rank
- Provider
- NanoGPT (
nano-gpt) - Kind
- text (outputs text)
- Context
- 128,000 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. ModelScope is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| ModelScope | free | free | $0.00 | 262k |
| NovitaAI | $0.07 | $0.27 | $0.12 | 160k |
| Helicone | $0.1 | $0.3 | $0.15 | 262k |
| NanoGPT (this) | $0.1 | $0.4 | $0.18 | 128k |
| Clarifai | $0.1146 | $0.7481 | $0.27 | 262k |
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-coder-30b-a3b-instruct","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):