Qwen3 30B A3B
zerogpu/qwen3-30b-a3b-fp8 · family qwen · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$0.19
Blended $/1M (3:1)
$0.1
Input $/1M
$0.45
Output $/1M
$0.55
1M in + 1M out
—
Cache read $/1M
#1772 of 9,563
Cheapest rank
- Provider
- ZeroGPU (
zerogpu) - Kind
- text (outputs text)
- Context
- 32,768 tokens
- Max output
- 16,384 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“Qwen3 30B A3B” is offered by 11 providers — cheapest-effective first. Helicone is the cheapest at $0.13 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Helicone | $0.08 | $0.29 | $0.13 | 41k |
| DevPass (LLM Gateway) | $0.095 | $0.285 | $0.14 | 33k |
| Jiekou.AI | $0.09 | $0.45 | $0.18 | 41k |
| ZeroGPU (this) | $0.1 | $0.45 | $0.19 | 33k |
| Qiniu | $0.1087 | $0.4348 | $0.19 | 40k |
| NanoGPT | $0.12 | $0.5 | $0.21 | 41k |
| OpenRouter | $0.12 | $0.5 | $0.21 | 41k |
| Hugging Face | $0.12 | $0.5 | $0.21 | 41k |
| Deep Infra | $0.12 | $0.5 | $0.21 | 41k |
| Kilo Gateway | $0.12 | $0.5 | $0.21 | 41k |
| Merge Gateway | $0.108 | $1.08 | $0.35 | 131k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at ZeroGPU and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"qwen3-30b-a3b-fp8","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):