Qwen
Qwen3 30B A3B Instruct 2507
Released 2025-07-29 · Knowledge up to 2025-06-30
Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and...
You send / 1M
$0.100
tokens in
It replies / 1M
$0.300
tokens out
Memory
262K
tokens it can read at once
Typical request
$0.0003
1,000 words in, 400 out
Data privacy
No training or retention: Yes. At least one provider serves it with zero data retention.
| Provider | You send / 1M | It replies / 1M | Uptime | Privacy policy |
|---|---|---|---|---|
| DekaLLM | $0.090 | $0.300 | 100% | Read |
| SiliconFlow · fp8 | $0.090 | $0.300 | 100% | Read |
| Nebius · fp8 | $0.100 | $0.300 | 100% | Read |
Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.
What it can do
- Reads: text
- Writes: text
- Reasoning: No
- Tool calling: Yes
- Longest reply: 236K tokens
- Repeated text is billed at $0.100 per 1M (prompt caching)
- Intelligence score: 7.5 / 100 (Artificial Analysis)
Similar models
- Voxtral Small 24B 2507Mistral · $0.100 in / $0.300 out per 1M
- Hy-MT2-30B-A3BTencent · $0.074 in / $0.295 out per 1M
- Hy-MT2-7BTencent · $0.074 in / $0.295 out per 1M
- Llama 3.3 70B InstructMeta · $0.100 in / $0.320 out per 1M
- Qwen3 Coder 30B A3B InstructQwen · $0.070 in / $0.280 out per 1M
- Llama 3.2 3B InstructMeta · $0.050 in / $0.330 out per 1M
Appears in
Top No-Training AI ModelsTop No-Training Zero Data Retention AI ModelsTop No-Training Zero Data Retention Cheap AI ModelsTop No-Training Zero Data Retention Tool-Calling AI ModelsTop No-Training Cheap AI ModelsTop No-Training Cheap Tool-Calling AI ModelsTop No-Training Tool-Calling AI ModelsTop Zero Data Retention AI Models
Estimate your monthly cost with Qwen3 30B A3B Instruct 2507 →