Qwen3 Omni 30B A3B Instruct
Qwen3 Omni 30B A3B Instruct is Alibaba's language model with a 66K context window and up to 16K output tokens, starting at $0.250 / 1M input and $0.970 / 1M output. An instruction-tuned omni-modal LLM accepting text, image, audio, and video inputs with 30B total and 3B active parameters, capable of generating both text and speech responses.
Alibaba's language model with a 66K context window and up to 16K output tokens, starting at $0.250 / 1M input and $0.970 / 1M output. An instruction-tuned omni-modal LLM accepting text, image, audio, and video inputs with 30B total and 3B active parameters, capable of generating both text and speech responses.10.7#256 |
7.2#221 |
52.3#78 |
0.7#128 |
0.6#144 |
0.1#163 |
0.4#108 |
0.3#210 |
0.92s#226 |
0.2#233 |
0.5#78 |
0.0#229 |
0.0#199 |
0.2#205 |
104.4#80 |
Capabilities
Input2/5
·
✓
✓
·
·
Output1/5
·
·
✓
·
·
Capabilities3/13
·
·
✓
✓
✓
·
·
·
·
·
·
·
·
Pricing by Provider
| Provider | Standard | |
|---|---|---|
| Input $ / 1M | Output $ / 1M | |
 Novita | $0.250 | $0.970 |
Cost Calculator
Preset:
Compares every provider & tier in USD
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| DeepSeek R1 0528 Qwen3 8B | — | 128K | $0.060 | $0.090 | Available |
| Qwen3 9.23 Max | — | — | — | — | Available |
| Qwen 7 28 Flash | — | 998K | — | — | Available |
| Qwen 4 28 Plus | — | 129K | — | — | Available |
| Qwen 3 32B | 128K | — | — | Available | |
| Qwen3.5-Flash | 1.0M | $0.065 | $0.260 | Available | |
| Qwen3.5 Plus 2026-02-15 | 1.0M | $0.260 | $1.56 | Available | |
| Qwen 1 25 Plus | — | 129K | — | — | Available |
| Qwen3.5 Max | — | 258K | — | — | Available |
| Qwen3.6 Plus | 1.0M | $0.325 | $1.95 | Available | |
| Qwen3 Omni 30B A3B Instruct | — | 66K | $0.250 | $0.970 | Current |