Qwen3 4B
Qwen3 4B is Alibaba's language model with a 131K context window and up to 8K output tokens, available from 3 providers, starting at $0.080 / 1M input and $0.200 / 1M output. A compact 4B parameter dense Qwen3 language model supporting both reasoning and non-reasoning modes, suitable for efficient on-device or low-latency inference.
Alibaba's language model with a 131K context window and up to 8K output tokens, available from 3 providers, starting at $0.080 / 1M input and $0.200 / 1M output. A compact 4B parameter dense Qwen3 language model supporting both reasoning and non-reasoning modes, suitable for efficient on-device or low-latency inference.14.2#197 |
9.5#203 |
22.3#140 |
0.7#150 |
0.5#189 |
0.1#162 |
0.5#100 |
0.7#27 |
0.3#193 |
1.00s#234 |
0.0#306 |
0.9#32 |
0.2#140 |
0.0#226 |
0.0#197 |
0.2#195 |
0.0#210 |
Capabilities
Input1/5
✓
·
·
·
·
Output1/5
✓
·
·
·
·
Capabilities1/13
·
·
✓
·
·
·
·
·
·
·
·
·
·
Pricing by Provider
| Provider | Standard | Batch | ||
|---|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Input $ / 1M | Output $ / 1M | |
 Nebius | $0.080 | $0.240 | — | — |
Alibaba Qwen | $0.110 | $0.420 | $0.055 | $0.210 |
 Fireworks AI | $0.200 | $0.200 | — | — |
Cost Calculator
Preset:
Compares every provider & tier in USD
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Qwen3 Embedding 0.6B | 33K | $0.010 | $0.000 | Available | |
| Qwen3 Embedding 4B | 41K | $0.020 | $0.000 | Available | |
| Qwen3 14B | 131K | $0.060 | $0.200 | Available | |
| Qwen3 32B | 131K | $0.080 | $0.240 | Available | |
| Qwen3 8B | 131K | $0.050 | $0.200 | Available | |
| Qwen3 4B | — | 131K | $0.080 | $0.200 | Current |
| KwaiPilot KAT 32B Dev | — | 131K | $0.900 | $0.900 | Available |
| Qwen3 0.6B | — | 41K | $0.100 | $0.100 | Available |
| Qwen3 1.7B | — | 131K | $0.100 | $0.100 | Available |
| Qwen3 4B Instruct | — | 262K | $0.200 | $0.200 | Available |
| Qwen3 Reranker 0.6B | — | 41K | — | — | Available |