Qwen3 4B
Qwen3 4B is Alibaba's language model with a 131K context window and up to 20K output tokens, available from 4 providers, starting at $0.030 / 1M input and $0.030 / 1M output. A compact 4B-parameter dense LLM from the Qwen3 series supporting hybrid thinking and non-thinking modes for efficient on-device or low-latency deployment.
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities2/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Pricing by Provider
| Provider | Standard | Batch | ||
|---|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Input $ / 1M | Output $ / 1M | |
 Novita | $0.030 | $0.030 | — | — |
 Nebius | $0.080 | $0.240 | — | — |
Alibaba Qwen | $0.110 | $0.420 | $0.055 | $0.210 |
 Fireworks AI | $0.200 | $0.200 | — | — |
Cost Calculator
Preset:
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Voyage 4 Nano | — | — | — | — | Available |
| DeepSeek R1 Distill Qwen3 8B | — | 131K | $0.200 | $0.200 | Available |
| Qwen3 Embedding 0.6B | 33K | $0.010 | — | Available | |
| Qwen3 Embedding 4B | 41K | $0.020 | — | Available | |
| Qwen3 Embedding 8B | 41K | $0.020 | — | Available | |
| Qwen3 14B | 132K | $0.060 | $0.200 | Available | |
| Qwen3 32B | 131K | $0.050 | $0.100 | Available | |
| Qwen3 8B | 131K | $0.035 | $0.138 | Available | |
| Qwen3 4B | — | 131K | $0.030 | $0.030 | Current |
| Qwen3 4B Instruct | — | 262K | $0.010 | $0.030 | Available |
| KwaiPilot KAT 32B Dev | — | 131K | $0.900 | $0.900 | Available |