Qwen Turbo
Qwen Turbo is Alibaba's language model with a 1.0M context window and up to 16K output tokens, starting at $0.05 / 1M input and $0.2 / 1M output. A fast, cost-efficient Qwen LLM from Alibaba with a 1M context window suited for high-throughput simple tasks.
| Benchmarks | |
|---|---|
| Intelligence Index | #433 |
| MMLU-Pro | #259 |
| GPQA | #434 |
| HLE | #440 |
| LiveCodeBench | #278 |
| AIME | #120 |
| Time to First Token | #455 |
| SciCode | #437 |
| MATH-500 | #109 |
| Output TPS | #116 |
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities3/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling·
Structured Outputs✓
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Pricing by Provider
US Dollar ($)
Per 1M tokens
| Provider | Standard | Batch | |||
|---|---|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Reasoning $ / 1M | Input $ / 1M | Output $ / 1M | |
| $0.05 | $0.2 | $0.5 | $0.025 | $0.1 | |
Cost Calculator
US Dollar ($)
Preset:
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Qwen Turbo | 1.0M | $0.050 | $0.200 | Current | |
| Qwen2.5 Turbo 72B Instruct | — | — | — | — | Deprecated |
| Qwen2.5 Turbo 7B Instruct | — | — | — | — | Available |
Other Models
| Model | Tier | Released | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|---|
| Qwen3.8 2.4T A95B | — | 1.0M | $2.00 | $6.00 | |
| Qwen Image 3 | — | — | — | — | — |
| Qwen Audio 3 Flash ASR | Flash | — | — | — | — |
| Qwen Audio 3 Flash ASR Filetrans | Flash | — | — | — | — |
| Qwen Audio 3 Flash ASR Streaming | Flash | — | — | — | — |
| Qwen Audio 3 Flash Realtime | Flash | — | — | $0.450 | $4.50 |
| Qwen Audio 3 Plus Realtime | Plus | — | — | $0.800 | $6.40 |
| Qwen Audio 3 Plus TTS | Plus | — | — | — | — |
| Qwen Image 3.0 Pro | Pro | — | — | — | — |
| EAGLE Qwen 2.5 3B Instruct | — | — | — | — | — |