Qwen3-Coder 1.5B: pricing, context window and benchmarks
Qwen3-Coder 1.5B is a coding model from Alibaba Cloud. It offers a 32,768-token context window, costs $0.76 per million input tokens and $2.67 per million output tokens, and averages 52.8 across the index's benchmark suite.
Pricing
Qwen3-Coder 1.5B costs $0.76 per million input tokens and $2.67 per million output tokens. A blended 3:1 input-to-output mix works out to about $1.24 per million tokens. Cached input is listed at $0.09 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $0.76 | per 1M tokens |
| Output | $2.67 | per 1M tokens |
| Cached input | $0.09 | per 1M tokens |
| Blended 3:1 | $1.24 | estimate per 1M tokens |
| 1M in + 1M out | $3.43 | estimate |
Benchmarks
Scores below are modelled estimates on a 0–100 scale. Use them to compare relative position, not as official vendor results.
| Benchmark | Score | Rank | Percentile | Relative |
|---|---|---|---|---|
| MMLU-Pro | 57.8 | 552 | 8th | |
| GPQA Diamond | 46.7 | 552 | 8th | |
| SWE-bench Verified | 37.0 | 541 | 10th | |
| HumanEval | 58.6 | 517 | 14th | |
| MATH-500 | 51.9 | 541 | 10th | |
| AIME 2025 | 43.2 | 521 | 13th | |
| LiveCodeBench | 40.8 | 533 | 11th | |
| IFEval | 63.8 | 540 | 10th | |
| TruthfulQA | 59.9 | 532 | 11th | |
| HellaSwag | 68.5 | 555 | 8th | |
| MMMU | 53.0 | 520 | 13th | |
| Arena Elo | 1215.0 | 538 | 10th |
What Qwen3-Coder 1.5B is good for
Qwen3-Coder 1.5B is tuned toward coding work. It is a reasonable candidate for code generation, review, debugging and repository-scale tasks, especially when paired with a retrieval layer. At $0.76 per million input tokens, it sits in the mid-range of the index, and the 32,768-token context window is enough for large files and multi-file diffs.
Strengths
- Input price of $0.76 per million tokens is at or below the index median.
- Open weights make self-hosting, fine-tuning and data-residency review possible.
- Coding benchmarks are a relative strength within its tier.
Trade-offs
- Average benchmark score is below the index median; test it on your own task.
- Less reliable on open-ended reasoning and complex multi-step instructions.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Kimi K1.5 1.5B | Moonshot AI | 4096 | $0.75 | 53.2 |
| Llama 4 Scout 1.5B | Meta AI | 8192 | $0.66 | 53.0 |
| Qwen3-Coder 1.5B | Alibaba Cloud | 32768 | $0.76 | 52.8 |
| Magistral 1.5B | Mistral AI | 4096 | $0.67 | 52.7 |
| OLMo 2 8B | Allen Institute for AI | 4096 | $0.64 | 52.5 |
| Arctic 8B | Snowflake | 8192 | $0.65 | 52.4 |
FAQ
How much does Qwen3-Coder 1.5B cost?
Qwen3-Coder 1.5B is listed at $0.76 per million input tokens and $2.67 per million output tokens. Cached input is $0.090 per million tokens. A blended 3:1 input-to-output mix is about $1.24 per million tokens.
What is the context window of Qwen3-Coder 1.5B?
Qwen3-Coder 1.5B has a context window of 32,768 tokens and can emit up to 8,192 output tokens per request in this index.
Is Qwen3-Coder 1.5B open weights?
Yes. Qwen3-Coder 1.5B is listed as an open-weight model under a open weights licence.
How does Qwen3-Coder 1.5B score on benchmarks?
Qwen3-Coder 1.5B averages 52.8 across the scored benchmarks in this index, ranking #537 of 600 models. Its strongest relative result is Arena Elo at 1215.0.
What is Qwen3-Coder 1.5B best for?
Qwen3-Coder 1.5B is tuned toward coding work. It is a reasonable candidate for code generation, review, debugging and repository-scale tasks, especially when paired with a retrieval layer. At $0.76 per million input tokens, it sits in the mid-range of the index, and the 32,768-token context window is enough for large files and multi-file diffs.