DeepSeek-V3.2 1.5B: pricing, context window and benchmarks
DeepSeek-V3.2 1.5B is a small open-weight model from DeepSeek. It offers a 4,096-token context window, costs $1.02 per million input tokens and $5.25 per million output tokens, and averages 56.9 across the index's benchmark suite.
Pricing
DeepSeek-V3.2 1.5B costs $1.02 per million input tokens and $5.25 per million output tokens. A blended 3:1 input-to-output mix works out to about $2.08 per million tokens. Cached input is listed at $0.10 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $1.02 | per 1M tokens |
| Output | $5.25 | per 1M tokens |
| Cached input | $0.10 | per 1M tokens |
| Blended 3:1 | $2.08 | estimate per 1M tokens |
| 1M in + 1M out | $6.27 | 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 | 63.7 | 476 | 21th | |
| GPQA Diamond | 53.6 | 486 | 19th | |
| SWE-bench Verified | 41.4 | 507 | 16th | |
| HumanEval | 61.0 | 487 | 19th | |
| MATH-500 | 55.4 | 517 | 14th | |
| AIME 2025 | 45.4 | 494 | 18th | |
| LiveCodeBench | 45.5 | 493 | 18th | |
| IFEval | 70.1 | 460 | 23th | |
| TruthfulQA | 61.3 | 516 | 14th | |
| HellaSwag | 72.0 | 496 | 17th | |
| MMMU | 56.3 | 483 | 20th | |
| Arena Elo | 1260.0 | 475 | 21th |
What DeepSeek-V3.2 1.5B is good for
DeepSeek-V3.2 1.5B is a small model. That makes it a good fit for classification, extraction, routing, summarization and other high-volume jobs where latency and cost dominate. It is not the right pick for open-ended frontier reasoning, but at $1.02 per million input tokens it can handle a large share of production traffic.
Strengths
- Input price of $1.02 per million tokens is at or below the index median.
- Open weights make self-hosting, fine-tuning and data-residency review possible.
Trade-offs
- Context window of 4,096 tokens is small for long-document work.
- 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 |
|---|---|---|---|---|
| Codestral 7B | Mistral AI | 32768 | $1.05 | 57.0 |
| Llama 3 Baseten 8B | Baseten | 4096 | $1.02 | 57.0 |
| Llama 3 Replicate 8B | Replicate | 32768 | $1.00 | 57.0 |
| DeepSeek-V3.2 1.5B | DeepSeek | 4096 | $1.02 | 56.9 |
| Nemotron 4 7B | NVIDIA | 16384 | $1.05 | 56.9 |
| Fusion Nano | OpenRouter | 8192 | $2.96 | 56.8 |
FAQ
How much does DeepSeek-V3.2 1.5B cost?
DeepSeek-V3.2 1.5B is listed at $1.02 per million input tokens and $5.25 per million output tokens. Cached input is $0.095 per million tokens. A blended 3:1 input-to-output mix is about $2.08 per million tokens.
What is the context window of DeepSeek-V3.2 1.5B?
DeepSeek-V3.2 1.5B has a context window of 4,096 tokens and can emit up to 4,096 output tokens per request in this index.
Is DeepSeek-V3.2 1.5B open weights?
Yes. DeepSeek-V3.2 1.5B is listed as an open-weight model under a open weights licence.
How does DeepSeek-V3.2 1.5B score on benchmarks?
DeepSeek-V3.2 1.5B averages 56.9 across the scored benchmarks in this index, ranking #490 of 600 models. Its strongest relative result is Arena Elo at 1260.0.
What is DeepSeek-V3.2 1.5B best for?
DeepSeek-V3.2 1.5B is a small model. That makes it a good fit for classification, extraction, routing, summarization and other high-volume jobs where latency and cost dominate. It is not the right pick for open-ended frontier reasoning, but at $1.02 per million input tokens it can handle a large share of production traffic.