DeepSeek-R1 1.5B: pricing, context window and benchmarks
DeepSeek-R1 1.5B is a small open-weight model from DeepSeek. It offers a 16,384-token context window, costs $1.04 per million input tokens and $5.02 per million output tokens, and averages 56.6 across the index's benchmark suite.
Pricing
DeepSeek-R1 1.5B costs $1.04 per million input tokens and $5.02 per million output tokens. A blended 3:1 input-to-output mix works out to about $2.04 per million tokens. Cached input is listed at $0.16 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $1.04 | per 1M tokens |
| Output | $5.02 | per 1M tokens |
| Cached input | $0.16 | per 1M tokens |
| Blended 3:1 | $2.04 | estimate per 1M tokens |
| 1M in + 1M out | $6.06 | 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 | 60.7 | 518 | 14th | |
| GPQA Diamond | 54.3 | 475 | 21th | |
| SWE-bench Verified | 45.2 | 464 | 23th | |
| HumanEval | 59.7 | 508 | 15th | |
| MATH-500 | 58.5 | 484 | 19th | |
| AIME 2025 | 42.7 | 527 | 12th | |
| LiveCodeBench | 42.9 | 516 | 14th | |
| IFEval | 66.6 | 506 | 16th | |
| TruthfulQA | 61.4 | 514 | 14th | |
| HellaSwag | 74.2 | 452 | 25th | |
| MMMU | 56.2 | 484 | 19th | |
| Arena Elo | 1250.5 | 490 | 18th |
What DeepSeek-R1 1.5B is good for
DeepSeek-R1 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 $1.04 per million input tokens it can handle a large share of production traffic.
Strengths
- Input price of $1.04 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 16,384 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 |
|---|---|---|---|---|
| Fusion Nano | OpenRouter | 8192 | $2.96 | 56.8 |
| Llama 3.3 Groq 7B | Groq | 16384 | $1.01 | 56.7 |
| DeepSeek-R1 1.5B | DeepSeek | 16384 | $1.04 | 56.6 |
| Llama 3 Modal 8B | Modal | 32768 | $0.98 | 56.6 |
| Gemma 3 8B | Google DeepMind | 16384 | $0.96 | 56.5 |
| Llama 3.1 Cerebras 7B | Cerebras | 32768 | $0.95 | 56.5 |
FAQ
How much does DeepSeek-R1 1.5B cost?
DeepSeek-R1 1.5B is listed at $1.04 per million input tokens and $5.02 per million output tokens. Cached input is $0.16 per million tokens. A blended 3:1 input-to-output mix is about $2.04 per million tokens.
What is the context window of DeepSeek-R1 1.5B?
DeepSeek-R1 1.5B has a context window of 16,384 tokens and can emit up to 8,192 output tokens per request in this index.
Is DeepSeek-R1 1.5B open weights?
Yes. DeepSeek-R1 1.5B is listed as an open-weight model under a open weights licence.
How does DeepSeek-R1 1.5B score on benchmarks?
DeepSeek-R1 1.5B averages 56.6 across the scored benchmarks in this index, ranking #496 of 600 models. Its strongest relative result is Arena Elo at 1250.5.
What is DeepSeek-R1 1.5B best for?
DeepSeek-R1 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 $1.04 per million input tokens it can handle a large share of production traffic.