StableLM 2 Instruct: pricing, context window and benchmarks
StableLM 2 Instruct is a open-weight model from Stability AI. It offers a 16,384-token context window, costs $1.93 per million input tokens and $8.75 per million output tokens, and averages 65.2 across the index's benchmark suite.
Pricing
StableLM 2 Instruct costs $1.93 per million input tokens and $8.75 per million output tokens. A blended 3:1 input-to-output mix works out to about $3.63 per million tokens. Cached input is listed at $0.19 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $1.93 | per 1M tokens |
| Output | $8.75 | per 1M tokens |
| Cached input | $0.19 | per 1M tokens |
| Blended 3:1 | $3.63 | estimate per 1M tokens |
| 1M in + 1M out | $10.68 | 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 | 69.9 | 396 | 34th | |
| GPQA Diamond | 62.2 | 389 | 35th | |
| SWE-bench Verified | 54.5 | 389 | 35th | |
| HumanEval | 69.5 | 404 | 33th | |
| MATH-500 | 67.7 | 403 | 33th | |
| AIME 2025 | 53.9 | 425 | 29th | |
| LiveCodeBench | 55.9 | 398 | 34th | |
| IFEval | 72.9 | 418 | 30th | |
| TruthfulQA | 70.0 | 400 | 33th | |
| HellaSwag | 77.5 | 408 | 32th | |
| MMMU | 63.0 | 399 | 34th | |
| Arena Elo | 1301.8 | 415 | 31th |
What StableLM 2 Instruct is good for
StableLM 2 Instruct is an open-weight model, so it can be self-hosted or run through a third-party inference provider. That matters for data residency, fine-tuning and long-run cost control. At $1.93 per million input tokens (hosted list price) and a 16,384-token context window, it is a practical option for teams that want more control than a closed API allows.
Strengths
- Input price of $1.93 per million tokens is at or below the index median.
- Open weights make self-hosting, fine-tuning and data-residency review possible.
- Accepts more than text, including image input where the provider supports it.
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.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Nova Pro Nano | Amazon | 8192 | $5.44 | 65.4 |
| Embed 4 Reasoning | Cohere | 4096 | $5.50 | 65.3 |
| StableLM 2 Instruct | Stability AI | 16384 | $1.93 | 65.2 |
| Reka Core Nano | Reka AI | 16384 | $5.45 | 65.1 |
| Nova Lite Mini | Amazon | 16384 | $5.43 | 65.0 |
| StableLM 2 | Stability AI | 8192 | $1.91 | 65.0 |
FAQ
How much does StableLM 2 Instruct cost?
StableLM 2 Instruct is listed at $1.93 per million input tokens and $8.75 per million output tokens. Cached input is $0.19 per million tokens. A blended 3:1 input-to-output mix is about $3.63 per million tokens.
What is the context window of StableLM 2 Instruct?
StableLM 2 Instruct has a context window of 16,384 tokens and can emit up to 4,096 output tokens per request in this index.
Is StableLM 2 Instruct open weights?
Yes. StableLM 2 Instruct is listed as an open-weight model under a open weights licence.
How does StableLM 2 Instruct score on benchmarks?
StableLM 2 Instruct averages 65.2 across the scored benchmarks in this index, ranking #401 of 600 models. Its strongest relative result is Arena Elo at 1301.8.
What is StableLM 2 Instruct best for?
StableLM 2 Instruct is an open-weight model, so it can be self-hosted or run through a third-party inference provider. That matters for data residency, fine-tuning and long-run cost control. At $1.93 per million input tokens (hosted list price) and a 16,384-token context window, it is a practical option for teams that want more control than a closed API allows.