StableLM 2 8B: pricing, context window and benchmarks
StableLM 2 8B is a small open-weight model from Stability AI. It offers a 32,768-token context window, costs $0.38 per million input tokens and $1.78 per million output tokens, and averages 47.0 across the index's benchmark suite.
Pricing
StableLM 2 8B costs $0.38 per million input tokens and $1.78 per million output tokens. A blended 3:1 input-to-output mix works out to about $0.73 per million tokens. Cached input is listed at $0.06 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $0.38 | per 1M tokens |
| Output | $1.78 | per 1M tokens |
| Cached input | $0.06 | per 1M tokens |
| Blended 3:1 | $0.73 | estimate per 1M tokens |
| 1M in + 1M out | $2.16 | 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 | 54.8 | 574 | 4th | |
| GPQA Diamond | 40.7 | 584 | 3th | |
| SWE-bench Verified | 31.0 | 577 | 4th | |
| HumanEval | 50.4 | 573 | 5th | |
| MATH-500 | 44.5 | 578 | 4th | |
| AIME 2025 | 35.7 | 562 | 6th | |
| LiveCodeBench | 29.5 | 583 | 3th | |
| IFEval | 60.8 | 567 | 6th | |
| TruthfulQA | 55.3 | 573 | 5th | |
| HellaSwag | 66.7 | 569 | 5th | |
| MMMU | 47.8 | 566 | 6th | |
| Arena Elo | 1183.9 | 571 | 5th |
What StableLM 2 8B is good for
StableLM 2 8B 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 $0.38 per million input tokens it can handle a large share of production traffic.
Strengths
- Input price of $0.38 per million tokens is at or below the index median.
- Open weights make self-hosting, fine-tuning and data-residency review possible.
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 |
|---|---|---|---|---|
| Mixtral 1.5B | Mistral AI | 16384 | $0.36 | 47.7 |
| Mixtral Turbo 1.5B | Together AI | 4096 | $0.31 | 47.6 |
| Nemotron Nano 7B | NVIDIA | 8192 | $0.35 | 47.5 |
| DBRX 1.5B | Databricks | 16384 | $0.32 | 47.0 |
| StableLM 2 8B | Stability AI | 32768 | $0.38 | 47.0 |
| Yi-Large 1.5B | 01.AI | 8192 | $0.42 | 46.8 |
FAQ
How much does StableLM 2 8B cost?
StableLM 2 8B is listed at $0.38 per million input tokens and $1.78 per million output tokens. Cached input is $0.055 per million tokens. A blended 3:1 input-to-output mix is about $0.73 per million tokens.
What is the context window of StableLM 2 8B?
StableLM 2 8B has a context window of 32,768 tokens and can emit up to 32,768 output tokens per request in this index.
Is StableLM 2 8B open weights?
Yes. StableLM 2 8B is listed as an open-weight model under a open weights licence.
How does StableLM 2 8B score on benchmarks?
StableLM 2 8B averages 47.0 across the scored benchmarks in this index, ranking #579 of 600 models. Its strongest relative result is Arena Elo at 1183.9.
What is StableLM 2 8B best for?
StableLM 2 8B 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 $0.38 per million input tokens it can handle a large share of production traffic.