Molmo: pricing, context window and benchmarks
Molmo is a open-weight model from Allen Institute for AI. It offers a 32,768-token context window, costs $2.49 per million input tokens and $9.45 per million output tokens, and averages 68.5 across the index's benchmark suite.
Pricing
Molmo costs $2.49 per million input tokens and $9.45 per million output tokens. A blended 3:1 input-to-output mix works out to about $4.23 per million tokens. Cached input is listed at $0.32 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $2.49 | per 1M tokens |
| Output | $9.45 | per 1M tokens |
| Cached input | $0.32 | per 1M tokens |
| Blended 3:1 | $4.23 | estimate per 1M tokens |
| 1M in + 1M out | $11.94 | 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 | 74.0 | 353 | 41th | |
| GPQA Diamond | 65.3 | 355 | 41th | |
| SWE-bench Verified | 57.9 | 357 | 41th | |
| HumanEval | 74.4 | 353 | 41th | |
| MATH-500 | 72.0 | 366 | 39th | |
| AIME 2025 | 59.3 | 392 | 35th | |
| LiveCodeBench | 57.1 | 394 | 34th | |
| IFEval | 77.5 | 372 | 38th | |
| TruthfulQA | 74.0 | 352 | 41th | |
| HellaSwag | 79.2 | 392 | 35th | |
| MMMU | 63.3 | 397 | 34th | |
| Arena Elo | 1328.8 | 389 | 35th |
What Molmo is good for
Molmo 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 $2.49 per million input tokens (hosted list price) and a 32,768-token context window, it is a practical option for teams that want more control than a closed API allows.
Strengths
- Input price of $2.49 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
- Average benchmark score is below the index median; test it on your own task.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Claude Haiku 4.5 Nano | Anthropic | 8192 | $6.47 | 68.7 |
| Firesearch | Fireworks AI | 32768 | $7.03 | 68.5 |
| Molmo | Allen Institute for AI | 32768 | $2.49 | 68.5 |
| Mixtral Groq Base | Groq | 32768 | $2.66 | 68.4 |
| Hunyuan-Turbo Mini | Tencent | 8192 | $6.59 | 68.3 |
| Molmo Instruct | Allen Institute for AI | 32768 | $2.53 | 68.3 |
FAQ
How much does Molmo cost?
Molmo is listed at $2.49 per million input tokens and $9.45 per million output tokens. Cached input is $0.32 per million tokens. A blended 3:1 input-to-output mix is about $4.23 per million tokens.
What is the context window of Molmo?
Molmo has a context window of 32,768 tokens and can emit up to 16,384 output tokens per request in this index.
Is Molmo open weights?
Yes. Molmo is listed as an open-weight model under a open weights licence.
How does Molmo score on benchmarks?
Molmo averages 68.5 across the scored benchmarks in this index, ranking #379 of 600 models. Its strongest relative result is Arena Elo at 1328.8.
What is Molmo best for?
Molmo 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 $2.49 per million input tokens (hosted list price) and a 32,768-token context window, it is a practical option for teams that want more control than a closed API allows.