Molmo Instruct: pricing, context window and benchmarks
Molmo Instruct is a open-weight model from Allen Institute for AI. It offers a 32,768-token context window, costs $2.53 per million input tokens and $9.23 per million output tokens, and averages 68.3 across the index's benchmark suite.
Pricing
Molmo Instruct costs $2.53 per million input tokens and $9.23 per million output tokens. A blended 3:1 input-to-output mix works out to about $4.21 per million tokens. Cached input is listed at $0.37 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $2.53 | per 1M tokens |
| Output | $9.23 | per 1M tokens |
| Cached input | $0.37 | per 1M tokens |
| Blended 3:1 | $4.21 | estimate per 1M tokens |
| 1M in + 1M out | $11.76 | 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 | 74.7 | 341 | 43th | |
| GPQA Diamond | 61.4 | 395 | 34th | |
| SWE-bench Verified | 57.4 | 364 | 39th | |
| HumanEval | 74.6 | 351 | 42th | |
| MATH-500 | 68.5 | 393 | 35th | |
| AIME 2025 | 62.2 | 375 | 38th | |
| LiveCodeBench | 57.8 | 391 | 35th | |
| IFEval | 75.9 | 390 | 35th | |
| TruthfulQA | 73.6 | 364 | 39th | |
| HellaSwag | 79.5 | 387 | 36th | |
| MMMU | 65.7 | 375 | 38th | |
| Arena Elo | 1350.5 | 363 | 40th |
What Molmo Instruct is good for
Molmo 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 $2.53 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 $2.53 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 |
|---|---|---|---|---|
| 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 |
| Sonar Mini | Perplexity | 65536 | $6.52 | 67.9 |
FAQ
How much does Molmo Instruct cost?
Molmo Instruct is listed at $2.53 per million input tokens and $9.23 per million output tokens. Cached input is $0.37 per million tokens. A blended 3:1 input-to-output mix is about $4.21 per million tokens.
What is the context window of Molmo Instruct?
Molmo Instruct has a context window of 32,768 tokens and can emit up to 16,384 output tokens per request in this index.
Is Molmo Instruct open weights?
Yes. Molmo Instruct is listed as an open-weight model under a open weights licence.
How does Molmo Instruct score on benchmarks?
Molmo Instruct averages 68.3 across the scored benchmarks in this index, ranking #382 of 600 models. Its strongest relative result is Arena Elo at 1350.5.
What is Molmo Instruct best for?
Molmo 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 $2.53 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.