Embed 4 Nano: pricing, context window and benchmarks
Embed 4 Nano is a mid-range model from Cohere. It offers a 8,192-token context window, costs $1.48 per million input tokens and $6.14 per million output tokens, and averages 49.7 across the index's benchmark suite.
Pricing
Embed 4 Nano costs $1.48 per million input tokens and $6.14 per million output tokens. A blended 3:1 input-to-output mix works out to about $2.64 per million tokens. Cached input is listed at $0.13 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $1.48 | per 1M tokens |
| Output | $6.14 | per 1M tokens |
| Cached input | $0.13 | per 1M tokens |
| Blended 3:1 | $2.64 | estimate per 1M tokens |
| 1M in + 1M out | $7.62 | 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 | 54.5 | 575 | 4th | |
| GPQA Diamond | 45.6 | 560 | 7th | |
| SWE-bench Verified | 33.1 | 571 | 5th | |
| HumanEval | 55.2 | 540 | 10th | |
| MATH-500 | 52.4 | 537 | 11th | |
| AIME 2025 | 33.5 | 575 | 4th | |
| LiveCodeBench | 40.3 | 535 | 11th | |
| IFEval | 61.0 | 564 | 6th | |
| TruthfulQA | 55.6 | 570 | 5th | |
| HellaSwag | 69.8 | 537 | 11th | |
| MMMU | 46.2 | 578 | 4th | |
| Arena Elo | 1207.9 | 547 | 9th |
What Embed 4 Nano is good for
Embed 4 Nano is a general-purpose model in the index. It handles text generation, summarization and question answering, and it can be a sensible default when you need a balance of quality, price and context. At $1.48 per million input tokens with a 8,192-token window, check its benchmark profile against the specific task before committing.
Strengths
- Input price of $1.48 per million tokens is at or below the index median.
Trade-offs
- Proprietary licence: you cannot download the weights or self-host the model.
- Context window of 8,192 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 |
|---|---|---|---|---|
| Codestral 1.5B | Mistral AI | 8192 | $0.52 | 49.9 |
| Molmo 8B | Allen Institute for AI | 32768 | $0.44 | 49.9 |
| Llama 3.1 Turbo 1.5B | Together AI | 16384 | $0.46 | 49.8 |
| Seed-OSS 1.5B | ByteDance | 4096 | $0.45 | 49.8 |
| Embed 4 Nano | Cohere | 8192 | $1.48 | 49.7 |
| Llama 3 Modal 1.5B | Modal | 4096 | $0.42 | 49.7 |
FAQ
How much does Embed 4 Nano cost?
Embed 4 Nano is listed at $1.48 per million input tokens and $6.14 per million output tokens. Cached input is $0.13 per million tokens. A blended 3:1 input-to-output mix is about $2.64 per million tokens.
What is the context window of Embed 4 Nano?
Embed 4 Nano has a context window of 8,192 tokens and can emit up to 4,096 output tokens per request in this index.
Is Embed 4 Nano open weights?
No. Embed 4 Nano is a proprietary model with a proprietary licence, so you cannot download the weights.
How does Embed 4 Nano score on benchmarks?
Embed 4 Nano averages 49.7 across the scored benchmarks in this index, ranking #561 of 600 models. Its strongest relative result is Arena Elo at 1207.9.
What is Embed 4 Nano best for?
Embed 4 Nano is a general-purpose model in the index. It handles text generation, summarization and question answering, and it can be a sensible default when you need a balance of quality, price and context. At $1.48 per million input tokens with a 8,192-token window, check its benchmark profile against the specific task before committing.