Embed 4 Max: pricing, context window and benchmarks
Embed 4 Max is a mid-range model from Cohere. It offers a 8,192-token context window, costs $5.68 per million input tokens and $21.60 per million output tokens, and averages 66.1 across the index's benchmark suite.
Pricing
Embed 4 Max costs $5.68 per million input tokens and $21.60 per million output tokens. A blended 3:1 input-to-output mix works out to about $9.66 per million tokens. Cached input is listed at $0.61 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $5.68 | per 1M tokens |
| Output | $21.60 | per 1M tokens |
| Cached input | $0.61 | per 1M tokens |
| Blended 3:1 | $9.66 | estimate per 1M tokens |
| 1M in + 1M out | $27.28 | 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 | 72.5 | 375 | 38th | |
| GPQA Diamond | 59.0 | 415 | 31th | |
| SWE-bench Verified | 55.1 | 383 | 36th | |
| HumanEval | 69.6 | 401 | 33th | |
| MATH-500 | 64.8 | 420 | 30th | |
| AIME 2025 | 61.5 | 377 | 37th | |
| LiveCodeBench | 58.2 | 386 | 36th | |
| IFEval | 75.3 | 395 | 34th | |
| TruthfulQA | 68.3 | 411 | 32th | |
| HellaSwag | 76.9 | 417 | 31th | |
| MMMU | 66.1 | 370 | 38th | |
| Arena Elo | 1326.3 | 392 | 35th |
What Embed 4 Max is good for
Embed 4 Max 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 $5.68 per million input tokens with a 8,192-token window, check its benchmark profile against the specific task before committing.
Strengths
- Accepts more than text, including image input where the provider supports it.
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 |
|---|---|---|---|---|
| Nemotron Nano | NVIDIA | 8192 | $2.24 | 66.6 |
| Command A Nano | Cohere | 8192 | $5.90 | 66.3 |
| DeepSeek-V3.2 8B | DeepSeek | 32768 | $2.02 | 66.2 |
| Nemotron Nano Chat | NVIDIA | 32768 | $2.21 | 66.2 |
| Embed 4 Max | Cohere | 8192 | $5.68 | 66.1 |
| Sonar Pro Nano | Perplexity | 32768 | $5.50 | 66.1 |
FAQ
How much does Embed 4 Max cost?
Embed 4 Max is listed at $5.68 per million input tokens and $21.60 per million output tokens. Cached input is $0.61 per million tokens. A blended 3:1 input-to-output mix is about $9.66 per million tokens.
What is the context window of Embed 4 Max?
Embed 4 Max has a context window of 8,192 tokens and can emit up to 8,192 output tokens per request in this index.
Is Embed 4 Max open weights?
No. Embed 4 Max is a proprietary model with a proprietary licence, so you cannot download the weights.
How does Embed 4 Max score on benchmarks?
Embed 4 Max averages 66.1 across the scored benchmarks in this index, ranking #395 of 600 models. Its strongest relative result is Arena Elo at 1326.3.
What is Embed 4 Max best for?
Embed 4 Max 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 $5.68 per million input tokens with a 8,192-token window, check its benchmark profile against the specific task before committing.