Embed 4: pricing, context window and benchmarks
Embed 4 is a mid-range model from Cohere. It offers a 32,768-token context window, costs $4.79 per million input tokens and $20.86 per million output tokens, and averages 63.8 across the index's benchmark suite.
Pricing
Embed 4 costs $4.79 per million input tokens and $20.86 per million output tokens. A blended 3:1 input-to-output mix works out to about $8.81 per million tokens. Cached input is listed at $0.49 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $4.79 | per 1M tokens |
| Output | $20.86 | per 1M tokens |
| Cached input | $0.49 | per 1M tokens |
| Blended 3:1 | $8.81 | estimate per 1M tokens |
| 1M in + 1M out | $25.65 | 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 | 67.9 | 419 | 30th | |
| GPQA Diamond | 61.6 | 393 | 35th | |
| SWE-bench Verified | 51.7 | 408 | 32th | |
| HumanEval | 69.3 | 406 | 32th | |
| MATH-500 | 66.0 | 412 | 31th | |
| AIME 2025 | 54.1 | 422 | 30th | |
| LiveCodeBench | 54.3 | 411 | 32th | |
| IFEval | 73.5 | 410 | 32th | |
| TruthfulQA | 69.9 | 401 | 33th | |
| HellaSwag | 75.3 | 436 | 27th | |
| MMMU | 58.2 | 455 | 24th | |
| Arena Elo | 1286.4 | 437 | 27th |
What Embed 4 is good for
Embed 4 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 $4.79 per million input tokens with a 32,768-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.
- Average benchmark score is below the index median; test it on your own task.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| DeepSeek-R1 8B | DeepSeek | 16384 | $1.87 | 64.3 |
| Embed 4 Turbo | Cohere | 4096 | $5.13 | 64.0 |
| Embed 4 | Cohere | 32768 | $4.79 | 63.8 |
| SmolLM3 Instruct | Hugging Face | 8192 | $1.69 | 63.6 |
| Embed 4 Pro | Cohere | 4096 | $5.05 | 63.5 |
| Llama 4 Maverick 8B | Meta AI | 4096 | $1.64 | 63.4 |
FAQ
How much does Embed 4 cost?
Embed 4 is listed at $4.79 per million input tokens and $20.86 per million output tokens. Cached input is $0.49 per million tokens. A blended 3:1 input-to-output mix is about $8.81 per million tokens.
What is the context window of Embed 4?
Embed 4 has a context window of 32,768 tokens and can emit up to 8,192 output tokens per request in this index.
Is Embed 4 open weights?
No. Embed 4 is a proprietary model with a proprietary licence, so you cannot download the weights.
How does Embed 4 score on benchmarks?
Embed 4 averages 63.8 across the scored benchmarks in this index, ranking #411 of 600 models. Its strongest relative result is Arena Elo at 1286.4.
What is Embed 4 best for?
Embed 4 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 $4.79 per million input tokens with a 32,768-token window, check its benchmark profile against the specific task before committing.