Embed 4 Pro: pricing, context window and benchmarks
Embed 4 Pro is a mid-range model from Cohere. It offers a 4,096-token context window, costs $5.05 per million input tokens and $19.40 per million output tokens, and averages 63.5 across the index's benchmark suite.
Pricing
Embed 4 Pro costs $5.05 per million input tokens and $19.40 per million output tokens. A blended 3:1 input-to-output mix works out to about $8.64 per million tokens. Cached input is listed at $0.52 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $5.05 | per 1M tokens |
| Output | $19.40 | per 1M tokens |
| Cached input | $0.52 | per 1M tokens |
| Blended 3:1 | $8.64 | estimate per 1M tokens |
| 1M in + 1M out | $24.45 | 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 | 69.3 | 404 | 33th | |
| GPQA Diamond | 61.3 | 397 | 34th | |
| SWE-bench Verified | 52.0 | 405 | 33th | |
| HumanEval | 68.0 | 414 | 31th | |
| MATH-500 | 63.8 | 427 | 29th | |
| AIME 2025 | 53.2 | 431 | 28th | |
| LiveCodeBench | 52.2 | 426 | 29th | |
| IFEval | 72.8 | 419 | 30th | |
| TruthfulQA | 66.8 | 433 | 28th | |
| HellaSwag | 78.6 | 397 | 34th | |
| MMMU | 60.5 | 423 | 30th | |
| Arena Elo | 1316.6 | 399 | 34th |
What Embed 4 Pro is good for
Embed 4 Pro 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 $5.05 per million input tokens with a 4,096-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 4,096 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 |
|---|---|---|---|---|
| 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 |
| Fusion Mini | OpenRouter | 4096 | $4.89 | 63.3 |
| Firefunction Mini | Fireworks AI | 32768 | $4.63 | 63.2 |
FAQ
How much does Embed 4 Pro cost?
Embed 4 Pro is listed at $5.05 per million input tokens and $19.40 per million output tokens. Cached input is $0.52 per million tokens. A blended 3:1 input-to-output mix is about $8.64 per million tokens.
What is the context window of Embed 4 Pro?
Embed 4 Pro has a context window of 4,096 tokens and can emit up to 4,096 output tokens per request in this index.
Is Embed 4 Pro open weights?
No. Embed 4 Pro is a proprietary model with a proprietary licence, so you cannot download the weights.
How does Embed 4 Pro score on benchmarks?
Embed 4 Pro averages 63.5 across the scored benchmarks in this index, ranking #413 of 600 models. Its strongest relative result is Arena Elo at 1316.6.
What is Embed 4 Pro best for?
Embed 4 Pro 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 $5.05 per million input tokens with a 4,096-token window, check its benchmark profile against the specific task before committing.