Embed 4 Mini: pricing, context window and benchmarks
Embed 4 Mini is a mid-range model from Cohere. It offers a 4,096-token context window, costs $2.48 per million input tokens and $9.98 per million output tokens, and averages 55.8 across the index's benchmark suite.
Pricing
Embed 4 Mini costs $2.48 per million input tokens and $9.98 per million output tokens. A blended 3:1 input-to-output mix works out to about $4.36 per million tokens. Cached input is listed at $0.20 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $2.48 | per 1M tokens |
| Output | $9.98 | per 1M tokens |
| Cached input | $0.20 | per 1M tokens |
| Blended 3:1 | $4.36 | estimate per 1M tokens |
| 1M in + 1M out | $12.46 | 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 | 63.2 | 486 | 19th | |
| GPQA Diamond | 52.3 | 496 | 17th | |
| SWE-bench Verified | 43.4 | 485 | 19th | |
| HumanEval | 60.4 | 497 | 17th | |
| MATH-500 | 54.6 | 523 | 13th | |
| AIME 2025 | 43.9 | 508 | 15th | |
| LiveCodeBench | 42.9 | 517 | 14th | |
| IFEval | 67.4 | 495 | 18th | |
| TruthfulQA | 60.5 | 524 | 13th | |
| HellaSwag | 73.0 | 482 | 20th | |
| MMMU | 51.8 | 533 | 11th | |
| Arena Elo | 1233.2 | 524 | 13th |
What Embed 4 Mini is good for
Embed 4 Mini 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 $2.48 per million input tokens with a 4,096-token window, check its benchmark profile against the specific task before committing.
Strengths
- Input price of $2.48 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 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 |
|---|---|---|---|---|
| Gemma 3 7B | Google DeepMind | 32768 | $0.90 | 55.9 |
| Pythia Base | EleutherAI | 16384 | $0.99 | 55.9 |
| Yi-Lightning 7B | 01.AI | 32768 | $1.00 | 55.9 |
| Embed 4 Mini | Cohere | 4096 | $2.48 | 55.8 |
| Firesearch Nano | Fireworks AI | 8192 | $2.49 | 55.6 |
| Llama 3 DeepInfra 7B | DeepInfra | 16384 | $0.95 | 55.6 |
FAQ
How much does Embed 4 Mini cost?
Embed 4 Mini is listed at $2.48 per million input tokens and $9.98 per million output tokens. Cached input is $0.20 per million tokens. A blended 3:1 input-to-output mix is about $4.36 per million tokens.
What is the context window of Embed 4 Mini?
Embed 4 Mini 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 Mini open weights?
No. Embed 4 Mini is a proprietary model with a proprietary licence, so you cannot download the weights.
How does Embed 4 Mini score on benchmarks?
Embed 4 Mini averages 55.8 across the scored benchmarks in this index, ranking #510 of 600 models. Its strongest relative result is Arena Elo at 1233.2.
What is Embed 4 Mini best for?
Embed 4 Mini 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 $2.48 per million input tokens with a 4,096-token window, check its benchmark profile against the specific task before committing.