Primary use stated or inferred cautiously from official documentation.
C
COHERE / embed-v5.0-fast
Cohere Embed 5 Fast
Embedding variant for interactive search, agent queries and high traffic. Accepts text, images and mixed documents in over one hundred languages. Shares Pro's vector space to query existing indexes at a lower text cost.
01 / SUMMARY
The essential
Maximum input capacity when published by the source.
Documented maximum generation limit.
Verified availability channels.
Primary functional family and verified specialties.
Declared terms for API access, model weights, or self-hosting.
02 / TECHNICAL SHEET
Limits and integration
| API ID | embed-v5.0-fast |
|---|---|
| Model type | Embeddings · Vision and documents |
| Access model | Paid proprietary |
| License | Proprietary |
| Deployment | Hosted API |
| Release | 30 SEP 2026 |
| Knowledge cutoff | Not published |
| Entrance | Text · Image · PDF |
| Exit | Vector |
| Context window | 128,000 tokens |
| maximum output | 256, 512, 768, 1,024, 1,536 or 2,048 dimensions |
| Reasoning | Not published |
| Published tools | |
| Structured Outings | Not published |
| Batch processing | Not published |
| Prompt cache | Not published |
| Fine-tuning | Not published |
| Verified platforms | Cohere API · Microsoft Foundry · Amazon SageMaker · Model Vault |
Interactive search, high-volume RAG and agents with repeated queries. Measure real latency and recall; faster indexing does not guarantee identical quality on every document.
Pro and Fast must use the same dimension. The float, int8 and binary outputs can reduce storage, but the impact of compression must be measured. These models produce vectors, not generative answers.
03 / CAPABILITIES
What it can do
Orientation
Interactive search, high-volume RAG and agents with repeated queries. Measure real latency and recall; faster indexing does not guarantee identical quality on every document.
Context
128,000 tokens · 256, 512, 768, 1,024, 1,536 or 2,048 dimensions
Tools and integration
Not published
Access
Cohere API and private deployment
Input modalities
TextImagePDF
04 / PRICES
Documented cost
| Concept | Worth | Unit/condition |
|---|---|---|
| Standard input | 0.08 USD / 1M tokens | Standard API rate |
| Cached input | Not published | Reading reused prefixes |
| Cache write or storage | Not published | The condition varies by provider |
| Standard output | Not published | May include reasoning tokens |
| Batch input | Not published | Asynchronous processing |
| Batch output | Not published | Asynchronous processing |
Text costs 0.12 USD per million tokens for Pro and 0.08 USD for Fast; images cost 0.40 USD for both. Model Vault costs depend on the instance. No Batch discount has been verified.
i Prices change and may depend on level, region or context length. Check the source before making a decision.
05 / EVALUATIONS
How to read the results
“
Results published by Cohere, not measurements by Inferama. RCP-nDCG@10 reorders a fixed candidate set and measures reranking, not first-stage retrieval. Also assess recall, latency and cost on your own documents; do not directly compare these figures with other nDCG metrics.
| Benchmark | Result | Metric | Source |
|---|---|---|---|
| ViDoRe V3 | 84,5 | RCP-nDCG@10 | View source ↗ |
| FinanceBench | 80,0 | RCP-nDCG@10 | View source ↗ |
| FinQA | 88,8 | RCP-nDCG@10 | View source ↗ |
Inferama only highlights a “best result” when the metric, test set, configuration, and date allow for an equivalent comparison. The supplier's figures are presented as claims from its own source.
06 / VERSIONS
Chronology
Cohere Embed 5 Fast
Version added to Inferama's verified catalog.
ANALYSIS
Related analysis
07 / SOURCES