Cohere is an enterprise AI company whose Command, North, Aya, Embed, Rerank, Parse and Transcribe models are offered through the Cohere API, private deployments and partner clouds, and its line-up changed several times in 2026. This hub lists every model in Cohere's public documentation as of 15 November 2026, with model IDs, release dates, context windows, prices, availability, licences and retirement dates. It is written for developers, buyers, architects and anyone who needs to know which Cohere model is which. Models are listed by release date, newest first, an objective order that implies no ranking. Every fact comes from Cohere's own documentation, pricing page, changelog or Cohere Labs model cards, cited in the sources list.
Last checked: 2026-11-15.
This is an independent reference page from NHI Mgmt Group based on public provider documentation; it is not sponsored or endorsed by any provider. It uses Cohere's public documentation as of November 2026. Model details change, so confirm against Cohere's current documentation.
Key takeaways
- Seven model families are live. Cohere's models page lists Command, North, Embed, Rerank, Parse, Transcribe and Aya models; the newest generative model in the Command line is Command A+ (command-a-plus-05-2026), announced on 20 May 2026.
- Context runs from 8K to 256K tokens. Command A, Command A Reasoning and North Mini Code list 256K; Command A+, Command A Vision and the Command R models list 128K; Tiny Aya and Command A Translate list 8K.
- Public token prices cover legacy models only. The pricing page lists per-token rates for Command, Command R and Aya Expanse, and per-GPU hourly rates for Model Vault; current Command, Embed 5 and Rerank 5 token prices are not stated on the public pricing page.
- Several models have open weights. Cohere Labs publishes Command A+ under Apache 2.0, and Command A and Tiny Aya under CC-BY-NC 4.0; Cohere describes Cohere Transcribe as an open source model.
- Retirements are dated. Embed v2 models and Aya Expanse 8B and Aya Vision 8B were retired on 4 April 2026, and the original Command, Command Light, Command R and Command R+ were deprecated effective 15 September 2025.
What is Cohere?
Cohere builds language, embedding, reranking, document parsing and speech models for enterprise use, and its research arm, Cohere Labs, publishes model weights on Hugging Face. Its documentation groups models by endpoint: Chat (Command, North, Aya), Embed, Rerank, Parse and Audio Transcriptions. Model IDs carry a month and year suffix, such as command-a-03-2025, or a version number, such as embed-v5.0-pro.
Cohere sells access through Trial and Production API keys, Model Vault dedicated GPU capacity and private deployment. The main table lists the generative and speech models; Embed and Rerank models follow with their own fields. Facts are as of 15 November 2026.
Current Cohere models at a glance
As of 2026-11-15. Source: Cohere models page, changelog and Cohere Labs model cards. Models are listed by release date, newest first; where the changelog gives no date, the month comes from the model ID. Category is the Cohere model family.
| Model | API ID or version | Category | Context | Licence | Status |
|---|---|---|---|---|---|
| North Small Translate 1.0 | north-small-translate-1.0 | North | 16K | Not stated by Cohere | Live (evaluation on the Cohere API) |
| Parse v5.0 | parse-v5.0 | Parse | Not stated by Cohere | Not stated by Cohere | Live |
| Cohere Transcribe Arabic | cohere-transcribe-arabic-07-2026 | Transcribe | Not stated by Cohere (25MB file limit) | Not stated by Cohere | Live |
| North Mini Code 1.0 | north-mini-code-1.0 | North | 256K | Not stated by Cohere | Live (evaluation; production via Model Vault) |
| Command A+ | command-a-plus-05-2026 | Command | 128K | Apache 2.0 (weights) | Live |
| Cohere Transcribe | cohere-transcribe-03-2026 | Transcribe | Not stated by Cohere (25MB file limit) | Described by Cohere as open source | Live |
| Tiny Aya (Global, Earth, Fire, Water) | tiny-aya-global, tiny-aya-earth, tiny-aya-fire, tiny-aya-water | Aya | 8K | CC-BY-NC 4.0 (weights) | Live |
| Command A Reasoning | command-a-reasoning-08-2025 | Command | 256K | Not stated by Cohere | Live |
| Command A Translate | command-a-translate-08-2025 | Command | 8K | Not stated by Cohere | Live |
| Command A Vision | command-a-vision-07-2025 | Command | 128K | Not stated by Cohere | Live |
| Command A | command-a-03-2025 | Command | 256K | CC-BY-NC 4.0 (weights) | Live |
| Command R7B | command-r7b-12-2024 | Command | 128K | Not stated by Cohere | Live |
| Command R and Command R+ (08-2024) | command-r-08-2024, command-r-plus-08-2024 | Command | 128K | Not stated by Cohere | Live |
| Aya Expanse 32B and Aya Vision 32B | c4ai-aya-expanse-32b, c4ai-aya-vision-32b | Aya | 128K and 16K | Not stated by Cohere | Live |
Command A+ and Command A Vision accept text and images; Aya Vision 32B accepts text and images; the other Chat models in the table are text in, text out. The Transcribe models take audio and return text. See Open-Weight vs Closed Models Explained.
Key facts for the main Cohere models
As of 2026-11-15. Identical fields for every model; "Not stated by Cohere" means not stated by Cohere on the pages checked (2026-11-15).
| Model | Released | Max output | Knowledge cutoff | Input / output | Open weights | Parameters | Positioning (provider wording) |
|---|---|---|---|---|---|---|---|
| North Small Translate 1.0 | 2026-09-09 | 16K | Not stated by Cohere | Text / text | Not stated by Cohere | 218B total, 25B active (MoE) | Machine translation across 50+ languages |
| North Mini Code 1.0 | 2026-06-09 | 64K | Not stated by Cohere | Text / text | Not stated by Cohere | 30B total, 3B active (MoE) | Agentic coding |
| Command A+ | 2026-05-20 | 64K | Not stated by Cohere | Text, image / text | Yes (Apache 2.0) | 218B total, 25B active (MoE) | First Mixture of Experts model in the Command A family, adding vision, agentic, reasoning and translation |
| Tiny Aya Global | 2026 (ID undated) | 8K | Not stated by Cohere | Text / text | Yes (CC-BY-NC 4.0) | 3.35B | Balanced coverage across regions, 70 languages |
| Command A Reasoning | 2025-08 (from ID) | 32K | Not stated by Cohere | Text / text | Not stated by Cohere | Not stated by Cohere | Cohere's first reasoning model, 23 languages |
| Command A Vision | 2025-07 (from ID) | 8K | Not stated by Cohere | Text, image / text | Not stated by Cohere | Not stated by Cohere | Charts, tables, OCR and document question answering |
| Command A | 2025-03 (from ID) | 8K | Not stated by Cohere | Text / text | Yes (CC-BY-NC 4.0) | 111B | Tool use, agents, RAG and multilingual tasks; runs on two GPUs |
| Command R7B | 2024-12 (from ID) | 4K | Not stated by Cohere | Text / text | Not stated by Cohere | Not stated by Cohere | Small, fast model for RAG, tool use and agents |
Embed and Rerank models
As of 2026-11-15. Source: Cohere models page and changelog. Max output tokens do not apply to these models.
| Model ID | Released | Modalities | Context | Dimensions or notes |
|---|---|---|---|---|
| rerank-v5.0-pro, rerank-v5.0-fast | 2026-10-21 | Text | 32K | Multilingual, handles JSON, Context Focus and calibrated scores |
| embed-v5.0-pro, embed-v5.0-fast | 2026-09-30 | Text, images, mixed (e.g. PDFs) | 128K | 256 to 2048 dimensions, default 2048 |
| rerank-v4.0-pro, rerank-v4.0-fast | Not stated by Cohere | Text | 32K | Previous generation; v5.0 recommended for new projects |
| embed-v4.0 | Not stated by Cohere | Text, images, mixed | 128K | 256 to 1536 dimensions, default 1536; Embed Jobs supported |
| rerank-v3.5, rerank-english-v3.0, rerank-multilingual-v3.0 | Not stated by Cohere | Text | 4K | v3 series |
| embed-english-v3.0, embed-multilingual-v3.0 and light variants | Not stated by Cohere | Text, images (as listed) | 512 | 1024 or 384 dimensions, cosine |
See the RAG Security Guide for the controls that apply when embedding and reranking models sit inside a retrieval pipeline.
Cohere model families and naming
- Command: the main generative line, from Command R and R+ (2024) to Command A (March 2025), its Reasoning, Vision and Translate variants, and Command A+ (May 2026).
- North: two models on the Cohere API for evaluation as of November 2026: North Mini Code 1.0 for agentic coding and North Small Translate 1.0 for translation across 50+ languages.
- Aya: Cohere Labs multilingual models: Tiny Aya (3.35B, four regional variants, 70 languages), Aya Expanse 32B and Aya Vision 32B.
- Embed and Rerank: retrieval models in pro and fast variants from version 4.0 onward; version 5.0 is the latest of each.
- Parse: parse-v5.0, a vision model that extracts structured data from enterprise documents.
- Transcribe: speech-to-text, with a general multilingual model and an Arabic fine-tune.
- IDs: Chat model IDs end in a month and year (command-a-plus-05-2026 is May 2026); retrieval models use a version number. Some older IDs were aliases, for example command-r pointed to command-r-03-2024. See LLM Naming and Versioning Explained.
When was each Cohere model released?
As of 2026-11-15. Dates are from the Cohere changelog; earlier rows use the month in the model ID, as the changelog pages checked give no announcement date for them.
| Date | Event | API ID |
|---|---|---|
| 2024-08 (from ID) | Command R and Command R+ August 2024 updates | command-r-08-2024, command-r-plus-08-2024 |
| 2024-12 (from ID) | Command R7B | command-r7b-12-2024 |
| 2025-03 (from ID) | Command A | command-a-03-2025 |
| 2025-07 and 2025-08 (from IDs) | Command A Vision, Command A Translate and Command A Reasoning | command-a-vision-07-2025, command-a-translate-08-2025, command-a-reasoning-08-2025 |
| 2025-09-15 | Original Command, Command Light, Command R and Command R+ deprecated | command, command-light, command-r-03-2024, command-r-plus-04-2024 |
| 2026-03 (from ID) | Cohere Transcribe | cohere-transcribe-03-2026 |
| 2026-04-04 | Embed v2 and Aya 8B models retired | embed-english-v2.0, c4ai-aya-expanse-8b, c4ai-aya-vision-8b and others |
| 2026-05-20 | Command A+ announced | command-a-plus-05-2026 |
| 2026-06-09 | North Mini Code announced | north-mini-code-1.0 |
| 2026-07-07 | Cohere Transcribe Arabic announced | cohere-transcribe-arabic-07-2026 |
| 2026-08-27 | Parse announced | parse-v5.0 |
| 2026-09-09 | North Small Translate announced | north-small-translate-1.0 |
| 2026-09-30 | Embed 5 announced | embed-v5.0-pro, embed-v5.0-fast |
| 2026-10-21 | Rerank 5 announced | rerank-v5.0-pro, rerank-v5.0-fast |
| 2026-11-03 | Open models in Model Vault; Model Vault Encrypted described | Not applicable |
| 2026-11-04 | Embed 5 and Rerank 5 available on OpenRouter | embed-v5.0-pro, rerank-v5.0-pro and fast variants |
The latest model release is Rerank 5, announced on 21 October 2026. The latest Command model is Command A+ (20 May 2026).
How much do Cohere models cost?
As of 2026-11-15. USD per million tokens (MTok) for token-priced models. Source: Cohere pricing page. The public pricing page lists per-token rates only for legacy models for existing customers and Aya Expanse; "Not stated" means not stated by Cohere.
| Model | Input | Cached input | Output | Batch | Cache write | Notes |
|---|---|---|---|---|---|---|
| Command R+ 08-2024 | $2.50 | Not stated | $10.00 | Not stated | Not stated | Legacy, existing customers |
| Command R+ 04-2024 | $3.00 | Not stated | $15.00 | Not stated | Not stated | Legacy, existing customers |
| Command R 03-2024 | $0.50 | Not stated | $1.50 | Not stated | Not stated | Legacy, existing customers |
| Command | $1.00 | Not stated | $2.00 | Not stated | Not stated | Legacy, existing customers |
| Command Light | $0.30 | Not stated | $0.60 | Not stated | Not stated | Legacy, existing customers |
| Aya Expanse (8B and 32B) | $0.50 | Not stated | $1.50 | Not stated | Not stated | 8B retired 2026-04-04 |
| Command A+, Command A family, North, Embed 5, Rerank 5 | Not stated by Cohere | Not on the public pricing page checked (2026-11-15) | ||||
Model Vault pricing
As of 2026-11-15. USD per GPU per hour. The pricing page shows an on-demand price and a promotional price valid through 31 March 2027; pricing is per GPU and replica, and reserved or committed capacity is through sales.
| GPU | On-demand | Promotional (to 2027-03-31) |
|---|---|---|
| L4 24GB | $3.00 | $1.00 |
| A100 40GB | $3.25 | $2.25 |
| A100 80GB | $3.50 | $2.25 |
| MI300X 192GB | $6.00 | $4.00 |
| H100 80GB | $6.25 | $4.25 |
| H100 80GB (Encrypted) | $9.00 | $4.25 |
| H200 141GB | $7.25 | $5.50 |
| B200 192GB | $9.75 | $8.00 |
| B200 192GB (Encrypted) | $12.00 | $8.00 |
| GB200 192GB | $12.50 | $10.00 |
- Rerank billing unit: one search unit is one query with up to 100 documents; documents over 500 tokens, counting the query, are split into chunks and each chunk counts as a document.
- Trial keys: free and rate limited, not permitted for production or commercial use.
- Billing: invoices are issued at the end of each calendar month or when the outstanding balance reaches $250.
- OpenRouter: Embed 5 and Rerank 5 prices on OpenRouter are listed on each model's OpenRouter page, per the 4 November 2026 changelog entry.
See Model Pricing Explained, the LLM Pricing Tracker and How to set spend limits on LLM API keys.
Where are Cohere models available?
- First-party: the Cohere API (Chat, Embed, Rerank, Parse and Audio Transcriptions endpoints), with Trial and Production keys.
- Model Vault: dedicated GPU capacity priced per GPU hour, with an Encrypted variant that uses confidential computing; North Mini Code supports production deployment through Model Vault, and open models were added to Model Vault on 3 November 2026.
- Cloud platforms: Cohere's platform support page lists Amazon Bedrock, Amazon SageMaker, Azure and Oracle OCI, each supporting a subset of features. Chat, Embed and Rerank are listed for Bedrock, SageMaker and Azure; Chat and Embed for OCI.
- Private deployment: on-premises or isolated VPC deployments, with all SDK features listed as supported.
- Other channels: Cohere Transcribe is on Microsoft Foundry as coherelabs-cohere-transcribe-03-2026; North Mini Code is on OpenRouter as cohere/north-mini-code:free; Embed 5 and Rerank 5 are on OpenRouter.
- Open weights: Command A+, Command A and Tiny Aya weights are on Hugging Face under Cohere Labs.
Confirm the exact model ID in the chosen cloud's catalogue and region.
Restricted-access Cohere models
As of 2026-11-15. Source: Cohere models page, pricing page and deprecations page.
| Model | Access stated by provider | Data retention condition |
|---|---|---|
| North Small Translate 1.0 | Available on the Cohere API for evaluation | Not stated by Cohere |
| North Mini Code 1.0 | Available on the Cohere API for evaluation; production deployment through Model Vault | Model Vault: zero data retention by default |
| Legacy Command and Command R 03/04-2024 models | Deprecated: unavailable to new customers; existing users (use within 90 days of the announcement) keep access until shutdown | Not stated by Cohere |
Cohere's documentation names no model that is limited to a verified or invited group of organisations.
What is the context window of Cohere models?
Command A, Command A Reasoning and North Mini Code list 256K-token context; Command A+, Command A Vision, Command R7B, the Command R models, Aya Expanse 32B and the Embed v4 and v5 models list 128K. North Small Translate lists 16K, Aya Vision 32B 16K, and Tiny Aya and Command A Translate 8K. Rerank v4 and v5 accept 32K and Rerank v3 4K. Max output is 64K on Command A+ and North Mini Code, 32K on Command A Reasoning, 8K on Command A and its Vision and Translate variants, and 4K on Command R models. The Command A model card notes that the model supports 256K but is configured in Hugging Face for 128K. See Context Windows Explained.
Is any Cohere model open source?
Some are. The Cohere Labs Hugging Face cards publish Command A+ weights under Apache 2.0, and Command A (111B, described as an open weights research release) and Tiny Aya under CC-BY-NC 4.0, a non-commercial licence; the CC-BY-NC cards also require adherence to the Cohere Labs Acceptable Use Policy. Cohere's models page describes Cohere Transcribe as an open source model. Licences for the other models are not stated on the pages checked. See the Open-Weight Model Licence Tracker.
Model cards and system cards
As of 2026-11-15.
| Model | Model card or page | System card | Technical report |
|---|---|---|---|
| Command A+ | Cohere Labs Hugging Face card (architecture, languages, licence, hardware) | Not stated by Cohere on the pages checked (2026-11-15) | Not stated by Cohere on the pages checked |
| Command A | Cohere Labs Hugging Face card | Not stated by Cohere on the pages checked (2026-11-15) | Paper linked from the card (published 1 April 2025) |
| Tiny Aya | Cohere Labs Hugging Face card | Not stated by Cohere on the pages checked (2026-11-15) | Paper "Tiny Aya: Bridging Scale and Multilingual Depth" linked from the card |
| Other models listed above | Models page entry (ID, context, max output, modality, endpoint) | Not stated by Cohere on the pages checked (2026-11-15) | Not stated by Cohere |
See Model Cards and System Cards Explained.
Benchmarks
As of 2026-11-15. Provider-reported and independent results are kept in separate columns.
| Model | Provider-reported benchmarks | Independent leaderboard results |
|---|---|---|
| Command A+ | Not stated on the model card (card refers to the Cohere blog) | None cited on this page |
| Command A | GPQA Diamond 50.51 (Cohere Labs model card) | None cited on this page |
| Tiny Aya Global | GPQA Diamond 28.28 (Cohere Labs model card) | None cited on this page |
| North, Embed 5, Rerank 5 | Not stated on the pages checked | None cited on this page |
See How to Read LLM Benchmarks.
Deprecations and retirements
As of 2026-11-15. Source: Cohere deprecations page and changelog. Cohere's lifecycle stages are Active, Legacy, Deprecated and Shutdown; impacted customers are notified by email, documentation and blog posts, and the page states no minimum notice period in days.
| Model | API ID | Deprecated or notice | Retirement or shutdown | Stated replacement |
|---|---|---|---|---|
| Embed English v2, Light v2, Multilingual v2 | embed-english-v2.0, embed-english-light-v2.0, embed-multilingual-v2.0 | Not stated by Cohere | 2026-04-04 (retired) | embed-english-v3.0, embed-multilingual-v3.0 or embed-v4.0 |
| Aya Expanse 8B, Aya Vision 8B | c4ai-aya-expanse-8b, c4ai-aya-vision-8b | Not stated by Cohere | 2026-04-04 (retired) | command-r7b-12-2024, command-a-03-2025 or command-a-reasoning-08-2025 |
| Command R (03-2024), Command R+ (04-2024) and aliases | command-r-03-2024, command-r-plus-04-2024, command-r, command-r-plus | Effective 2025-09-15 | Not stated by Cohere | command-r-08-2024, command-r-plus-08-2024 or command-a-03-2025 |
| Command, Command Light | command, command-light | Effective 2025-09-15 | Not stated by Cohere | command-r-08-2024, command-r-plus-08-2024 or command-a-03-2025 |
| Rerank v2 | rerank-english-v2.0, rerank-multilingual-v2.0 | 2024-12-02 | 2025-04-30 (retired) | rerank-v3.5 |
| Rerank v4 | rerank-v4.0-pro, rerank-v4.0-fast | N/A (live, previous generation) | Not stated by Cohere | rerank-v5.0-pro or rerank-v5.0-fast recommended for new projects |
Endpoints and features deprecated effective 15 September 2025 include /v1/generate, /v1/summarize, /v1/classify and /v1/connectors; fine-tuning for older models was retired on the same date. See the AI Model Retirement Guide.
Data handling and security
- Training use: Cohere's enterprise data commitments page states that enterprise customers can opt out in the dashboard data settings, after which prompts and generations are not used to train Cohere models; the opt-out applies to data created after the change.
- Default retention: on the SaaS platform, logged prompts and generations are deleted after 30 days, except where retention is required by law or contract or usage is flagged as violating Cohere's terms.
- Zero data retention (ZDR): offered to enterprise customers who make additional usage commitments, on request to Cohere support; Cohere still receives usage data. Model Vault has zero data retention by default, per the 3 November 2026 changelog.
- Private and partner deployments: for on-premises, isolated VPC and third-party cloud deployments, Cohere states it does not access or process customer prompts or generations.
- Confidential compute: Model Vault Encrypted uses confidential computing so that neither Cohere nor the cloud provider can see prompts or responses.
- Key handling: generic controls apply to every provider's API: keep keys out of code, scope and rotate them, and set spend limits.
See AI Data Retention and Deletion and the Open-Weight Model Security Guide for self-hosted weights.
How to choose a Cohere model: factual criteria
- Task and endpoint: Chat models for generation, Embed and Rerank for retrieval, Parse for document extraction, Transcribe for audio.
- Modality: image input is listed for Command A+, Command A Vision and Aya Vision 32B.
- Context and output: 256K context on Command A, Command A Reasoning and North Mini Code; 64K output on Command A+ and North Mini Code.
- Licence: Apache 2.0 for Command A+ weights; CC-BY-NC 4.0 (non-commercial) for Command A and Tiny Aya weights.
- Pricing route: confirm token prices for current models with Cohere, or compare Model Vault GPU hours, noting the promotional period ends 31 March 2027.
- Retention: SaaS logs are kept 30 days by default; ZDR, Model Vault and private deployment change that.
- Lifecycle: avoid deprecated IDs and check the Legacy and Deprecated stages before building.
- Platform: confirm the model ID and feature set on Bedrock, SageMaker, Azure or OCI, as each supports a subset.
Practitioner checklist
- Pin production code to a dated model ID, not an alias, and record it in the AI inventory.
- Replace any remaining calls to command, command-light, command-r or command-r-plus aliases and to /v1/generate or /v1/summarize.
- Confirm that no workload still calls the Embed v2 or Aya 8B IDs retired on 4 April 2026.
- Use Production keys for commercial workloads; Trial keys are not permitted for production use.
- Set the training opt-out in the dashboard data settings, or request ZDR, before sending sensitive data.
- Check the licence on the Hugging Face card before self-hosting Command A or Tiny Aya commercially.
- Store Cohere API keys in a secrets manager and set spend limits. See the LLMjacking Guide.
Standards and references
- Cohere: Models overview (accessed 2026-11-15)
- Cohere: Pricing (accessed 2026-11-15)
- Cohere: Deprecations (accessed 2026-11-15)
- Cohere: Changelog (accessed 2026-11-15)
- Cohere: Enterprise data commitments (accessed 2026-11-15)
- Cohere: Platform support (accessed 2026-11-15)
- Cohere Labs: Command A+ model card (accessed 2026-11-15)
- Cohere Labs: Command A model card (accessed 2026-11-15)
- Cohere Labs: Tiny Aya Global model card (accessed 2026-11-15)
Related NHI Mgmt Group resources: Cohere Command A family, LLM Release Tracker, Reasoning Models Explained, LLM Security Guide.