LLM Availability Overview
8 min read
Overview
Unique can connect to almost any Large Language Model (LLM), whether it is an open-source model or a proprietary one. Depending on the LLM and the deployment model of Unique, using a non-standard model (e.g. Azure OpenAI) may have certain implications.
Unique can tailor the selection of LLMs based on each Space and use case, ensuring you have access to the most suitable models for your specific needs to increase accuracy.
Proprietary LLM API Providers
We can connect your Unique deployment to any AI platform of your choice. Examples include OpenAI, Anthropic, and Google Cloud.
Connecting a third-party AI platform means data will leave your tenant or on-premise system. Our AI Governance team reviews each request to connect a third-party provider and ensures that the provider adheres to our strict data privacy and AI safety guidelines.
For customers on our US tenant we have vetted and support
Anthropic (Claude Opus, Sonnet, and Haiku )
OpenAI (GPT-5 and later)
Together AI (LLaMA, DeepSeek, Qwen, and other open-source models)
Google (Gemini 3.0+ Pro and Flash)
You can use any model supported by these platforms. If the account on the platform is managed by Unique, you will benefit from our negotiated rate limits and pricing.
We also optionally support a bring-your-own-API-key model, allowing you to sign up and manage the relationship with the third-party provider yourself. This option is only available for single-tenant, customer-managed tenant, and on-premise deployments.
Open-Source LLM Inference Providers
We also support a number of inference platforms for open-source models. You can use any model they serve via Unique. As with proprietary providers, we offer both Unique-managed accounts and bring-your-own-API-key options.
How To Set Up Spaces With Different LLMs
When configuring a Unique AI space, choose an AI model from the dropdown menu. For specific models listed in the following Model Availability Matrix, go to Language Model under Advanced Settings. Refer to the first column of the Model Availability Matrix and copy the corresponding Model Name into the LanguageModelName text field.
Additional configuration details and exceptions (e.g., for open‑source models) are available here: Unique AI Space
Please contact our support team or refer to your contract to confirm which models are activated for your deployment.
Model Availability Matrix
Legend for support in UniqueAI and Translation:
⚪ Not yet validated
🔴 Not suited
🟡 Functionally working - No quality support
🟢 Passed extensive Quality testing
Azure Deployment
Unique Enum
(to be used in configurations) | Model | Version / Release Date | Retirement Date | Availability in Unique (release) | Supported Models for Unique AI Chat | Supported Models for Translation | Standard CH | Standard SWE | Data Zone Standard EU Quota in | Available Global Standard Quota in | Additional information |
|---|---|---|---|---|---|---|---|---|---|---|---|
|
| 2024-05-13 | 2026-10-01 | before | 🟡 (use | 🟡 | ❌ | ✅ 500k | ✅ | ✅ | |
|
| 2024-08-06 | 2026-10-01 | before | 🟡 (use | 🟡 | ❌ | ✅ 200k | ✅ 10M | ✅ | |
|
| 2024-11-20 | 2026-10-01 | 2025.18 | 🟢 | 🟢 | ✅ 1M | ✅ | ✅ 10M | ✅ | |
|
| 2024-07-18 | 2026-10-01 | before | 🔴 | 🟡 | ❌ | ✅ 700k | ✅ 20M | ✅ | |
|
| 2024-12-17 | 2026-07-15 | 2025.14 | 🟡 | 🟡 | ❌ | ✅ | ✅ 6M | ✅ 2.5M |
|
|
| 2025-01-31 | 2026-08-02 | 2025.14 | 🔴 | 🟡 | ❌ | ❌ | ✅ 20M | ✅ 2.5M |
|
|
| 2025-04-14 | 2026-10-14 | 2025.14 | 🟢 | 🟡 | ❌ | ❌ | ✅ 2M | ✅ 5M | |
|
| 2025-04-14 | 2026-10-14 | 2025.24 | ⚪ | 🟡 | ❌ | ❌ | ✅ | ✅ 5M | |
|
| 2025-04-14 | 2026-10-14 | 2025.24 | ⚪ | 🟡 | ❌ | ❌ | ✅ 2M | ✅ 5M | |
|
| 2025-04-16 | 2026-10-16 | 2025.20 | 🟡 | 🟡 | ❌ | ❌ | ✅ 3M | ✅ 5M | |
|
| 2025-04-16 | 2026-10-16 | 2025.20 | 🟡 set temperature to 1.0 in configs | 🟡 | ❌ | ❌ | ✅ 3M | ✅ 5M | |
|
| 2025-08-07 | 2027-02-06 | 2025.34 | 🟢 | 🟢 | ❌ | ❌ | ✅ | ✅ | ❗ Needs request via Dynamics 365 Customer Voice |
|
| 2025-08-07 | 2027-02-06 | 2025.34 | 🟡 | 🟡 | ❌ | ❌ | ✅ | ✅ | |
|
| 2025-08-07 | 2027-02-06 | 2025.34 | 🟡 | 🟡 | ❌ | ❌ | ✅ 50M | ✅ 150M | |
|
| 2025-08-07 | 2026-06-22 | 2025.34 | 🔴 | 🟡 | ❌ | ❌ | ❌ | ✅ | |
|
| 2025-11-13 | 2027-05-25 | 2025.44 | 🟢 | 🟡 | ❌ | ❌ | ✅ | ✅ | |
|
| 2025-12-11 | 2026-12-12 | 2025.52 | 🟢 | 🟡 | ❌ | ❌ | ❌ | ✅ 5M | |
|
| 2026-03-05 | 2027-03-03 | 2026.12 | 🟢 | 🟡 | ❌ | ❌ | ✅ | ✅ | |
|
| 2026-03-05 | 2027-03-05 | 2026.12 | 🔴 | 🔴 | ❌ | ❌ | ❌ | ✅ | |
|
| 2026-04-24 | 2027-04-23 | 2026.18 | 🟢 | 🟡 | ❌ | ❌ | ✅ | ✅ |
LiteLLM Deployment
Unique Enum
(to be used in configurations) | Provider | Model | Version / Release Date | Retirement Date | Availability in Unique (release) | Supported Models for Unique AI Chat | Supported Models for Translation |
|---|---|---|---|---|---|---|---|
| Anthropic |
| 20251001 | Not sooner than October 15, 2026 | 2025.44 | To be tested | To be tested |
| Anthropic |
| 20250805 | Not sooner than August 5, 2026 | 2025.40 | 🟡 | 🟡 |
| Anthropic |
| 20251101 | Not sooner than November 24, 2026 | 2025.50 | 🟡 | 🟡 |
| Anthropic |
| Not sooner than February 5, 2027 | 2026.08 | 🟢 | 🟡 | |
| Anthropic |
| Not sooner than April 16, 2027 | 2026.18 | 🟢 | 🟡 | |
| Anthropic |
| Not sooner than May 28, 2027 | 2026.24 | 🟡 | 🟡 | |
| Anthropic |
| 20250929 | Not sooner than September 29, 2026 | 2025.40 | 🟡 | 🟡 |
| Anthropic |
| Not sooner than February 17, 2026 | 2026.10 | 🟡 | 🟡 | |
| Gemini |
| June 17, 2025 | October 16, 2026 | 2025.20 | 🟡 | 🟡 |
| Gemini |
| June 17, 2025 | October 16, 2026 | 2025.46 | 🟡 | 🟡 |
| Gemini |
| June 17, 2025 | October 16, 2026 | 2025.28 | 🟢 | 🟡 |
| Gemini |
| February 19, 2026 | n/a | 2026.10 | 🟡 | 🟡 |
| Gemini |
| December, 2025 | n/a | 2025.52 | 🟢 | 🟡 |
| OpenAI |
| 2025-04-14 | 2026-10-14 | 2025.20 | 🟡 | 🔴 |
| OpenAI |
| 2025-04-14 | 2026-10-14 | 2025.20 | 🔴 | 🔴 |
| OpenAI |
| 2025-08-07 | No earlier than August 7, 2026 | 2025.34 | 🟡 Use Azure deployment | 🔴 |
| OpenAI |
| 2025-08-07 | 2026-03-01 | 2025.34 | 🔴 tool calls not allowed | 🔴 |
| OpenAI |
| 2025-08-07 | 2027-02-06 | 2025.34 | 🟡 Use Azure deployment | 🟡 |
| OpenAI |
| 2025-08-07 | 2027-02-06 | 2025.34 | 🟡 Use Azure deployment | 🟡 |
| OpenAI |
| 2025-12-11 | No earlier than December 11, 2026 | 2025.52 | 🟢 Use Azure deployment | 🟡 |
| OpenAI |
| 2026-03-05 | No earlier than March 5, 2027 | 2026.12 | 🟢 Use Azure deployment | 🟡 |
| OpenAI |
| 2026-03-05 | No earlier than March 5, 2027 | 2026.12 | 🔴 | 🟡 |
| OpenAI |
| 2026-04-24 | No earlier than April 24, 2027 | 2026.18 | 🔴Use Azure deployment | 🟡 |
| OpenAI |
| 2024-12-17 | No earlier than July 15, 2026 | 2025.20 | 🟡 | 🟡 |
| OpenAI |
| 2025-04-16 | No earlier than April 11, 2026 | 2025.20 | 🟡 | 🟡 |
| OpenAI |
| 2025-06-10 | No earlier than June 18, 2026 | 2025.26 | 🔴: Chat Completion API is not supported for o3-pro. Only response API. | 🔴 |
| OpenAI |
| 2025-04-16 | No earlier than April 11, 2026 | 2025.20 | 🟡 | 🟡 |
| TogetherAI |
| 2025.20 | 🔴
| 🟡 | ||
| TogetherAI |
| 2025.36 | 🔴
| 🟡 | ||
| TogetherAI |
| 2025.20 | 🔴
| 🟡 | ||
| TogetherAI |
| 2025.36 | 🟡 | 🟡 | ||
| TogetherAI |
| 2025.36 | 🔴
| 🟡 | ||
| xAI |
| 2025-11-19 | 2026.08 | 🟡 | 🟡 | |
| xAI |
| 2025-11-19 | 2026.08 | 🟡 | 🟡 | |
| Vertex AI |
| Not sooner than February 5, 2027 | 2026.20 | 🟢 | 🟡 | |
| Vertex AI |
| Not sooner than April 16, 2027 | 2026.20 | 🟢 | 🟡 | |
| Vertex AI |
| Not sooner than February 17, 2026 | 2026.20 | 🟢 | 🟡 |
Retired Models
Unique Enum
(to be used in configurations) | Model | Version | Retirement | Replacement |
|---|---|---|---|---|
|
| 0613 | June 6, 2025 |
|
|
| 0613 | June 6, 2025 |
|
|
| 2024-04-09 | June 6, 2025 |
|
|
| 2025-04-17 | July, 2025 |
|
|
| 2025-06-05 | December, 2 2025 |
|
|
| 0125 | November 11, 2025 |
|
|
| 2024-09-12 | November 17, 2025 |
|
|
| 20250219 | February 19, 2026 |
|
|
| 20250219 | February 19, 2026 |
|
|
| March 9, 2026 |
| |
|
| 20250514 | June 15, 2026 |
|
|
| 20250514 | June 15, 2026 |
|
Notes
Global Models: These models perform inference (data processing) across all regions provided by Microsoft, including the US. This is the default option for US tenants.
Standard SWE Models: Available exclusively in Sweden Central. This option applies when customers opt for data processing solely within Europe.
Data zone Standard Models: Data is processed somewhere in Europe (and not anymore only in Sweden). This option applies when customers opt for data processing solely within Europe.
Standard CH Models: Designed specifically for Switzerland. This option applies when customers choose to have data processing only within Switzerland.
Request-Based Models: Certain models require a request and approval from Microsoft. (Refer to the Request Table below for details.)
PTU (Prepaid Through Unit): Some customers have purchased PTUs and maintain direct communication with Microsoft. However, they likely also follow a pay-as-you-go strategy, making this page relevant to them as well.
Escalations to Microsoft: If a model is not available, customers should escalate the request directly to Microsoft via the email contact they have from MS. The customer should submit a request specifying the model needed.
Details about model retirement
Azure https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/model-retirements?tabs=text
Google (Gemini) https://ai.google.dev/gemini-api/docs/deprecations , Release notes | Gemini API | Google AI for Developers
Anthropic https://platform.claude.com/docs/en/about-claude/model-deprecations
TogetherAI https://docs.together.ai/docs/deprecations
Change Logs
Date | Change Summary |
|---|---|
| Retirement of |
| Claude models provided via Vertex AI added |
| The following models are available with DataZoneStandard via Azure:
|
| New models:
|
| New models:
|
| New models added:
|
| New Gemini model added with release 2026.10
|
| Retirement of |
| New xAI model added with release 2026.08
|
| New Anthropic model added with release 2026.08
|
| Update retirement dates OpenAI & Gemini models |
| Updating retirement date and replacement model for |
| New models added:
Both of them are supported by UniqueAI with release 2025.52 |
| New OpenAI model added
|
| Gemini 3 Pro works with UniqueAI using the updated version of LiteLLM |
| New Anthropic model added with release 2025.50
|
|
|
| New Gemini model added with release 2025.48
Retired model:
|
| New Gemini model added with release 2025.46
|
| Retirement date of |
| Update retirement date of |
|
|
| No changes |
|
|
| Several OpenAI models retire by |