After a period of time, [MaaS
models](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/use-partner-models) are
deprecated and typically replaced with newer model versions. This page lists
deprecated MaaS models and their shutdown dates to help you plan and migrate to
newer model versions.

## Anthropic's Claude Sonnet 4.5 on Google Cloud

Anthropic's Claude Sonnet 4.5 on Google Cloud is **deprecated as of September 29, 2026** and will
be **shut down on November 30, 2026**. Anthropic's Claude Sonnet 4.5 on Google Cloud is available
to existing customers only.

Anthropic's Claude Sonnet 4.5 on Google Cloud is Anthropic's Sonnet-class model for powering
real-world agents, with capabilities in coding, computer use, cybersecurity, and
working with office files like spreadsheets.


[Try in Agent Studio](https://console.cloud.google.com/agent-platform/generative/multimodal/create/text?model=claude-sonnet-4-5)


[View model card in Model Garden](https://console.cloud.google.com/agent-platform/publishers/anthropic/model-garden/claude-sonnet-4-5)

| Model ID | `claude-sonnet-4-5` ||
| Launch stage | deprecated ||
| Supported inputs \& outputs | - Inputs: Text, Code, Images - Outputs: Text ||
| Token limits | - Maximum input tokens: 1M (Preview) 200,000 (GA) - Maximum output tokens: 64,000 ||
| Capabilities | - Supported - [Web search](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/claude/web-search.md.txt) - [Batch predictions](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/claude/batch.md.txt) - [Prompt caching](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/claude/prompt-caching.md.txt) - [Function calling](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/claude/use-claude.md.txt#tool_use_function_calling) - [Extended thinking](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/claude/use-claude.md.txt#use_a_curl_command) - [Count tokens](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/claude/count-tokens.md.txt) - Not supported ||
| Usage types | - Supported - [Fixed quota](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/quotas.md.txt) - [Provisioned Throughput](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/provisioned-throughput.md.txt) - Not supported ||
| Technical specifications |
| Technical specifications |
| Technical specifications |
|---|---|---|
| Images | - **Limitation and specifications:** See [Vision](https://docs.anthropic.com/en/docs/build-with-claude/vision) in Anthropic's documentation |
| Documents | - **Limitation and specifications:** See [PDF support](https://docs.anthropic.com/en/docs/build-with-claude/pdf-support) in Anthropic's documentation |
| Model availability (Includes fixed quota \& Provisioned Throughput) | - United States - `us-east5` - Europe - `europe-west1` - Asia Pacific - `asia-southeast1` - Global - `global endpoint` |
| ML processing | - United States - `Multi-region` - Europe - `Multi-region` - Asia Pacific - `asia-southeast1` |

## Anthropic's Claude 3 Haiku on Google Cloud

Anthropic's Claude 3 Haiku on Google Cloud is **deprecated as of February 23, 2026** and will be
**shut down on August 23, 2026**. Anthropic's Claude 3 Haiku on Google Cloud is available to
existing customers only.

Anthropic's Claude 3 Haiku on Google Cloud is Anthropic's fastest vision and text model for
near-instant responses to basic queries, meant for seamless AI experiences
mimicking human interactions.


| Model ID | `claude-3-haiku` ||
| Launch stage | deprecated ||
| Supported inputs \& outputs | - Inputs: Text, Code, Images - Outputs: Text ||
| Token limits | - Maximum input tokens: 200,000 - Maximum output tokens: 8,000 ||
| Capabilities | - Supported - [Prompt caching](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/claude/prompt-caching.md.txt) - [Function calling](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/claude/use-claude.md.txt#tool_use_function_calling) - [Count tokens](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/claude/count-tokens.md.txt) - Not supported - [Batch predictions](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/claude/batch.md.txt) - [Extended thinking](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/claude/use-claude.md.txt#use_a_curl_command) ||
| Usage types | - Supported - [Fixed quota](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/quotas.md.txt) - [Provisioned Throughput](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/provisioned-throughput.md.txt) - Not supported ||
| Technical specifications |
| Technical specifications |
| Technical specifications |
|---|---|---|
| Images | - **Limitation and specifications:** See [Vision](https://docs.anthropic.com/en/docs/build-with-claude/vision) in Anthropic's documentation |
| Documents | - **Limitation and specifications:** See [PDF support](https://docs.anthropic.com/en/docs/build-with-claude/pdf-support) in Anthropic's documentation |
| Model availability (Includes fixed quota \& Provisioned Throughput) | - United States - `us-east5` - Europe - `europe-west1` - Asia Pacific - `asia-southeast1` |
| ML processing | - United States - `Multi-region` - Europe - `Multi-region` - Asia Pacific - `asia-southeast1` |

## Claude 3.5 Haiku on Google Cloud

Claude 3.5 Haiku on Google Cloud is **deprecated as of January 5, 2026** and
will be **shut down on July 5, 2026**. Claude 3.5 Haiku on Google Cloud is
available to existing customers only.

Claude 3.5 Haiku on Google Cloud, the next
generation of Anthropic's fastest and most cost-effective model, is
optimal for use cases where speed and affordability matter.


[View model card in Model Garden](https://console.cloud.google.com/agent-platform/publishers/anthropic/model-garden/claude-3-5-haiku)

| Model ID | `claude-3-5-haiku` ||
| Launch stage | deprecated ||
| Supported inputs \& outputs | - Inputs: Text, Code, Images - Outputs: Text ||
| Token limits | - Maximum input tokens: 200,000 - Maximum output tokens: 8,000 ||
| Capabilities | - Supported - [Batch predictions](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/claude/batch.md.txt) - [Prompt caching](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/claude/prompt-caching.md.txt) - [Function calling](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/claude/use-claude.md.txt#tool_use_function_calling) - [Count tokens](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/claude/count-tokens.md.txt) - Not supported - [Extended thinking](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/claude/use-claude.md.txt#use_a_curl_command) ||
| Usage types | - Supported - [Fixed quota](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/quotas.md.txt) - [Provisioned Throughput](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/provisioned-throughput.md.txt) - Not supported ||
| Technical specifications |
| Technical specifications |
| Technical specifications |
|---|---|---|
| Images | - **Limitation and specifications:** See [Vision](https://docs.anthropic.com/en/docs/build-with-claude/vision) in Anthropic's documentation |
| Documents | - **Limitation and specifications:** See [PDF support](https://docs.anthropic.com/en/docs/build-with-claude/pdf-support) in Anthropic's documentation |
| Model availability (Includes fixed quota \& Provisioned Throughput) | - United States - `us-east5` - Europe - `europe-west1` |
| ML processing | - United States - `Multi-region` - Europe - `Multi-region` |

## Claude 3.7 Sonnet on Google Cloud

Claude 3.7 Sonnet on Google Cloud is **deprecated as of November 11, 2025** and
will be **shut down on May 11, 2026**. Claude 3.7 Sonnet on Google Cloud is
available to existing customers only.

Claude 3.7 Sonnet on Google Cloud is a state-of-the-art model for real-world
software engineering tasks and agentic capabilities.


| Model ID | `claude-3-7-sonnet` ||
| Launch stage | deprecated ||
| Supported inputs \& outputs | - Inputs: Text, Code, Images - Outputs: Text ||
| Token limits | - Maximum input tokens: 200,000 - Maximum output tokens: 128,000 ||
| Capabilities | - Supported - [Batch predictions](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/claude/batch.md.txt) - [Prompt caching](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/claude/prompt-caching.md.txt) - [Function calling](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/claude/use-claude.md.txt#tool_use_function_calling) - [Count tokens](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/claude/count-tokens.md.txt) - Not supported - [Extended thinking](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/claude/use-claude.md.txt#use_a_curl_command) ||
| Usage types | - Supported - [Fixed quota](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/quotas.md.txt) - [Provisioned Throughput](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/provisioned-throughput.md.txt) - Not supported ||
| Technical specifications |
| Technical specifications |
| Technical specifications |
|---|---|---|
| Images | - **Limitation and specifications:** See [Vision](https://docs.anthropic.com/en/docs/build-with-claude/vision) in Anthropic's documentation |
| Documents | - **Limitation and specifications:** See [PDF support](https://docs.anthropic.com/en/docs/build-with-claude/pdf-support) in Anthropic's documentation |
| Model availability (Includes fixed quota \& Provisioned Throughput) | - United States - `us-east5` - Europe - `europe-west1` - Global - `global endpoint` |
| ML processing | - United States - `Multi-region` - Europe - `Multi-region` |

## Claude 3.5 Sonnet v2 on Google Cloud

Claude 3.5 Sonnet v2 on Google Cloud is **deprecated as of August 20, 2025** and
will be
**shut down on February 19, 2026**. Claude 3.5 Sonnet v2 on Google Cloud is
available to existing customers only.

Claude 3.5 Sonnet v2 on Google Cloud is a state-of-the-art model for real-world
software engineering tasks and agentic capabilities.


[Try in Agent Studio](https://console.cloud.google.com/agent-platform/generative/multimodal/create/text?model=claude-3-5-sonnet-v2)


| Model ID | `claude-3-5-sonnet-v2` ||
| Launch stage | GA ||
| Supported inputs \& outputs | - Inputs: Text, Code, Images - Outputs: Text ||
| Token limits | - Maximum input tokens: 200,000 - Maximum output tokens: 8,000 ||
| Capabilities | - Supported - [Batch predictions](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/claude/batch.md.txt) - [Prompt caching](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/claude/prompt-caching.md.txt) - [Function calling](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/claude/use-claude.md.txt#tool_use_function_calling) - [Count tokens](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/claude/count-tokens.md.txt) - Not supported - [Extended thinking](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/claude/use-claude.md.txt#use_a_curl_command) ||
| Usage types | - Supported - [Fixed quota](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/quotas.md.txt) - [Provisioned Throughput](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/provisioned-throughput.md.txt) - Not supported ||
| Technical specifications |
| Technical specifications |
| Technical specifications |
|---|---|---|
| Images | - **Limitation and specifications:** See [Vision](https://docs.anthropic.com/en/docs/build-with-claude/vision) in Anthropic's documentation |
| Documents | - **Limitation and specifications:** See [PDF support](https://docs.anthropic.com/en/docs/build-with-claude/pdf-support) in Anthropic's documentation |
| Model availability (Includes fixed quota \& Provisioned Throughput) | - United States - `us-east5` - Europe - `europe-west1` - Global - `global endpoint` |
| ML processing | - United States - `Multi-region` - Europe - `Multi-region` |

## Claude 3.5 Sonnet on Google Cloud

Claude 3.5 Sonnet on Google Cloud is **deprecated as of August 20, 2025** and
will be
**shut down on February 19, 2026**. Claude 3.5 Sonnet on Google Cloud is
available to existing customers only.

Claude 3.5 Sonnet on Google Cloud outperforms Anthropic's
Claude 3 Opus on Google Cloud on a wide range of Anthropic's evaluations with the
speed and cost of Anthropic's mid-tier model, Claude 3 Sonnet on Google Cloud.


| Model ID | `claude-3-5-sonnet` ||
| Launch stage | GA ||
| Supported inputs \& outputs | - Inputs: Text, Code, Images - Outputs: Text ||
| Token limits | - Maximum input tokens: 200,000 - Maximum output tokens: 8,000 ||
| Capabilities | - Supported - [Prompt caching](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/claude/prompt-caching.md.txt) - [Function calling](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/claude/use-claude.md.txt#tool_use_function_calling) - [Count tokens](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/claude/count-tokens.md.txt) - Not supported - [Batch predictions](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/claude/batch.md.txt) - [Extended thinking](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/claude/use-claude.md.txt#use_a_curl_command) ||
| Usage types | - Supported - [Fixed quota](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/quotas.md.txt) - [Provisioned Throughput](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/provisioned-throughput.md.txt) - Not supported ||
| Technical specifications |
| Technical specifications |
| Technical specifications |
|---|---|---|
| Images | - **Limitation and specifications:** See [Vision](https://docs.anthropic.com/en/docs/build-with-claude/vision) in Anthropic's documentation |
| Documents | - **Limitation and specifications:** See [PDF support](https://docs.anthropic.com/en/docs/build-with-claude/pdf-support) in Anthropic's documentation |
| Model availability (Includes fixed quota \& Provisioned Throughput) | - United States - `us-east5` - Europe - `europe-west1` - Asia Pacific - `asia-southeast1` |
| ML processing | - United States - `Multi-region` - Europe - `Multi-region` - Asia Pacific - `asia-southeast1` |

## Jamba 1.5 Large

Jamba 1.5 Large is **deprecated as of August 27, 2025** and will be
**shut down on February 27, 2026**. Jamba 1.5 Large is available to
existing customers only.

AI21 Labs's Jamba 1.5 Large is well balanced across quality,
throughput, and low cost.


[View model card in Model Garden](https://console.cloud.google.com/agent-platform/model-garden)

| Model ID | `jamba-1.5-large` ||
| Launch stage | Preview ||
| Supported inputs \& outputs | - Inputs: Text, Documents - Outputs: Text ||
| Usage types | - Supported - [Fixed quota](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/quotas.md.txt) - Not supported - [Provisioned Throughput](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/provisioned-throughput.md.txt) ||
| Knowledge cutoff date | March 2024 ||
| Versions | - `jamba-1.5-large` - **Launch stage:** Preview - **Release date:** August 22, 2024 ||
| Supported regions |
| Supported regions |
| Supported regions |
|---|---|---|
| Model availability | - United States - `us-central1` - Europe - `europe-west4` |
| ML processing | - United States - `Multi-region` |

## Jamba 1.5 Mini

Jamba 1.5 Mini is **deprecated as of August 27, 2025** and will be
**shut down on February 27, 2026**. Jamba 1.5 Mini is available to existing
customers only.

AI21 Labs's Jamba 1.5 Mini is well balanced across quality, throughput,
and low cost.


[View model card in Model Garden](https://console.cloud.google.com/agent-platform/model-garden)

| Model ID | `jamba-1.5-mini` ||
| Launch stage | Preview ||
| Supported inputs \& outputs | - Inputs: Text, Documents - Outputs: Text ||
| Usage types | - Supported - [Fixed quota](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/quotas.md.txt) - Not supported - [Provisioned Throughput](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/provisioned-throughput.md.txt) ||
| Knowledge cutoff date | March 2024 ||
| Versions | - `jamba-1.5-mini` - **Launch stage:** Preview - **Release date:** August 22, 2024 ||
| Supported regions |
| Supported regions |
| Supported regions |
|---|---|---|
| Model availability | - United States - `us-central1` - Europe - `europe-west4` |
| ML processing | - United States - `Multi-region` |

## Claude 3 Opus on Google Cloud

Anthropic's Claude 3 Opus on Google Cloud is **deprecated as of June 30, 2025** and will be
**shut down on August 1, 2025**. Claude 3 Opus on Google Cloud is available to
existing customers only.

Anthropic's Claude 3 Opus on Google Cloud is a powerful AI model with top-level performance on highly
complex tasks. It can navigate open-ended prompts and sight-unseen scenarios
with remarkable fluency and human-like understanding. Claude 3 Opus on Google Cloud
is optimized for the following use cases:

- Task automation, such as interactive coding and planning, or running complex
  actions across APIs and databases.

- Research and development tasks, such as research review, brainstorming and
  hypothesis generation, and product testing.

- Strategy tasks, such as advanced analysis of charts and graphs, financials
  and market trends, and forecasting.

- Vision tasks, such as processing images to return text output. Also,
  analysis of charts, graphs, technical diagrams, reports, and other visual
  content.


| Model ID | `claude-3-opus` ||
| Launch stage | deprecated ||
| Supported inputs \& outputs | - Inputs: Text, Code, Images - Outputs: Text ||
| Token limits | - Maximum input tokens: 200,000 - Maximum output tokens: 8,000 ||
| Capabilities | - Supported - [Prompt caching](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/claude/prompt-caching.md.txt) - [Function calling](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/claude/use-claude.md.txt#tool_use_function_calling) - [Count tokens](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/claude/count-tokens.md.txt) - Not supported - [Batch predictions](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/claude/batch.md.txt) - [Extended thinking](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/claude/use-claude.md.txt#use_a_curl_command) ||
| Usage types | - Supported - [Fixed quota](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/quotas.md.txt) - [Provisioned Throughput](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/provisioned-throughput.md.txt) - Not supported ||
| Technical specifications |
| Technical specifications |
| Technical specifications |
|---|---|---|
| Images | - **Limitation and specifications:** See [Vision](https://docs.anthropic.com/en/docs/build-with-claude/vision) in Anthropic's documentation |
| Documents | - **Limitation and specifications:** See [PDF support](https://docs.anthropic.com/en/docs/build-with-claude/pdf-support) in Anthropic's documentation |
| Model availability (Includes fixed quota \& Provisioned Throughput) | - United States - `us-east5` |
| ML processing | - United States - `Multi-region` |