Model deprecations (MaaS)

MaaS models are periodically deprecated and replaced with newer versions. This page lists deprecated models and their shutdown dates to help you plan your migration.

Mistral Nemo

Mistral Nemo is deprecated as of June 30, 2025 and will be shut down on August 20, 2025. Mistral Nemo is available to existing customers only.

Mistral Nemo is a cost-efficient proprietary model from Mistral AI. You can use Mistral Nemo for low-latency workloads and basic tasks that can be done in bulk, such as classification, customer support, and text generation.

View model card in Model Garden

Property Description
Model ID mistral-nemo
Versions
  • mistral-nemo
    • Launch stage: Deprecated
    • Release date: July 24, 2024
Supported regions

Model availability

United States

  • us-central1

Europe

  • europe-west4

ML processing

United States

  • Multi-region

Europe

  • Multi-region
Quota limits

us-central1:

  • QPM: 60
  • TPM: 400,000
  • Context length: 128,000

europe-west4:

  • QPM: 60
  • TPM: 400,000
  • Context length: 128,000
Pricing See Pricing.

Claude 3 Opus

Anthropic's Claude 3 Opus is deprecated as of June 30, 2025 and will be shutdown on January 5, 2026. Claude 3 Opus is available to existing customers only.

Anthropic's Claude 3 Opus is a powerful AI model designed for highly complex tasks. It can navigate open-ended prompts and sight-unseen scenarios. Claude 3 Opus is optimized for the following use cases:

  • Task automation: Interactive coding and planning, or running complex actions across APIs and databases.
  • Research and development: Research review, brainstorming and hypothesis generation, and product testing.
  • Strategy: Advanced analysis of charts and graphs, financials and market trends, and forecasting.
  • Vision: Processing images to return text output and analysis of charts, graphs, technical diagrams, reports, and other visual content.

View model card in Model Garden

Property Description
Model ID claude-3-opus@20240229
Token limits
Maximum input tokens 200,000
Maximum output tokens 8,000
Capabilities
Technical specifications
Images
  • Limitation and specifications: See Vision in Anthropic's documentation
Documents
  • Limitation and specifications: See PDF support in Anthropic's documentation
Knowledge cutoff date August 2023
Versions
  • claude-3-opus@20240229
    • Launch stage: Deprecated
    • Release date: May 31, 2024
Supported regions

Model availability

(Includes fixed quota & Provisioned Throughput)

United States

  • us-east5

ML processing

United States

  • Multi-region
Quota limits

us-east5:

  • QPM: 20
  • TPM: 105,000 (input and output)
  • Context length: 200,000
Pricing See Pricing.