We monitor Amazon (Bedrock) for API changes, pricing updates, model releases, deprecation notices, and service incidents.
16 Changes Detected
💰 Pricing
Amazon Bedrock pricing page updated — new/changed model prices and region entries
The Amazon Bedrock pricing page was updated to add and/or change many model pricing rows and region-specific price entries. Notable additions/changes in the pricing tables include NVIDIA Nemotron 3 Super 120B A12B (multiple region prices), Palmyra Vision 7B pricing, Z AI (GLM 5) pricing and expanded regions, and MiniMax (MiniMax M2.5) pricing entries and regional variations. Multiple region-specific price lines were inserted or adjusted across several providers and models.
Amazon Bedrock pricing page updated — AI21 Labs (Jamba/Jurassic-2) model prices added with region-specific entries
The Amazon Bedrock pricing page was updated to add AI21 Labs model pricing rows (Jamba 1.5 Large, Jamba 1.5 Mini, Jurassic-2 Mid, Jurassic-2 Ultra, Jamba-Instruct) including per-1M input/output token prices and region-specific price entries. These new table rows expand the list of providers/models and include region-specific pricing variations that were not present in the prior scrape.
The Amazon Bedrock pricing page shows AI21 Labs models and pricing information (examples referencing Jurassic-2 / Jamba) present in the current scrape after those model price rows had been absent in the prior scrape. The change restores model-specific pricing rows and example calculations referencing AI21 models; no other Bedrock documentation pages (models/regions, quotas, doc-history) showed substantive changes in this run.
The Amazon Bedrock pricing page no longer contains the AI21 Labs model pricing rows (Jamba 1.5 Large, Jamba 1.5 Mini, Jurassic-2 Mid, Jurassic-2 Ultra, Jamba-Instruct) that were present in the prior scrape. This removed content affects the per-1M input/output token price table entries and region-specific price listings for those models. No other Bedrock documentation pages (models/regions, quotas, doc-history) showed content changes in this run.
Amazon Bedrock model-region support table updated (Mar 25, 2026)
AWS updated the Amazon Bedrock 'Model support by AWS Region' documentation on 2026-03-25, refreshing the table that maps specific foundation models to AWS Regions and inference-profile availability. The update includes many provider/model entries (Amazon Nova variants, Titan embeddings, Anthropic Claude versions, Mistral, Meta Llama variants, and others) and clarifies cross-region inference-profile notes.
Nova Forge SDK announced to customize Nova models (Mar 2026)
AWS announced the Nova Forge SDK (called out in the Mar 23, 2026 weekly roundup) as a new SDK to customize Amazon Nova models for enterprise AI, enabling streamlined fine-tuning/customization and deployment of Nova models directly within Amazon Bedrock.
The Amazon Bedrock 'Request an increase for Amazon Bedrock quotas' documentation was updated (Mar 22, 2026) to clarify which quotas can be increased, the process (via the Service Quotas workflow), and that requesting an increase for the 'Cross-Region InvokeModel tokens per minute for ${model}' quota is the way to request bundled increases for related quotas. The page also notes priority is given to customers consuming their existing quota.
The Amazon Bedrock 'Monitoring the performance of Amazon Bedrock' documentation was updated (Mar 22, 2026) to enumerate CloudWatch metrics and monitoring guidance for Bedrock (InvocationThrottles, InputTokenCount, OutputTokenCount, TimeToFirstToken, and EstimatedTPMQuotaUsage, among others) and to recommend using CloudWatch, CloudTrail, and EventBridge for runtime monitoring and alarms.
NVIDIA Nemotron 3 Super now available on Amazon Bedrock (Mar 18, 2026)
AWS announced that NVIDIA Nemotron 3 Super is now available on Amazon Bedrock (posted Mar 18, 2026). The page states Nemotron 3 Super is available across select AWS Regions and describes it as an open hybrid MoE model for complex multi-agent/agentic workloads, with full openness (weights, datasets, recipes) and suitability for customization and secure enterprise deployment.
Minimax M2.5 and GLM 5 models now available on Amazon Bedrock (Mar 18, 2026)
AWS announced Minimax M2.5 and GLM 5 are now available on Amazon Bedrock (posted Mar 18, 2026). The announcement describes GLM 5 as a frontier-class general-purpose LLM for long-horizon agentic and systems-engineering tasks and Minimax M2.5 as an agent-native frontier model optimized for token-efficient reasoning and workflow completion.
Migration guide: Migrate from Amazon Nova 1 to Amazon Nova 2 on Amazon Bedrock (Mar 18, 2026)
AWS published a migration/technical blog (Mar 18, 2026) explaining how to migrate Amazon Nova 1→Nova 2 on Amazon Bedrock. It includes recommended migration paths (Nova 1 Lite/Pro/Premier → Nova 2 Lite), API/model ID changes, new capabilities (extended thinking, built-in tools, 1M token context), pricing examples for Nova 2 Lite, and breaking/integration notes (e.g., parameter restrictions when using high reasoning effort).
Amazon Bedrock now available in Asia Pacific (New Zealand) (Mar 17, 2026)
AWS announced Amazon Bedrock is available in the Asia Pacific (New Zealand) Region starting Mar 17, 2026. The announcement lists model availability in the region—Anthropic (Sonnet 4.5, Sonnet 4.6, Opus 4.5, Opus 4.6, Haiku 4.5) and Amazon (Nova 2 Lite)—and points customers to the Bedrock product page and region/model compatibility docs for details.
AWS Partner Central agents powered by Amazon Bedrock AgentCore (Mar 16, 2026)
AWS announced AWS Partner Central agents powered by Amazon Bedrock AgentCore, available to Partners who have migrated to the new Partner Central experience. The post describes agentic capabilities embedded into Partner Central, MCP integration options for connecting tools, and migration/get-started guidance for partners.
New CloudWatch metrics for Amazon Bedrock: TimeToFirstToken and EstimatedTPMQuotaUsage (Mar 16, 2026)
AWS announced two new Amazon CloudWatch metrics for Amazon Bedrock — TimeToFirstToken and EstimatedTPMQuotaUsage — to help customers observe model latency and estimated token‑per‑minute quota usage. The announcement explains the metrics and how they can be used to monitor Bedrock performance and quota consumption.
AWS and Cerebras announced a collaboration to deploy Cerebras CS-3 systems in AWS data centers and offer a Trainium + Cerebras disaggregated inference solution accessible via Amazon Bedrock. The joint solution uses Trainium for prefill and Cerebras WSE/CS-3 for decode, promising much higher token-per-second decode throughput and up to ~5x more high-speed token capacity. AWS said the capability will be available via Bedrock in the coming months and that major open-source LLMs and Amazon Nova models will be offered on Cerebras hardware.
New CloudWatch metrics (TimeToFirstToken, EstimatedTPMQuotaUsage) for Amazon Bedrock (Mar 13, 2026)
AWS announced two new CloudWatch metrics for Amazon Bedrock — TimeToFirstToken and EstimatedTPMQuotaUsage — which are automatically emitted to the AWS/Bedrock namespace for successful inference requests. TimeToFirstToken gives server-side streaming latency (ms) and EstimatedTPMQuotaUsage estimates Tokens-Per-Minute quota consumption (accounting for burndown multipliers and cache weighting). Both metrics are available now and designed to help set alarms, baselines, and capacity planning.