Releasesby GlyphPlatform SSO documentation: IdP-initiated SAML Updated the Custom SSO guide
Platform SSO documentation: IdP-initiated SAML Updated the Custom SSO guide. IdP-initiated SAML is supported as an opt-in ( --enable-idp-initiated-sso ); the previous troubleshooting copy that said Fireworks only supported SP-initiated login was incorrect.
Also shipped Aug 25, 2026Fireworks AI in August 2026 →
BigQuery data governance tags are supported in Terraform
BigQuery data governance tags are supported in Terraform. This feature is in Preview .
Multi-value tags (General availability)
With this release, multi-value tags are generally available. You can assign more than one string value to the same tag.
Remote app operations for Snowflake Native Apps (Preview)
Remote app operations are now available in public preview for Snowflake Native Apps. Providers can perform on-demand operations on consumer apps, including running SQL statements ( run_sql ), retrying a failed upgrade ( retry_upgrade ), and disabling/enabling the app ( disable / enable ), all through a new system function SYSTEM$REMOTE_APP_OPERATION .
Remote Development with the Snowflake Extension for Visual Studio Code (Preview)
Remote Development with the Snowflake Extension for Visual Studio Code is now available in public preview.
Stable egress IP addresses on Azure (Preview)
Stable egress IP addresses are now available in preview on Azure. You can generate Snowflake egress IP address ranges (as CIDR addresses) and add them to an external server's allowlist so that Snowflake can make requests to that server.
LTAP Direct Writes accelerates synced table loads (Beta)
LTAP Direct Writes speeds up how synced tables load into Lakebase. When you create a synced table, Lakebase loads a full copy of your Unity Catalog data into your Postgres branch.
More from Fireworks AI platformEvery Fireworks AI platform release →
Training Serverless Training deprecation: Qwen 3.5 9B and Qwen 3.6 27B Qwen 3.5 9B and Qwen 3.6 27B are...
Training Serverless Training deprecation: Qwen 3.5 9B and Qwen 3.6 27B Qwen 3.5 9B and Qwen 3.6 27B are deprecated from Serverless Training effective August 26, 2026. Migrate new and existing Serverless Training workloads to Qwen 3.8 27B . This change applies to the shared Serverless Training pool.
Recommended migrations
- MiniMax M2.7 , migrate to MiniMax M3 GPT OSS 20B , migrate to GPT OSS 120B or Qwen3 8B for lower-latency workloads Kimi K2.6 Turbo / Fast , migrate to Kimi K2.6 (standard mode) Kimi K2.7 Code Fast , migrate to Kimi K2.7 Code (standard mode) DeepSeek V4 Pro , migrate to DeepSeek V4 Pro (0813)
Training New Serverless Training models: DeepSeek V4 Flash 0731, Qwen 3.8 27B, and Muse Glimmer 30B The...
Training New Serverless Training models: DeepSeek V4 Flash 0731, Qwen 3.8 27B, and Muse Glimmer 30B The following models are now available for LoRA workloads on the shared Serverless Training pool: DeepSeek V4 Flash 0731 with up to 262K context Qwen 3.8 27B with up to 128K context Muse Glimmer 30B with up to 128K context See the Serverless Training guide...
Inference Serverless rate limit ceilings now scale by model size Serverless adaptive rate limit ceilings now...
Inference Serverless rate limit ceilings now scale by model size Serverless adaptive rate limit ceilings now vary by model size tier. Smaller models ( Serverless rate limits for tier thresholds and ceiling values.
Inference Serverless deprecation: DeepSeek V4 Flash DeepSeek V4 Flash is deprecated from serverless
Inference Serverless deprecation: DeepSeek V4 Flash DeepSeek V4 Flash is deprecated from serverless. Migrate to DeepSeek V4 Flash (0731) .
Platform Deployment tags and annotation API changes Deployment tags are customer-managed entries stored in a...
Platform Deployment tags and annotation API changes Deployment tags are customer-managed entries stored in a deployment's annotations map. firectl presents logical keys such as environment ; the REST API represents the same key as custom/environment . firectl: Version 1.8.3 adds deployment tag set , unset , and list , including atomic batch operations.
Training Training cost estimator The new training cost estimator helps you estimate what a training job will...
Training Training cost estimator The new training cost estimator helps you estimate what a training job will cost before you run it. Managed and Serverless estimates use published per-token rates. Dedicated estimates use allocated GPU-hour rates. Planning estimates are not quotes.
Action required
If you use any of the models below on serverless, migrate to a recommended replacement before September 25, 2026 . After that date, they will no longer be available via serverless endpoints.