Releasesby GlyphFireworks AI releases Training Cookbook on PyPI and migrates repository
Fireworks AI published fireworks-training-cookbook 2026.11.5.1 on PyPI for Python 3.11+ and migrated its training cookbook to fw-ai-external/cookbook.
Also shipped Nov 4, 2026Fireworks AI in November 2026 →
[Launched] Generally Available: Azure Database for PostgreSQL stable REST API version 2026-10-01
The Azure Database for PostgreSQL Flexible Server REST API version 2026-10-01 is now generally available, introducing new capabilities for maintenance, immutable backups, and encryption.
Analytics API (Public preview): report on the health of the data behind your agents, from your AI tool
The Monte Carlo Analytics API is now in public preview, allowing users to query data health, alert status, and cost metrics directly from AI tools via the Monte Carlo MCP server.
Twice the included embedding tokens through December 31
Pinecone is doubling the included monthly embedding tokens for Starter and Builder organizations through December 31, 2026.
Gemini Enterprise: Switch between teams in the mobile app
The Gemini Enterprise mobile app now supports switching between multiple teams without re-authentication, and allows renaming or removing teams from the list.
Compare AI agent changes with Online Experiments in Agent Observability
Datadog Online Experiments allows engineers to test AI agent changes against production traffic. It enables comparison of response quality, cost, latency, and error rates.
Postmortems End of Life Completed
The Postmortems feature has been retired in favor of the upgraded Post-Incident Reviews in the PagerDuty web UI.
More from Fireworks AI platformEvery Fireworks AI platform release →
Inference New Serverless mode: Ultra-fast (Preview) Ultra-fast is a new high-speed Serverless mode, now in...
Inference New Serverless mode: Ultra-fast (Preview) Ultra-fast is a new high-speed Serverless mode, now in Preview, for highly latency-sensitive applications. Ultra-fast variants aim for 6-8x generation speed, and up to 10x for agentic coding tasks. Like Fast, it is not a different model, so output quality is the same.
Training Serverless Training deprecation: DeepSeek V4 Flash (0731) DeepSeek V4 Flash (0731) is removed from...
Training Serverless Training deprecation: DeepSeek V4 Flash (0731) DeepSeek V4 Flash (0731) is removed from the shared Serverless Training pool effective November 2, 2026. Migrate Serverless Training workloads to DeepSeek V4.1 Flash 1017 . This change applies only to Serverless Training.
Fireworks AI adds Rune 26B-A4B model to Serverless
Fireworks AI has added the Rune 26B-A4B model to its Serverless platform. This decision model processes documents and questions to return calibrated probabilities without generating text, and is billed based on input tokens only.
Errors identify their source
Fireworks AI updated its error reporting to provide more granular source identification for failures, including new error codes for parsing and transport issues.
Unparseable trajectories are discarded
Fireworks AI now discards unparseable trajectories to prevent them from impacting training data quality.
Failure traces are saved locally
Failed model trajectories now generate private JSONL traces in the system temporary directory. These traces include request data, token IDs, and exception chains to help developers identify whether failures originated from the model, tokenizer, or renderer.
Image inputs for FiretitanSamplingClient.sample
The sample and sample_async methods now support a keyword-only images argument. This allows developers to pass base64 data URLs for token prompts using placeholders.
Errors identify their source
Before 1.2.27, the sidecar returned HTTP 502 for two failures that weren't server-side: tito_model_malformed_output (unparseable model output) and tito_upstream_error (any sampling exception, including client timeouts and dropped connections). They are replaced by: tito_sdk_parse_error (422): the output couldn't be parsed into an assistant or tool message.