Releasesby GlyphRecommended 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)
Also shipped Aug 29, 2026Fireworks AI in August 2026 →
ai_transcribe function (Beta)
The ai_transcribe() SQL function transcribes an audio file into text. It returns the transcript as time-stamped segments, and labels each segment with a speaker when speaker diarization is enabled for your workspace. The output is a VARIANT value, so you can chain it into other AI Functions. This feature is in Beta . See ai_transcribe function .
OpenAI API mTLS and X.509 workload identity federation are GA
Mutual TLS and X.509 workload identity federation can be configured in the Platform console, with access governed by organization roles and permissions, enabling keyless authentication.
Zhipu AI GLM 5.3 now available as a Databricks-hosted model
Model Serving now supports GLM 5.3 as a Databricks-hosted model in supported US and Americas regions. This text-only mixture of experts (MoE) model supports a context window of up to 1,048,576 tokens, up to 65,536 output tokens, function calling, structured output, coding, agentic tool use, and always-on reasoning.
Restrict service principal OAuth secrets to specific API scopes
You can now restrict a service principal's OAuth secret to specific API scopes, such as sql or jobs , instead of all APIs. A token minted from a scoped secret can't exceed those scopes, which limits the impact of a leaked secret. See Authorize service principal access to Databricks with OAuth .
active_sessions autoscaling metric for TTS
Dedicated endpoint autoscaling now accepts active_sessions , which targets concurrent open client WebSocket sessions per replica on a TTS deployment ( AVERAGE_VALUE only). The default inflight_requests metric also covers TTS handlers, so HTTP TTS traffic can keep scaling without a policy change. See Configure autoscaling .
Edit Image Quality Update
Hey everyone, we've updated our V8.2 edit model for better image quality. If you've had any issues in the last 24 hours give it a new shot and keep giving us feedback. Thanks! More updates soon.
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.
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.
Platform 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.
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.
Recommended migrations
- DeepSeek V4 Flash (0731) , migrate to DeepSeek V4.1 Flash DeepSeek V4 Pro (0813) , migrate to DeepSeek V4.1 Flash DeepSeek V4 Flash Vision Exp , migrate to DeepSeek V4.1 Flash GLM 5.2 , migrate to GLM 5.3 Muse Glimmer 30B , migrate to NVIDIA Nemotron 3.5 Lightning 30B A3B Kimi K2.6 , migrate to GLM 5.3 or Kimi K3 Kimi K2.7 Code , migrate to GLM 5.3 or...