Releasesby GlyphInference Expanded Small serverless rate-limit tier The Small serverless model tier now includes models with...
Inference Expanded Small serverless rate-limit tier The Small serverless model tier now includes models with fewer than 800B total parameters , up from 600B. The Medium tier now covers models from 800B to less than 1.6T . This moves models such as GLM 5.3 into the Small tier. The ceiling values for each tier are unchanged.
Also shipped Oct 18, 2026Fireworks AI in October 2026 →
feldera 0.367.0
- [pipeline-manager] expose the user creation time in /config/session [adapters] Reject JSON update format redis for input. Drop the YAML copy of the pipeline configuration [adapters] Read the operation of raw Avro input from cdc_field [web-console] Combine the storage status with the clear storage button [dbsp] Keep an old subcircuit live during a...
New serverless models
The following models are now available on serverless : deepseek-ai/DeepSeek-V4.1-Flash-1017 : 1,000,000 context length, FP8 quantization, function calling, and structured outputs. Pricing: $0.30 input / $1.20 output / $0.006 cached input (per 1M tokens).
Ollama 0.40.7
- pplx-decider is a 27B decision model from Perplexity, fine-tuned from Qwen3.8-27B - Continuing an OpenAI-compatible Responses conversation no longer fails when switching between models with and without thinking, or when the history contains another provider's compaction items - Fixed streaming Responses requests where client tool calls (e.g.
Request edit access to a project you can only view
You can now ask for edit access without leaving the project. Select Request to edit at the top of the project and add an optional message. Lovable emails the project's owner, or the workspace's admins and owners, who can approve or deny the request.
vLLM 0.32.0
v0.32.0 Highlights This release features 814 commits from 363 contributors (121 new)! - Structured decisions and generic parsers: the new POST /v1/systemone endpoint answers choice, noul and score questions over a structured state , is served by default (#60677, #60696), and also runs on Cloudflare/clef-omni , LiquidAI/d1-3B and DiffusionGemma .
More from Fireworks AI platformEvery Fireworks AI platform release →
Training Upcoming Serverless Training deprecation: DeepSeek V4 Flash (0731) On November 2, 2026 , DeepSeek V4...
Training Upcoming Serverless Training deprecation: DeepSeek V4 Flash (0731) On November 2, 2026 , DeepSeek V4 Flash (0731) will be removed from the shared Serverless Training pool. This change applies only to Serverless Training. If you train DeepSeek V4 Flash (0731) on Serverless Training, migrate to DeepSeek V4.1 Flash 1017 before November 2, 2026.
Training New Serverless Training model: DeepSeek V4.1 Flash 1017 DeepSeek V4.1 Flash 1017 is now available...
Training New Serverless Training model: DeepSeek V4.1 Flash 1017 DeepSeek V4.1 Flash 1017 is now available for LoRA workloads on the shared Serverless Training pool, with up to 262K context. It's available on Serverless Training only: Managed Training and the Dedicated Training API don't support it yet.
Training New training model: NVIDIA Nemotron 3.5 Super VL NVIDIA Nemotron 3.5 Super VL 120B A12B is now...
Training New training model: NVIDIA Nemotron 3.5 Super VL NVIDIA Nemotron 3.5 Super VL 120B A12B is now available for training on all three surfaces, with up to 262K context: Managed Training : LoRA SFT and DPO Dedicated Training API : LoRA and full-parameter training, including RL Serverless Training : LoRA on the shared pool, billed per token See the...
Training Upcoming Serverless Training deprecation: DeepSeek V4 Flash (0731) On November 2, 2026 , DeepSeek V4...
Training Upcoming Serverless Training deprecation: DeepSeek V4 Flash (0731) On November 2, 2026 , DeepSeek V4 Flash (0731) will be removed from the shared Serverless Training pool. This change applies only to Serverless Training. If you train DeepSeek V4 Flash (0731) on Serverless Training, migrate to DeepSeek V4.1 Flash 1017 before November 2, 2026.
Training New Serverless Training model: Muse Spark Open Muse Spark Open is now available for LoRA workloads...
Training New Serverless Training model: Muse Spark Open Muse Spark Open is now available for LoRA workloads on the shared Serverless Training pool, with up to 262K context. Use accounts/fireworks/models/muse-spark-open-nvfp4 as the base model. See the Serverless Training guide for setup and the training model catalog for current availability.
Action required
If you use any of the models below on serverless, migrate to a recommended replacement before November 7, 2026 . After that date, they will no longer be available via serverless endpoints.
Recommended migrations
- GPT OSS 120B , move to a dedicated deployment of GPT OSS 120B Inkling , migrate to Muse Spark Open (US endpoint, 50% US regional premium waived) NVIDIA Nemotron 3 Ultra , move to a dedicated deployment of Nemotron Super VL NVIDIA Nemotron 3.5 Lightning 30B A3B , move to a dedicated deployment of Nemotron Super VL MiniMax M3 (US endpoint only) , migrate to...
New models on Serverless
- DeepSeek V4.1 Flash 1017: accounts/fireworks/models/deepseek-v4p1-flash-1017 DeepSeek V4.1 Flash 1017 (US endpoint): accounts/fireworks/routers/deepseek-v4p1-flash-1017-us ( US-only Serverless ) Muse Spark Open (US endpoint, 50% US regional premium waived): accounts/fireworks/models/muse-spark-open MiniMax M3.1: coming to serverless after its open-source...