The latest AI news and updates of Fireworks AI — AI inference platform for fast, customizable model serving and compound AI systems at scale. Covering Fireworks AI's latest product updates, analysis, and company news from the past 90 days.
Fireworks AI14h agoFireworks AI now serves Qwen 3.7 Plus as a direct inference provider, offering full control over latency and data paths. The model supports thinking and non-thinking modes, preserved reasoning history, and prompt caching by default. It is available on serverless endpoints compatible with OpenAI and Anthropic APIs, priced at 0.50 dollars per million input tokens.
Fireworks AI15h agoFireworks AI launched day-0 support for MiniMax M3, a multimodal model featuring native image and video input. Powered by MiniMax Sparse Attention, the model delivers 9× faster prefill and 15× faster decode speeds. It is available now on serverless and on-demand endpoints, priced at parity with M2.7 at $0.30 per million input tokens.
Fireworks AIJun 4Fireworks AI now offers NVIDIA Nemotron 3 Ultra, an open model for advanced autonomous agents, with immediate deployment support. This provides developers with optimized infrastructure for long-running agentic tasks that require frontier reasoning and orchestration.
Fireworks AIJun 4Fireworks AI has deployed Step 3.7 Flash, a 198B-parameter vision-language model designed for rapid inference. The model enables real-time agentic workflows by delivering up to 400 tokens per second with selectable reasoning depths.
Fireworks AIJun 4Fireworks AI is now powering inference for MiniMax M3, a multimodal model featuring a novel sparse attention architecture. The partnership enables 15.6x faster decoding at 1-million-token context, making real-time agentic workflows viable at scale.
Fireworks AIJun 4Fireworks AI demonstrated that a GLM 5.1 worker using Claude Opus 4.7 as a sparse advisor beats standalone Opus on legal benchmarks. This architectural shift achieves higher accuracy on complex tasks while reducing inference costs by over 60%.
Fireworks AIJun 2Microsoft AI is launching a family of seven in-house models and partnering with Fireworks AI to enable weight-level customization. This allows organizations to integrate proprietary institutional knowledge directly into Microsoft's frontier reasoning models.
Fireworks AIMay 30Fireworks AI launched Serverless 2.0, introducing three distinct serving paths—Standard, Priority, and Fast—to its inference platform. By allowing developers to choose between cost-efficiency, congestion reliability, or high throughput at the request level, the update removes the binary choice between shared fleets and expensive reserved capacity.
Fireworks AIMay 29NVIDIA CEO Jensen Huang characterized Fireworks AI as the TSMC of AI factories, highlighting the company's specialized role in the inference stack. This endorsement signals a shift where high-performance inference providers are becoming the essential foundries for the generative AI era.
Fireworks AIMay 29Ramp Labs used a fleet of 10,000 autonomous agents powered by open-weight models to identify high-severity vulnerabilities in its production backend. The deployment achieved a fivefold reduction in token costs compared to GPT 5.5 while maintaining the reasoning depth required for complex security auditing.
Fireworks AIMay 27Cursor and Fireworks AI shared a technical breakdown of the distributed reinforcement learning infrastructure used to build the Composer 2.5 coding model. The team treats model weights as finite storage bits dedicated entirely to software engineering, allowing the model to match frontier performance at one-tenth the cost. This shift demonstrates how specialized products can use real-world usage as a proprietary training loop.
Fireworks AIMay 20Fireworks AI released a benchmark report on browser agents revealing that malformed outputs create a hidden execution tax that inflates production costs. The study found that reliability in multi-step loops matters more than raw intelligence, with some frontier models wasting nearly a quarter of their inference budget on retries.
Fireworks AIMay 16Fireworks AI expanded its training platform to support full-parameter and LoRA-based reinforcement learning for Google's Gemma 4 Dense model. This allows developers to perform SFT, DPO, or RL on the model's full 256K context window using a unified stack that eliminates numerical drift between training and production.
Fireworks AIMay 15Fireworks AI launched managed fine-tuning for Alibaba's Qwen 3.6 27B model, supporting 256K context windows and out-of-the-box DPO. This allows developers to specialize a high-performance dense model for complex coding and reasoning tasks on a production-ready stack.
Fireworks AIMay 15Fireworks AI added DeepSeek V4 Pro and Kimi K2.6 to Microsoft Azure AI Foundry while expanding provisioned throughput support to the US Data Zone. The update allows enterprise teams to run high-performance open models with guaranteed throughput and data residency within their existing Azure environment.
Fireworks AIMay 15Fireworks AI expanded its training platform to support LoRA-based reinforcement learning for Z.ai's GLM 5.1 model. This allows developers to align the model's reasoning steps with specific domain logic using custom loss functions on a 200K context window.
Fireworks AIMay 13Fireworks AI added full-parameter reinforcement learning support for Moonshot AI's 1-trillion parameter Kimi K2.6 model. This allows developers to tune the entire model weight set on proprietary data to build specialized agentic moats that outperform off-the-shelf frontier systems.
Fireworks AIMay 5Fireworks AI introduced a distributed reinforcement learning architecture that uses delta-compressed weight updates to sync training and inference clusters across different regions. By shipping only the 2% of weights that change between checkpoints, teams can train frontier-scale models using fragmented GPU capacity instead of expensive mega-clusters.
Fireworks AIApr 30Fireworks AI introduced an opt-in safe_tokenization flag that prevents user input from being parsed as model control tokens. This update addresses a fundamental security flaw in open-weights inference where malicious text can forge turn boundaries to bypass system instructions. By separating user content from structural code at the tokenizer level, developers can ensure their core product logic remains authoritative.
Fireworks AIApr 30Fireworks AI integrated Alibaba's Qwen 3.5 into its training platform, supporting full-parameter fine-tuning and reinforcement learning with a 256K context window. This allows developers to customize the high-performance open-weight model for specialized reasoning and coding tasks on a unified stack.
Fireworks AIApr 28Fireworks AI integrated Google's Gemma 4 models into its training platform, enabling full-parameter fine-tuning and DPO with a 256K context window. This allows teams to build specialized reasoning agents on a unified stack that transitions from training to production inference in seconds.
Fireworks AIApr 28Fireworks AI added Z.ai's GLM 5.1 to its training platform, supporting supervised fine-tuning and direct preference optimization with a 200K context window. This allows developers to customize the flagship agentic model for multi-hour autonomous tasks without the numerical drift common in fragmented training and inference stacks.
Fireworks AIApr 27Fireworks AI added DeepSeek V4-Pro to its inference platform, offering frontier-level coding and reasoning via an open-weight model. The deployment standardizes a 1-million token context window at a price point significantly lower than closed-source competitors.
Fireworks AIApr 25Fireworks AI added Moonshot AI's Kimi K2.6 to its training platform, enabling supervised fine-tuning and reinforcement learning on the 1-trillion parameter model. This allows teams to customize the leading open-weight agentic model for specific production workflows while maintaining a 265K context window.
Fireworks AIApr 21Fireworks AI added immediate support for Kimi K2.6, a 1-trillion parameter multimodal model optimized for long-horizon agentic coding. The update provides the high-speed inference and fine-tuning infrastructure needed to run the successor to the model that powered Cursor's Composer 2.
Fireworks AIApr 8Fireworks AI released a training platform in preview that supports full-parameter fine-tuning for models ranging from 8B to 1T parameters. This allows teams to move beyond prompt engineering by using reinforcement learning to build proprietary models that outperform closed frontier systems on specific tasks.
Fireworks AIApr 5Fireworks AI released a major update to its Training SDK featuring Blackwell-native kernels and 4D parallelism for trillion-parameter Mixture-of-Experts models. By fusing reinforcement learning losses and optimizing for asynchronous data, the platform enables frontier-grade model training that was previously restricted to elite research labs.
Fireworks AIMar 28Fireworks AI revealed the infrastructure behind Cursor's Composer 2, using disaggregated sampling to run RL across multiple global clusters. By shipping only 2% of model weights as compressed deltas, they eliminated the need for a single massive mega-cluster. This shift makes frontier-scale RL training economically viable using fragmented, multi-region GPU capacity.
Frequently asked questions