Managed reinforcement fine-tuning paused; 70 models no longer tunable

Managed reinforcement fine-tuning (RFT) is paused. Managed Training no longer accepts new RFT jobs from the Fireworks UI, firectl, or the REST API. Existing jobs stay visible in your dashboard, and models you already trained with managed RFT keep serving.

Try RL on the Training API, where you write the rollout and training loop yourself and Fireworks runs the GPUs. Compared with managed RFT, you also get:

• Full-parameter RL on most current models, not just LoRA
• The training shape's full context length, up to 524K tokens, instead of managed RFT's fixed 32K limit
• Other methods such as on-policy distillation (OPD) and custom objectives

Your evaluator logic carries over. Start with Cookbook: Reinforcement Learning.

Managed SFT and DPO are unaffected.

Models no longer available for fine-tuning

The 70 models below were tunable only through managed RFT. With managed RFT paused, none of them can be fine-tuned on Fireworks anymore, and they no longer appear on the Models page. Inference on these models is not affected by this change.

[accordion] Full list (70 models)

• DeepSeek: deepseek-r1, deepseek-r1-basic, deepseek-r1-0528, deepseek-r1-0528-distill-qwen3-8b, deepseek-r1-distill-llama-8b, deepseek-r1-distill-llama-70b, deepseek-r1-distill-qwen-14b, deepseek-r1-distill-qwen-32b, deepseek-v3, deepseek-v3-0324, deepseek-v3p1, deepseek-v3p1-terminus, deepseek-prover-v2, deepseek-coder-1b-base
• Kimi: kimi-k2-instruct, kimi-k2-instruct-0905, kimi-k2-thinking
• GLM: glm-4p5, glm-4p6, glm-4p7
• Qwen 3: qwen3-1p7b, qwen3-30b-a3b, qwen3-30b-a3b-thinking-2507, qwen3-235b-a22b, qwen3-235b-a22b-thinking-2507, qwen3-coder-30b-a3b-instruct, qwen3-vl-30b-a3b-instruct, qwen3-vl-30b-a3b-thinking, qwen3-vl-235b-a22b-instruct, qwen3-vl-235b-a22b-thinking
• Qwen 2.5 and QwQ: qwen2p5-14b, qwen2p5-14b-instruct, qwen-v2p5-14b-instruct, qwen2p5-32b, qwen2p5-coder-14b, qwen2p5-coder-14b-instruct, qwen2p5-coder-32b, qwen2p5-coder-32b-instruct, qwen2p5-coder-32b-instruct-32k-rope, qwen2p5-coder-32b-instruct-64k, qwen2p5-coder-32b-instruct-128k, qwen2p5-vl-7b-instruct, qwq-32b, qwen-qwq-32b-preview
• Llama: llama-v3-8b, llama-v3-8b-instruct, llama-v3-8b-instruct-hf, llama-v3-70b-instruct, llama-v3-70b-instruct-hf, llama-v3p1-70b-instruct, llama-v3p1-nemotron-70b-instruct, llama-v3p2-1b, llama-v3p2-1b-instruct, llama-guard-2-8b, llama-guard-3-1b, llama-guard-3-8b
• gpt-oss: gpt-oss-20b, gpt-oss-120b, gpt-oss-safeguard-20b, gpt-oss-safeguard-120b
• Gemma: gemma-3-27b-it
• Other: cogito-v1-preview-llama-8b, cogito-v1-preview-llama-70b, cogito-v1-preview-qwen-14b, cogito-v1-preview-qwen-32b, fare-20b, firefunction-v2, kat-dev-32b, mirothinker-1p7, rolm-ocr