Releasesby IbisPost-training
UpdatetodayUnverifiedAdded Oct 13, 2026
Post-training lets you write your own training loop and run it against Together AI GPUs. Your code builds each batch and chooses the loss function and learning rate, while the GPUs you provision run the forward and backward passes, optimizer steps, and sampling. It bills per GPU-minute.
Topics: Developer tools
More Together AI platform releases
Every Together AI platform releaseWhat's included:
- Three training methods: Supervised fine-tuning (SFT) , direct preference optimization (DPO) , and reinforcement learning with group relative policy optimization (GRPO) . Each method trains a low-rank adapter (LoRA) or the full model weights. Custom loss functions : Train with any objective you compute in PyTorch from the model's log-probabilities.
New provisioned throughput models
The following models are now available on provisioned throughput : zai-org/GLM-5.3 . zai-org/GLM-5.3-Flash . deepseek-ai/DeepSeek-V4.1-Flash .
Dynamic rate limits for serverless retired
Serverless no longer applies dynamic rate limits that scale with your recent traffic. Most users will no longer encounter rate limits, though requests can still be limited during periods of high demand. If you get a 429 Too Many Requests response, reduce your request rate and spread out bursts.
Together Link beta
Together Link runs six coding agents on models hosted by Together AI: Claude Code, Codex, OpenCode, and Pi Code in the terminal, plus Claude Desktop (including Cowork) and ChatGPT Desktop. Install it with one command, launch your agent through it, and your normal agent configuration stays untouched. It's now in beta on macOS and Linux.
What's included:
- Six agents: Launch Claude Code ( tclaude ), Codex ( tcodex ), OpenCode ( topencode ), or Pi Code ( tpi ) in your terminal, or switch Claude Desktop and ChatGPT Desktop to a reversible Together Link profile. OpenCode requires OpenCode 2, and Pi Code requires version 0.80.8 or newer.
Code sandbox SDK and CLI
The new together-sandbox SDK runs commands and code in isolated runtime environments built from Docker-image snapshots. It ships as a Python SDK, a TypeScript SDK, and a standalone CLI, and is available to organizations on an allowlist ( contact us to request access).
New dedicated endpoint models
The following models are now available for deployment on dedicated endpoints : hexgrad/Kokoro-82M (text-to-speech). Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice (text-to-speech).
Higher LoRA rank limit for fine-tuning
You can now train LoRA adapters with a rank of up to 128 for the majority of models, up from 64. The default rank for these models stays at 64, so set lora_r to use a higher one. The model limits response has a new lora_training.default_rank field next to lora_training.max_rank . Run tg fine-tuning model-limits to see both values for a model.
Also shipped on Oct 13, 2026
Together AI in October 2026LangSmith SDK 0.14.8
- fix(py): send session_id on RunTree.patch fix: keep punctuation out of freeze guard links chore(deps): bump source-map-js from 1.2.1 to 1.2.2 in /js fix(py): make the /runs/multipart 404 fallback to /runs/batch reachable feat(sandbox): accept any JOSE asymmetric algorithm chosen by the JWKS key (python) feat(sandbox): customer-managed KMS keys for S3...
Retry jobs with narrower API token permissions
Retry automation no longer needs the broader write_builds REST API scope. The new retry_builds scope allows a token to retry failed jobs in existing builds or individual eligible jobs, without granting access to the create-build or rebuild endpoints. When creating or editing an API access token, select Build Retries ( retry_builds ).
2026-10-13 updates
See what changed in Sourcegraph.
truss 0.18.34
- Add include and exclude filters to BDN mount configuration feat: Forward egress_restrictions for BIS and warn about missing hosts Release 0.18.34
arize-phoenix-sqlean: v0.2.0
0.2.0 (2026-10-12) Features phoenix-sqlean: bundle SQLite 3.54.0 and support Python 3.15 (fff25bc)
Agent skills v0.2996.0
Build from c2cd5c6467dbf3306291821b4c421ef09fc5b143