Together AI partners with IBM and NVIDIA on dedicated B300 cluster for open-source inference

TTogether AI10/7/2026, 14:31:19

Together AI announced it is scaling open-source model inference in partnership with IBM and NVIDIA using a dedicated B300 cluster deployed on IBM Cloud.

IBM Cloud General Manager Alan Peacock noted that spending money on tokens remains worthwhile as long as the business realizes the benefit.

#together-ai #ibm-cloud #nvidia #ai-infrastructure

View original post ↗

Previous articleArtificial Analysis launches AA-Music v1.1 benchmarks with Suno v6 leading Next articleOpenRouter adds Perplexity Decider v1.1 with free output

Related AI news

Together AI says it leads OpenRouter token share for top open coding models

Together AI says it currently has the largest OpenRouter token share for GLM 5.3 Flash, DeepSeek V4.1 Flash, and Kimi K3, at 29.2%, 25.6%, and 18.9% respectively.

TTogether AI•9/29/2026, 08:17:06•

#together-ai #openrouter #glm-5.3-flash #deepseek #kimi-k3

Together AI publishes Tev1-4B-experimental weights on Hugging Face

The Tev1-4B-experimental weights are in the togethercomputer repository on Hugging Face. Together AI describes the model as an experiment meant to show how specialized decision models can be trained fairly easily.

TTogether AI•9/23/2026, 15:16:56•

#together-ai #tev1-4b #hugging-face #model-weights

Together AI releases tev1-4B-experimental on Together serverless

The Jev-like classifier is finetuned on Qwen3.5 4B and priced at $0.042/M input and $0/M output. Together AI is also releasing a data recipe and a finetuning tutorial, and says training Tev1 cost $17.

TTogether AI•9/23/2026, 15:11:55•

#together-ai #tev1 #qwen #model-release #pricing

Together AI offers 40% off Qwen3.7-Max and Qwen3.8-Flash on serverless through September 30

The discount applies to both Alibaba_Qwen models on Together AI serverless and runs through September 30. Together AI recommends Qwen3.7-Max for long-horizon agent work and Qwen3.8-Flash for high-volume, cost-sensitive workloads.

TTogether AI•9/23/2026, 11:42:04•

#qwen #together-ai #pricing #serverless

Together AI adds canary rollouts to Dedicated Model Inference

Dedicated Model Inference can now upgrade the model behind a live endpoint without downtime. Traffic shifts in gated steps, and metric gates can pause a rollout if p95 latency or the error rate worsens.

TTogether AI•9/22/2026, 17:03:44•

#together-ai #dedicated-model-inference #canary-rollouts #model-deployment

Reset history AI News FAQ Usage limits RSS feeds API MCP Skill

News is compiled from public information. The data is for reference only, and this site has no affiliation with OpenAI.

Data & original project: Did Codex Reset · Licoy