Kimi K3 launches with 2.8T parameters, 1M context and $0.30 input pricing
togethercompute · x · 2026-07-28
Together’s Kimi K3 launch page adds more concrete product details around the model’s agent use case.
It describes Kimi K3 as Moonshot AI’s most capable model and the first open model in the 3-trillion-parameter class. The page highlights:
- 2.8T total parameters
- 16 of 896 experts activated per token
- Kimi Delta Attention and Attention Residuals as the architectural changes behind the model
- native vision plus a 1-million-token context window
- use cases such as extended engineering sessions, multi-step research, document workflows, and screenshots/charts/documents in the same model
- availability on serverless and dedicated infrastructure with 99.9% SLA
The page also lists launch pricing:
- Cached input: $3.00 per 1M tokens
- Input: $0.30 per 1M tokens
- Output: $15.00 per 1M tokens
More from coding & agent
- A unified RL harness can swap in Kimi Code, Claude Code, Codex, and more — stochasticchasm · 2026-07-28
- ChatGPT Work users are automating ticket alerts, listings, and trip planning from their phones — OpenAIDevs · 2026-07-28
- Kimi K3 launches on Together AI with Day 0 access for coding agents — togethercompute · 2026-07-28
- Open-source repo bundles 129 practical AI app, agent, and RAG projects — Arindam_1729 · 2026-07-28
- Kimi K3 is running a 9-subagent parallel creative workflow — altryne · 2026-07-28
- Kimi-style agentic reward modeling adds rubric scoring and budgeted verbosity control — stochasticchasm · 2026-07-28