Kimi K3.1 Pro
Moonshot
- Janela de contexto
- 1M 1.048.576 tokens
- Entrada / Saída
- imagem, texto, vídeo → texto
Preços da API
USD / 1 milhão de tokens
| Entrada | Saída | Entrada em cache |
|---|---|---|
|
|
|
Cronologia
- · Versão dos pesos · link de referência
Preço entrada/saída · USD / 1 milhão de tokens
| Modelo | Links de referência | Preço entrada/saída |
|---|---|---|
moonshotai/kimi-k3.1-prostandard | openrouter | $2,00 / $10,00 |
moonshotai/kimi-k3.1-pro:batchbatch | openrouter | $0,70 / $6,00 |
moonshotai/kimi-k3.1-prostandard | vercel-gateway | $2,00 / $10,00 |
kimi-k3.1-prostandard · texto | opencode-go | $2,00 / $10,00 |
- · Links de referência · GitHub search · Moonshot · commits · renj-arch/dimsred · @github-actions[bot]
Excerto
Kimi K3.1 Pro is NOT callable. build.nvidia.com publishes the model, but its
- · Links de referência · GitHub search · Moonshot · commits · renj-arch/dimsred · @github-actions[bot]
- · Links de referência · GitHub search · Moonshot · commits · cmyolo441-coder/py.test · @claude
- · Links de referência · GitHub search · Moonshot · commits · MadAppGang/claudish · @erudenko
- · Links de referência · GitHub search · Moonshot · commits · DarkPrince922/Oreshnik · @claude
Excerto
The form showed "Для Strix: openai/kimi-k3.1-pro" under a model with no such
- · Links de referência · GitHub search · Moonshot · pulls · zhao-wuyan/llm-info · @github-actions[bot]
- · Links de referência · GitHub search · Moonshot · pulls · vllm-project/vllm · @xaguilar-amd
Excerto
- With Kimi-K3.1-Pro and the recipe's DSpark draft (`kv_cache_dtype: fp8`) on 8x MI325X, draft acceptance at 3 speculative tokens no longer collapses after a batch
- · Links de referência · GitHub search · Moonshot · pulls · vercel-labs/fx · @fazxes
Excerto
- Kimi K3.1 Pro (`moonshotai/kimi-k3.1-pro`) is now a Token Pass model.
- · Links de referência · GitHub search · Moonshot · pulls · router-for-me/CLIProxyAPI · @evan188199-tech
Excerto
feat(devin): add claude-fable-5-2 and kimi-k3-1-pro to default catalog
- · Links de referência · GitHub search · Moonshot · pulls · keithhchen/hatch · @keithhchen
Excerto
Models: new `hatch_model_roles` roles `inspiration` and `content`, seeded `kimi-k3.1-pro`, resolved per session role.
- · Links de referência · GitHub search · Moonshot · pulls · keithhchen/hatch · @keithhchen
- · Links de referência · GitHub search · Moonshot · pulls · huggingface/speech-to-speech · @andimarafioti
Excerto
Models: Qwen3.8-2.4T, Qwen3.8-27B, Gemma 4 31B, DeepSeek-V4.1-Flash, DeepSeek-V4-Pro, Kimi-K3.1-Pro, GLM-5.3, MiniMax-M3.1-Flash, Mistral-Large-4, Muse-Spark-Open, Nemotron-3.5-Super, Hy4-preview; small: LFM3-1.7B, Ling-3.0-tiny, granite-4.2-3b, granite-4.2-8b, Qwen3.5-9B, LFM2.5-24B, Nemotron-3.5-Lightning, Gemma 4
- · Links de referência · GitHub search · Moonshot · pulls · can1357/oh-my-pi · @will-bogusz
- · Links de referência · GitHub search · Moonshot · pulls · attilaolah/dotfiles · @renovate[bot]
Excerto
[`bcb0152`](https://redirect.github.com/ggml-org/llama.cpp/commit/bcb015287) model: add Kimi-K3.1-Pro text model ([#​31779](https://redirect.github.com/ggml-org/llama.cpp/issues/31779))
- · Links de referência · GitHub search · Moonshot · pulls · adiudiuu/tps · @adiudiuu
- · Links de referência · GitHub search · Moonshot · pulls · adiudiuu/tps · @adiudiuu
- · Links de referência · GitHub search · Moonshot · pulls · Pinvou/CodeWhale · @asto18089
Excerto
documents that missing field as HTTP 400. The `kimi-k3.1-pro[-highspeed]` direct-platform spellings did replay at default effort via the generic `kimi-` prefix heuristic, but were still
- · Links de referência · GitHub search · Moonshot · pulls · JavaZeroo/torchtitan · @JavaZeroo
Excerto
| Kimi-K3.1-Pro attention shape (96 heads, 4096 tokens, top-k 2048), pairs, 1x H100 | first call about 7 s (compile), then 12 ms forward and
- · Links de referência · GitHub search · Moonshot · pulls · Heknon/AskCalls · @dependabot[bot]
Excerto
<li>ai-sdk-provider: add kimi-k3-1-pro to known model ids by <a href="https://github.com/andrelandgraf"><code>@andrelandgraf</code></a> in <a href="https://redirect.github.com/neondatabase/neon-pkgs/pull/1091">neondatabase/neon-pkgs#1091</a></li>
- · Links de referência · GitHub search · Moonshot · pulls · Heknon/AskCalls · @dependabot[bot]
Excerto
<li>ai-sdk-provider: add kimi-k3-1-pro to known model ids by <a href="https://github.com/andrelandgraf"><code>@andrelandgraf</code></a> in <a href="https://redirect.github.com/neondatabase/neon-pkgs/pull/1091">neondatabase/neon-pkgs#1091</a></li>
- · Links de referência · GitHub search · Moonshot · commits · Nulluminati/pi-extensions · @Nulluminati
- · Links de referência · GitHub search · Moonshot · pulls · lightseekorg/tokenspeed · @Yu-Zhewen
Excerto
Kimi-K3.1-Pro on 8x MI355X (TP8, KVP8, FP8 KV cache, 3 DSpark drafts, the gfx950 stack through #3355), InferenceX's acceptance-length gate: SPEED-Bench coding prompts, 80 requests
- · Links de referência · GitHub search · Moonshot · pulls · lidge-jun/opencodex · @andrew05060414
Excerto
rows showed prices. `cn:deepseek-v4.1-flash` came from OpenRouter (0.3/1.2). `cn:kimi-k3.1-pro`, `cn:glm-5.3-flash`, `zd/gpt-6-sol` and `zd/gemini-4-argon` came from models.dev.
- · Links de referência · GitHub search · Moonshot · pulls · anomalyco/models.dev · @models-dev-automation[bot]
Excerto
- created: `/home/runner/_work/models.dev/models.dev/providers/requesty/models/kimi-k3.1-pro@eu.toml`
Links de referência
- · Entrada no catálogo · Moonshot API ·
kimi-k3.1-pro
Sinais 4
Especificações
Kimi K3.1 Pro é um modelo de Moonshot com pesos abertos, lançado em 2026-10-23. A janela de contexto é de 1.048.576 tokens. O preço por milhão de tokens é de $2,00 na entrada e $10,00 na saída.
- Janela de contexto
- 1.048.576
- Entrada
- imagem · texto · vídeo
- Saída
- texto
- Pesos
- Abertos
- Entrada · USD / 1 milhão de tokens
- $2,00
- Saída · USD / 1 milhão de tokens
- $10,00
- Entrada em cache · USD / 1 milhão de tokens
- $0,20
Perguntas
Qual é a janela de contexto do Kimi K3.1 Pro?
A janela de contexto é de 1.048.576 tokens.
Quanto custa o Kimi K3.1 Pro?
O preço por milhão de tokens é de $2,00 na entrada e $10,00 na saída. A entrada em cache custa $0,20 por milhão.
O Kimi K3.1 Pro tem pesos abertos?
Sim. Moonshot disponibiliza os pesos.
Quando o Kimi K3.1 Pro foi lançado?
Em 2026-10-23.