- 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
[`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))
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
<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>
<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>
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.
Kimi K3.1 Pro er en modell fra Moonshot med åpne vekter, lansert 2026-10-23. Kontekstvinduet er 1 048 576 tokener. Prisen er $2,00 per million inndatatokener og $10,00 per million utdatatokener.
Kontekstvindu
1 048 576
Inndata
bilde · tekst · video
Utdata
tekst
Vekter
Åpen
Inndata · USD / 1 mill. tokener
$2,00
Utdata · USD / 1 mill. tokener
$10,00
Bufrede inndata · USD / 1 mill. tokener
$0,20
Spørsmål
Hvor stort er kontekstvinduet til Kimi K3.1 Pro?
Kontekstvinduet er 1 048 576 tokener.
Hva koster Kimi K3.1 Pro?
Prisen er $2,00 per million inndatatokener og $10,00 per million utdatatokener. Bufrede inndata koster $0,20 per million tokener.
Er vektene til Kimi K3.1 Pro offentlig tilgjengelige?