Kimi K2.5 vs NVIDIA Nemotron 3 Super 120B A12B BF16
At a Glance
| Compare |  Kimi K2.5Moonshot AI | |
|---|---|---|
| Pricing and Limits | ||
| Input priceFrom · USD / 1M tokens | $0.45Deepinfra ↗ · Aug 29, 2026 | Not reported |
| Output priceFrom · USD / 1M tokens | $2.25Deepinfra ↗ · Aug 29, 2026 | Not reported |
| Context windowMaximum documented tokens | 262K | 262K |
| Model facts checked | Aug 28, 2026View model evidence → | Aug 28, 2026View model evidence → |
Token prices are the lowest available sourced USD rates; input and output may use different providers. Cost ranking estimates output spend on LiveBench, not a full request bill. Ranking methodology →
Available Benchmarks
Side-by-Side Facts
| Field | Kimi-K2.5 | NVIDIA-Nemotron-3-Super-120B-A12B-BF16 |
|---|---|---|
| Developer | Moonshot AI | NVIDIA |
| Family | Kimi K2 5 | Nvidia Nemotron 3 Super 120b A12b Bf16 |
| Model | Kimi-K2.5 | NVIDIA-Nemotron-3-Super-120B-A12B-BF16 |
| Version | Kimi-K2.5 | NVIDIA-Nemotron-3-Super-120B-A12B-BF16 |
| Lifecycle | active | active |
| Released | 2026-01-27 | 2026-03-11 |
| Knowledge cutoff | Unknown | Unknown |
| Input modalities | Text, Image | Text |
| Output modalities | Text | Text |
| Context window | 262K | 262K |
| Total parameters | 1T | 123.6B |
| Active parameters | 32B | 12B |
| License | other | other |
| Open weights | Yes | Yes |
| API available | Yes | Yes |
| Self-hostable | Yes | Yes |
| Provider access | Deepinfra (Standard), Hugging Face (Standard), Openrouter (Standard) | Hugging Face (Standard), Together Ai (Standard) |
| Capabilities | chat, generation, reasoning, tools | chat, generation, reasoning, tools |
Kimi K2.5 Capabilities
NVIDIA Nemotron 3 Super 120B A12B BF16 Capabilities
Related Comparisons
All text comparisons →| A | Pair | B | Context |
|---|---|---|---|
Kimi-K2.5Moonshot AI | vs |  GPT-6 AstraOpenAI | cross-developer peersimage, text |
Claude Fable 5.1Anthropic | vs | Kimi-K2.5Moonshot AI | cross-developer peersimage, text |
 Gemini 3.1 ProGoogle DeepMind | vs | Kimi-K2.5Moonshot AI | cross-developer peerstext |
 DeepSeek-V4.1-FlashDeepSeek | vs | Kimi-K2.5Moonshot AI | cross-developer peersimage, text |
Kimi-K2.5Moonshot AI | vs | Grok 4.6xAI | cross-developer peersimage, text |
Kimi-K2.5Moonshot AI | vs |  Qwen3.8-MaxQwen | cross-developer peersimage, text |
Kimi-K2.5Moonshot AI | vs | Kimi-K3Moonshot AI | family variantsembedding, image, text |
 MiniMax-M3MiniMax | vs | Kimi-K2.5Moonshot AI | cross-developer peersimage, text |
Kimi-K2.5Moonshot AI | vs |  GLM-5.3Z.ai | cross-developer peerstext |
Kimi-K2.5Moonshot AI | vs |  Hy4 previewTencent | cross-developer peerstext |
Seed 2.1 ProByteDance Seed | vs | Kimi-K2.5Moonshot AI | cross-developer peersimage, text |
 Mistral Large 3Mistral AI | vs | Kimi-K2.5Moonshot AI | cross-developer peersimage, text |
Primary Evidence
Sources and Freshness
Questions
Kimi K2.5 vs NVIDIA Nemotron 3 Super 120B A12B BF16 FAQs
Is Kimi K2.5 or NVIDIA Nemotron 3 Super 120B A12B BF16 better for coding?+
This comparison does not currently contain a protocol-matched coding benchmark for both Kimi K2.5 and NVIDIA Nemotron 3 Super 120B A12B BF16, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.
Which is cheaper, Kimi K2.5 or NVIDIA Nemotron 3 Super 120B A12B BF16?+
Only Kimi K2.5 has a directly sourced input price: $0.45 per million tokens. Only Kimi K2.5 has a directly sourced output price: $2.25 per million tokens.
Which has a larger context window, Kimi K2.5 or NVIDIA Nemotron 3 Super 120B A12B BF16?+
Neither model has a larger sourced context window in this comparison. Kimi K2.5 is 262K and NVIDIA Nemotron 3 Super 120B A12B BF16 is 262K.
Which performs better in benchmarks, Kimi K2.5 or NVIDIA Nemotron 3 Super 120B A12B BF16?+
There is no overall benchmark winner: At least two independently verified, protocol-matched benchmarks are required for an overall winner.
Can Kimi K2.5 or NVIDIA Nemotron 3 Super 120B A12B BF16 be self-hosted?+
Both models have the same recorded self-hosting status: supported. Kimi K2.5 is open weight; NVIDIA Nemotron 3 Super 120B A12B BF16 is open weight.
Can Kimi K2.5 and NVIDIA Nemotron 3 Super 120B A12B BF16 understand images?+
Kimi K2.5 is documented with image input; NVIDIA Nemotron 3 Super 120B A12B BF16 is not documented with image input. This reflects supported input modalities, not vision quality.
Which can generate longer answers, Kimi K2.5 or NVIDIA Nemotron 3 Super 120B A12B BF16?+
Neither has a larger sourced maximum output. Kimi K2.5 is — and NVIDIA Nemotron 3 Super 120B A12B BF16 is —.
Do Kimi K2.5 and NVIDIA Nemotron 3 Super 120B A12B BF16 support reasoning and tool use?+
Kimi K2.5: reasoning, tool calling, and image input. NVIDIA Nemotron 3 Super 120B A12B BF16: reasoning and tool calling. Feature support does not establish relative quality.
Which is available from more inference providers, Kimi K2.5 or NVIDIA Nemotron 3 Super 120B A12B BF16?+
Kimi K2.5 has 3 sourced provider routes; NVIDIA Nemotron 3 Super 120B A12B BF16 has 2, so Kimi K2.5 has broader tracked availability.
Which offers better value, Kimi K2.5 or NVIDIA Nemotron 3 Super 120B A12B BF16?+
There is no universal value winner. Compare the input and output prices above with the matched benchmark result for your workload: cheaper tokens can be offset by different quality, token usage, latency, or provider availability.