Kimi K2.5
moonshotai/kimi-k2-5Par Moonshot AI · famille: kimi-k2 · sorti 2026-01 · fin de connaissance: 2025-01
Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.
Capacités
Model fit scores
0–100 · higher is betterThese scores reward declared capabilities, context size, price and provider availability — they are not benchmark results. Use them as a directional signal alongside your own evaluation.
Coding88
- Tool calling40/40
- Structured output20/20
- Reasoning10/10
- Context window (100K → 1M)8/20
- Provider availability10/10
Agents100
- Tool calling35/35
- Structured output25/25
- Reasoning15/15
- Output token limit15/15
- Provider availability10/10
JSON / structured output96
- Structured output / JSON mode50/50
- Tool calling20/20
- Temperature control10/10
- Price-friendly for high-volume16/20
Cost efficiency59
- Headline price (log-scaled)54/95
- Has prompt-cache pricing5/5
Long context61
- Context window (100K → 2M)51/90
- Has published price for full window10/10
Vision91
- Accepts image input50/50
- Context window (10K → 1M)21/30
- Has published price10/10
- Provider availability10/10
Production-readiness94
- Number of independent providers40/40
- Has published per-token price20/20
- Context window ≥ 8K15/15
- No data inconsistencies across providers4/10
- Official model (not derivative)15/15
Cost Efficiency Index
Open full calculator →Estimated cost using the recommended provider's headline rate. Each scenario fixes average input/output tokens — the assumptions are shown in the third column.
| Scenario | Cost | Assumption |
|---|---|---|
RAG answer per 1,000 RAG answers | $2.45 < $0.01 per request | 5K input tokens (query + 4 retrieved chunks of ~1K each) and a 500-token answer. Typical SaaS knowledge-base bot. |
Support ticket triage per 10,000 tickets | $4.90 < $0.01 per request | 1K input tokens (ticket body + system prompt) and a 100-token JSON classification reply. High-volume customer support. |
Data extraction per 1,000 documents | $1.55 < $0.01 per request | 2K input tokens (a single document page) and a 500-token JSON extraction. ETL / invoice / form pipelines. |
Code review per 1,000 PRs | $4.30 < $0.01 per request | 8K input tokens (diff + surrounding files) and a 1K-token review comment. PR-bot workloads. |
Agent step per 1,000 steps | $4.74 < $0.01 per request | 12K input tokens (long-running tool history) and a 600-token tool-call decision. Cost per agent step. |
Détail des tarifs
Tarif recommandé de nano-gpt · moonshotai/kimi-k2.5
Fournisseur le moins cher : alibaba-token-plan · Unknown entrée + Unknown sortie
Disponible chez 50 fournisseurs
| Fournisseur | ID modèle fournisseur | Entrée / 1M | Sortie / 1M | Contexte | Publié le |
|---|---|---|---|---|---|
| Azure azure | kimi-k2.5 | $0.600 | $3.00 | 262K | 2026-02-06 |
| Amazon Bedrock amazon-bedrock | moonshotai.kimi-k2.5 | $0.600 | $3.00 | 262K | 2026-01-27 |
| OpenRouter openrouter | moonshotai/kimi-k2.5 | $0.450 | $2.25 | 262K | 2026-01 |
| Vercel AI Gateway vercel | moonshotai/kimi-k2.5 | $0.600 | $3.00 | 256K | 2026-01 |
| Together AI togetherai | moonshotai/Kimi-K2.5 | $0.500 | $2.80 | 262K | 2026-01-27 |
| Deep Infra deepinfra | moonshotai/Kimi-K2.5 | $0.450 | $2.25 | 262K | 2026-01-27 |
| Hugging Face huggingface | moonshotai/Kimi-K2.5 | $0.600 | $3.00 | 262K | 2026-01-01 |
| Alibaba Token Plan alibaba-token-plan | kimi-k2.5 | Unknown | Unknown | 262K | 2026-01 |
| NanoGPT nano-gpt | moonshotai/kimi-k2.5 | $0.300 | $1.90 | 256K | 2026-01 |
| Baseten baseten | moonshotai/Kimi-K2.5 | $0.600 | $3.00 | 262K | 2026-01-30 |
| SiliconFlow siliconflow | moonshotai/Kimi-K2.5 | $0.450 | $2.25 | 262K | 2026-01-27 |
| Alibaba Coding Plan alibaba-coding-plan | kimi-k2.5 | Unknown | Unknown | 262K | 2026-01-27 |
| LLM Gateway llmgateway-providers | embercloud/kimi-k2.5 | $0.405 | $1.98 | 262K | 2026-01 |
| LLM Gateway llmgateway-providers | moonshot/kimi-k2.5 | $0.600 | $3.00 | 262K | 2026-01 |
| Kilo Gateway kilo | moonshotai/kimi-k2.5 | $0.600 | $3.00 | 262K | 2026-01 |
| Venice AI venice | kimi-k2-5 | $0.560 | $3.50 | 256K | 2026-01-27 |
| Alibaba Token Plan (China) alibaba-token-plan-cn | kimi-k2.5 | Unknown | Unknown | 262K | 2026-01 |
| Melious melious | kimi-k2.5 | $0.580 | $2.96 | 262K | 2026-01 |
| Abacus abacus | kimi-k2.5 | $0.600 | $3.00 | 262K | 2026-01 |
| NovitaAI novita-ai | moonshotai/kimi-k2.5 | $0.600 | $3.00 | 262K | 2026-01-27 |
| 302.AI 302ai | kimi-k2.5 | $0.660 | $3.30 | 262K | 2026-01 |
| Azure Cognitive Services azure-cognitive-services | kimi-k2.5 | $0.600 | $3.00 | 262K | 2026-01 |
| Auriko auriko | kimi-k2.5 | $0.500 | $2.80 | 262K | 2026-01 |
| ZenMux zenmux | moonshotai/kimi-k2.5 | $0.580 | $3.02 | 262K | 2026-01-27 |
| SiliconFlow (China) siliconflow-cn | Pro/moonshotai/Kimi-K2.5 | $0.450 | $2.25 | 262K | 2026-01-27 |
| Qiniu qiniu-ai | moonshotai/kimi-k2.5 | Unknown | Unknown | 256K | 2026-01-28 |
| FrogBot frogbot | kimi-k2.5 | $0.600 | $3.00 | 256K | 1970-01-01 |
| Jiekou.AI jiekou | moonshotai/kimi-k2.5 | $0.600 | $3.00 | 262K | 2026-01 |
| Ollama Cloud ollama-cloud | kimi-k2.5 | Unknown | Unknown | 262K | 2026-01-27 |
| Jalapeno Cloud jalapeno | Kimi-K2.5 | $0.600 | $3.00 | 262K | 2026-01 |
| OrcaRouter orcarouter | kimi/kimi-k2.5 | $0.600 | $3.00 | 262K | 2026-01 |
| SCNet Token Plan scnet-token-plan | Kimi-K2.5 | Unknown | Unknown | 262K | 2026-01 |
| Ofox ofox | moonshotai/kimi-k2.5 | $0.600 | $3.00 | 262K | 2026-01 |
| AIHubMix aihubmix | kimi-k2.5 | $0.600 | $3.00 | 262K | 2026-01 |
| Merge Gateway merge-gateway | moonshot/kimi-k2.5 | $0.600 | $3.00 | 262K | 2026-01 |
| TensorX tensorx | moonshotai/kimi-k2.5 | $0.500 | $2.80 | 262K | 2026-01 |
| Eden AI edenai | deepinfra/moonshotai/Kimi-K2.5 | $0.450 | $2.25 | 262K | 2026-01 |
| Eden AI edenai | tensorx/moonshotai/kimi-k2.5 | $0.500 | $2.80 | 262K | 2026-01 |
| Eden AI edenai | amazon/moonshotai.kimi-k2.5 | $0.600 | $3.00 | 262K | 2026-01 |
| HPC-AI hpc-ai | moonshotai/kimi-k2.5 | $0.600 | $3.00 | 256K | 2026-01 |
| Tencent Coding Plan (China) tencent-coding-plan | kimi-k2.5 | Unknown | Unknown | 262K | 2026-01-27 |
| OpenCode Zen opencode | kimi-k2.5 | $0.600 | $3.00 | 262K | 2026-01-27 |
| Meganova meganova | moonshotai/Kimi-K2.5 | $0.450 | $2.80 | 262K | 2026-01-27 |
| DevPass (LLM Gateway) llmgateway | kimi-k2.5 | $0.405 | $1.98 | 262K | 2026-01 |
| Cortecs cortecs | kimi-k2.5 | $0.495 | $2.77 | 262K | 2026-01 |
| DaoXE daoxe | kimi-k2.5 | $0.600 | $3.00 | 262K | 2026-01 |
| Alibaba Coding Plan (China) alibaba-coding-plan-cn | kimi-k2.5 | Unknown | Unknown | 262K | 2026-01-27 |
| DigitalOcean digitalocean | kimi-k2.5 | $0.500 | $2.70 | 262K | 2026-01 |
| Alibaba (China) alibaba-cn | kimi-k2.5 | $0.574 | $2.41 | 262K | 2026-01-27 |
| Alibaba (China) alibaba-cn | kimi/kimi-k2.5 | $0.600 | $3.00 | 262K | 2026-01-27 |
Incohérences de données entre fournisseurs
- context_window varies: 256000, 262000, 262144
- release_date varies (span 20490d): 1970-01-01, 2026-01, 2026-01-01, 2026-01-27, 2026-01-28, 2026-01-30, 2026-02-06
- modalities varies across offerings
Les fournisseurs rapportent des valeurs différentes pour ce modèle. Les infos clés ci-dessus utilisent un fournisseur représentatif ; voir le tableau pour le détail par fournisseur.
Frequently asked questions
How much does Kimi K2.5 cost?
Kimi K2.5 costs $0.300 per 1M input tokens and $1.90 per 1M output tokens, sourced from nano-gpt. Cache reads, audio tokens and >200K-context tiers (where applicable) are listed in the Pricing detail block above.
What is the context window of Kimi K2.5?
Kimi K2.5 has a context window of 262K tokens, with a max output of 262K tokens per reply. This is the total combined size of prompt + completion.
Does Kimi K2.5 support tool calling?
Yes. Kimi K2.5 supports tool calling (function calling). This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.
Does Kimi K2.5 support structured output / JSON mode?
Yes. Kimi K2.5 supports structured output / JSON-schema-constrained decoding. This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.
Can Kimi K2.5 accept image input?
Yes. Kimi K2.5 accepts both text and image input. Vision pricing per image is usually billed on top of the regular token rate — check Moonshot AI's docs for the exact rule.
Is Kimi K2.5 open-weight?
Yes. Kimi K2.5's weights are publicly available, so you can self-host or fine-tune. Note that open weights ≠ open source — the training data and code are typically not released.
What are the best alternatives to Kimi K2.5?
If Kimi K2.5 doesn't fit, consider Kimi K3, Kimi K2.6, Kimi K2.7 Code. Each one targets the same use case — see the Related links below for direct head-to-head pages.
Where does this data come from?
All numbers are normalised into a single canonical model record and reconciled with each provider's official documentation. We re-pull daily and write any changes (price, context, capability) to the /changelog page.
Explore more
More Moonshot AI models
- Kimi K3$3.00 in / $15.00 out
- Kimi K2.6$0.95 in / $4.00 out
- Kimi K2.7 Code$0.95 in / $4.00 out
- Kimi K2 Thinking$0.47 in / $2.00 out
- Kimi K2.7 Code HighSpeed$1.90 in / $8.00 out
Capability lists this model is in
Dernière mise à jour :
Pricing and capabilities are refreshed daily and reconciled against each provider's official documentation. Always verify critical production decisions with the provider directly.