Kimi-K2-Instruct-0905
moonshotai/kimi-k2-instruct-0905By Moonshot AI · family: kimi-k2 · released 2025-09-04 · knowledge: 2024-10
Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.
Capabilities
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.
Coding52
- Tool calling40/40
- Structured output0/20
- Reasoning0/10
- Context window (100K → 1M)8/20
- Provider availability4/10
Agents49
- Tool calling35/35
- Structured output0/25
- Reasoning0/15
- Output token limit10/15
- Provider availability4/10
JSON / structured output45
- Structured output / JSON mode0/50
- Tool calling20/20
- Temperature control10/10
- Price-friendly for high-volume15/20
Cost efficiency58
- Headline price (log-scaled)53/95
- Has prompt-cache pricing5/5
Long context61
- Context window (100K → 2M)51/90
- Has published price for full window10/10
Production-readiness76
- Number of independent providers20/40
- Has published per-token price20/20
- Context window ≥ 8K15/15
- No data inconsistencies across providers6/10
- 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 | $2.90 < $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 | $5.80 < $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 | $1.73 < $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 | $5.02 < $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 | $5.82 < $0.01 per request | 12K input tokens (long-running tool history) and a 600-token tool-call decision. Cost per agent step. |
Pricing detail
Recommended pricing from io-net · moonshotai/Kimi-K2-Instruct-0905
Cheapest provider: nvidia · Unknown input + Unknown output
Available on 4 providers
| Provider | Provider model id | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|---|
| Hugging Face huggingface | moonshotai/Kimi-K2-Instruct-0905 | $1.00 | $3.00 | 262K | 2025-09-04 |
| Nvidia nvidia | moonshotai/kimi-k2-instruct-0905 | Unknown | Unknown | 262K | 2025-09-05 |
| IO.NET io-net | moonshotai/Kimi-K2-Instruct-0905 | $0.390 | $1.90 | 33K | 2024-09-05 |
| NanoGPT nano-gpt | moonshotai/Kimi-K2-Instruct-0905 | $0.400 | $2.00 | 256K | 2025-09-25 |
Data inconsistencies across providers
- context_window varies: 256000, 262144, 32768
- release_date varies (span 385d): 2024-09-05, 2025-09-04, 2025-09-05, 2025-09-25
Different providers report different values for this model. Quick facts above use the representative provider; consult the table for per-provider truth.
Frequently asked questions
How much does Kimi-K2-Instruct-0905 cost?
Kimi-K2-Instruct-0905 costs $0.390 per 1M input tokens and $1.90 per 1M output tokens, sourced from io-net. 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-Instruct-0905?
Kimi-K2-Instruct-0905 has a context window of 262K tokens, with a max output of 16K tokens per reply. This is the total combined size of prompt + completion.
Does Kimi-K2-Instruct-0905 support tool calling?
Yes. Kimi-K2-Instruct-0905 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-Instruct-0905 support structured output / JSON mode?
Support for structured output / JSON-schema-constrained decoding is not reported for Kimi-K2-Instruct-0905 in our data source. Verify with Moonshot AI's official documentation before relying on it in production.
Can Kimi-K2-Instruct-0905 accept image input?
No. Kimi-K2-Instruct-0905 only accepts text as input. If you need image input, see our /capabilities/vision list for current vision-capable models.
Is Kimi-K2-Instruct-0905 open-weight?
Yes. Kimi-K2-Instruct-0905'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-Instruct-0905?
If Kimi-K2-Instruct-0905 doesn't fit, consider Kimi K2.6, Kimi K2.5, Kimi K2 Thinking. 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 K2.6$0.95 in / $4.00 out
- Kimi K2.5$0.60 in / $3.00 out
- Kimi K2 Thinking$0.60 in / $2.50 out
- Kimi K2.7 Code$0.95 in / $4.00 out
- Kimi K2 0711$0.55 in / $2.20 out
Capability lists this model is in
Last updated:
Pricing and capabilities are refreshed daily and reconciled against each provider's official documentation. Always verify critical production decisions with the provider directly.