moonshotai/Kimi-K3 pricing
Kimi K3 is Moonshot AI's 2.8T-parameter open-weight multimodal reasoning model. Built for complex coding, knowledge work, and long-horizon agentic workflows, it excels at navigating large repositories, calling tools, debugging, and iterating on images, logs, tests, and runtime feedback. moonshotai/Kimi-K3 from DeepInfra costs $2.85 per 1M input tokens and $14.25 per 1M output tokens. Cached input is $0.285 per 1M. Context window 1,048,576 tokens.
API id moonshotai/Kimi-K3 · DeepInfra · source · updated 2026-11-10 · general-purpose
moonshotai/Kimi-K3 specifications
- Provider
- DeepInfra
- API id
moonshotai/Kimi-K3- Model type
- general-purpose
- Context window
- 1M tokens
- Max output
- not published
- Currency
- USD
- Price source
- Provider API
- Last checked
- 2026-11-10
Kimi K3 across providers
The same model, priced by every seller we track. Ranked by the cost of 1M input + 1M output tokens, standard tier; savings measured against buying from the vendor directly.
| Provider | Input /1M | Cached /1M | Output /1M | 1M in + 1M out | vs vendor |
|---|---|---|---|---|---|
| $0.192 | $0.182 | $16.00 | $16.19 | — | |
OpenRouterHost | $0.192 | $0.182 | $16.00 | $16.19 | — |
| $2.85 | $0.285 | $14.25 | $17.10 | +6% | |
Together AIHost | $3.00 | $0.300 | $15.00 | $18.00 | +11% |
What moonshotai/Kimi-K3 costs in practice
| Workload | Input tokens | Output tokens | Estimated cost |
|---|---|---|---|
| Short chat turn | 1,000 | 500 | $0.0100 |
| Document summary | 50,000 | 2,000 | $0.17 |
| 1M tokens in, 200K out | 1,000,000 | 200,000 | $5.70 |
Estimates use the standard tier and ignore caching discounts, so real bills with repeated prompt prefixes are typically lower.
Common questions
- How much does moonshotai/Kimi-K3 cost per 1M tokens?
- moonshotai/Kimi-K3 costs $2.85 per 1M input tokens and $14.25 per 1M output tokens on the standard tier. Cached input is $0.285 per 1M.
- What is moonshotai/Kimi-K3's context window?
- moonshotai/Kimi-K3 accepts up to 1,048,576 tokens in a single request.
- Is there a cheaper DeepInfra model than moonshotai/Kimi-K3?
- Yes. Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo is $0.300 per 1M input tokens versus $2.85 for moonshotai/Kimi-K3, with a 262,144 token context window.
- Where does this moonshotai/Kimi-K3 price come from?
- From the OpenRouter catalogue, because DeepInfra does not publish machine-readable pricing. OpenRouter is a reseller, so its rate can differ from DeepInfra's own — verify before committing spend.
Head-to-head comparisons
Other DeepInfra models
- inclusionAI/Ling-3.0-flash $0.060
- nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B $0.500
- Qwen/Qwen3.6-27B $0.320
- deepseek-ai/DeepSeek-V4.1-Flash-1017 $0.200
- Qwen/Qwen3.6-35B-A3B $0.100
- tencent/Hy4-preview $0.834
- nvidia/NVIDIA-Nemotron-3-Super-120B-A12B $0.075
- anthropic/claude-opus-5-5 $4.00
- google/gemini-2.5-flash $0.300
- meta-llama/Llama-4-Scout-17B-16E-Instruct $0.100
- mistralai/Mistral-Small-24B-Instruct-2501 $0.050
- deepseek-ai/DeepSeek-V4.1-Flash $0.200
- anthropic/claude-opus-4-7 $5.00
- Sao10K/L3-8B-Lunaris-v1-Turbo $0.040
- thinkingmachines/Inkling-Small $0.450
- openai/gpt-oss-20b $0.030