Kimi K3
Moonshot AI · Active · available in 31 of 31 regions
Tool useVisionPrompt cachingBatch inferenceStreaming EmbeddingsFine-tuning
- Context window
- 1M
- 1,000,000 tokens
- Max output
- —
- Input / 1M
- $3.00
- us-east-1
- Output / 1M
- $15.00
What Kimi K3 is good for
editorialKimi K3 offers a 1M-token context window with tool use and prompt caching, at the premium end of this provider’s range at $3.00 per 1M input tokens. Callable in 31 of 31 regions.
Suits
- Very long inputs. A 1M-token window holds an entire codebase or a day of transcripts in one call, so you can skip chunking.
- Repeated prompts. Supports prompt caching, so a re-sent prefix costs about 10× less than fresh input. On agentic loops that resend a long system prompt every step, this moves the bill more than the headline price does.
- Tool use. Can call functions, so it can drive retrieval, look things up, and take actions rather than only answering.
- Images. Accepts image input: screenshots, scanned documents, charts and UI captures.
- Bulk jobs. Batch inference is available, typically at half the on-demand rate, for work that can wait — backfills, nightly enrichment, evaluation runs.
Think twice if
- High volume. At $3.00 per 1M input tokens it sits at the expensive end of the Moonshot AI range. Worth it for hard tasks, wasteful for bulk extraction.
- Invocation. Reachable only through a cross-region inference profile — calling the bare model ID returns a validation error. Use an ID such as global.moonshotai.kimi-k3.
This section is judgement, not data from AWS. It is composed from the capabilities, context window, price position and region coverage shown elsewhere on this page — so it stays in step with the daily snapshot rather than going stale.
Model & inference profile IDs
Base model ID — direct on-demand invoke
Cross-region inference profiles (3)
Regions marked Inference profile only require a profile ID rather than the base model ID — invoking the base ID there returns a validation error. Regional (us., eu.) profiles carry a 10% premium over global.
Pricing by region
USD per 1M tokens| Region | Input | Output | Cache read | Cache write | Batch in | Batch out | Source |
|---|---|---|---|---|---|---|---|
| us-east-1 US East (N. Virginia) | $3.00 | $15.00 | $0.300 | $3.75 | $1.65 | $8.25 | API |
| us-east-2 US East (Ohio) | $3.00 | $15.00 | $0.300 | $3.75 | $1.65 | $8.25 | API |
| us-west-1 US West (N. California) | $3.00 | $15.00 | $0.300 | $3.75 | $1.65 | $8.25 | API |
| us-west-2 US West (Oregon) | $3.00 | $15.00 | $0.300 | $3.75 | $1.65 | $8.25 | API |
| ca-central-1 Canada (Central) | $3.00 | $15.00 | $0.300 | $3.75 | $1.65 | $8.25 | API |
| ca-west-1 Canada West (Calgary) | $3.00 | $15.00 | $0.300 | $3.75 | $1.65 | $8.25 | API |
| mx-central-1 Mexico (Central) | $3.00 | $15.00 | $0.300 | $3.75 | $1.65 | $8.25 | API |
| eu-west-1 EU (Ireland) | $3.00 | $15.00 | $0.300 | $3.75 | $1.65 | $8.25 | API |
| eu-west-2 EU (London) | $3.00 | $15.00 | $0.300 | $3.75 | $1.65 | $8.25 | API |
| eu-west-3 EU (Paris) | $3.00 | $15.00 | $0.300 | $3.75 | $1.65 | $8.25 | API |
| eu-central-1 EU (Frankfurt) | $3.00 | $15.00 | $0.300 | $3.75 | $1.65 | $8.25 | API |
| eu-central-2 Europe (Zurich) | $3.00 | $15.00 | $0.300 | $3.75 | $1.65 | $8.25 | API |
| eu-north-1 EU (Stockholm) | $3.00 | $15.00 | $0.300 | $3.75 | $1.65 | $8.25 | API |
| eu-south-1 EU (Milan) | $3.00 | $15.00 | $0.300 | $3.75 | $1.65 | $8.25 | API |
| eu-south-2 Europe (Spain) | $3.00 | $15.00 | $0.300 | $3.75 | $1.65 | $8.25 | API |
| ap-east-2 Asia Pacific (Taipei) | $3.00 | $15.00 | $0.300 | $3.75 | $1.65 | $8.25 | API |
| ap-northeast-1 Asia Pacific (Tokyo) | $3.00 | $15.00 | $0.300 | $3.75 | $1.65 | $8.25 | API |
| ap-northeast-2 Asia Pacific (Seoul) | $3.00 | $15.00 | $0.300 | $3.75 | $1.65 | $8.25 | API |
| ap-northeast-3 Asia Pacific (Osaka) | $3.00 | $15.00 | $0.300 | $3.75 | $1.65 | $8.25 | API |
| ap-south-1 Asia Pacific (Mumbai) | $3.00 | $15.00 | $0.300 | $3.75 | $1.65 | $8.25 | API |
| ap-south-2 Asia Pacific (Hyderabad) | $3.00 | $15.00 | $0.300 | $3.75 | $1.65 | $8.25 | API |
| ap-southeast-1 Asia Pacific (Singapore) | $3.00 | $15.00 | $0.300 | $3.75 | $1.65 | $8.25 | API |
| ap-southeast-2 Asia Pacific (Sydney) | $3.00 | $15.00 | $0.300 | $3.75 | $1.65 | $8.25 | API |
| ap-southeast-3 Asia Pacific (Jakarta) | $3.00 | $15.00 | $0.300 | $3.75 | $1.65 | $8.25 | API |
| ap-southeast-4 Asia Pacific (Melbourne) | $3.00 | $15.00 | $0.300 | $3.75 | $1.65 | $8.25 | API |
| ap-southeast-5 Asia Pacific (Malaysia) | $3.00 | $15.00 | $0.300 | $3.75 | $1.65 | $8.25 | API |
| ap-southeast-6 Asia Pacific (New Zealand) | $3.00 | $15.00 | $0.300 | $3.75 | $1.65 | $8.25 | API |
| ap-southeast-7 Asia Pacific (Thailand) | $3.00 | $15.00 | $0.300 | $3.75 | $1.65 | $8.25 | API |
| il-central-1 Israel (Tel Aviv) | $3.00 | $15.00 | $0.300 | $3.75 | $1.65 | $8.25 | API |
| af-south-1 Africa (Cape Town) | $3.00 | $15.00 | $0.300 | $3.75 | $1.65 | $8.25 | API |
| sa-east-1 South America (Sao Paulo) | $3.00 | $15.00 | $0.300 | $3.75 | $1.65 | $8.25 | API |
Region availability
Inference profile only us-east-1 Profile only Inference profile only us-east-2 Profile only Inference profile only us-west-1 Profile only Inference profile only us-west-2 Profile only Inference profile only ca-central-1 Profile only Inference profile only ca-west-1 Profile only Inference profile only mx-central-1 Profile only Inference profile only eu-west-1 Profile only Inference profile only eu-west-2 Profile only Inference profile only eu-west-3 Profile only Inference profile only eu-central-1 Profile only Inference profile only eu-central-2 Profile only Inference profile only eu-north-1 Profile only Inference profile only eu-south-1 Profile only Inference profile only eu-south-2 Profile only Inference profile only ap-east-2 Profile only Inference profile only ap-northeast-1 Profile only Inference profile only ap-northeast-2 Profile only Inference profile only ap-northeast-3 Profile only Inference profile only ap-south-1 Profile only Inference profile only ap-south-2 Profile only Inference profile only ap-southeast-1 Profile only Inference profile only ap-southeast-2 Profile only Inference profile only ap-southeast-3 Profile only Inference profile only ap-southeast-4 Profile only Inference profile only ap-southeast-5 Profile only Inference profile only ap-southeast-6 Profile only Inference profile only ap-southeast-7 Profile only Inference profile only il-central-1 Profile only Inference profile only af-south-1 Profile only Inference profile only sa-east-1 Profile only
TPM / RPM are default account quotas from AWS Service Quotas where a model-specific limit is published. They are per-account defaults and adjustable on request.
Where this model actually runs
Under a strict residency constraint, Kimi K3 can be served without the request leaving 2 of the 25 jurisdictions with a Bedrock region.
Kimi K3 compared
Side-by-side pages against every model people weigh this one against.
Kimi K3 vs Claude Fable 5Kimi K3 costs 3.3× less per input token than Claude Fable 5.Kimi K3 vs Claude Fable 5.1Kimi K3 costs 3.3× less per input token than Claude Fable 5.1.Kimi K3 vs Claude Haiku 4.5Claude Haiku 4.5 costs 3.0× less per input token than Kimi K3, and Kimi K3 holds 1M tokens against 200K for Claude Haiku 4.5.Kimi K3 vs Claude Haiku 5.5Claude Haiku 5.5 costs 30× less per input token than Kimi K3.Kimi K3 vs Claude Opus 4.5Kimi K3 costs 1.7× less per input token than Claude Opus 4.5, and Kimi K3 holds 1M tokens against 200K for Claude Opus 4.5.Kimi K3 vs Claude Opus 4.6Kimi K3 costs 1.7× less per input token than Claude Opus 4.6.Kimi K3 vs Claude Opus 4.7Kimi K3 costs 1.7× less per input token than Claude Opus 4.7.Kimi K3 vs Claude Opus 4.8Kimi K3 costs 1.7× less per input token than Claude Opus 4.8.Kimi K3 vs Claude Opus 5Kimi K3 costs 1.7× less per input token than Claude Opus 5.Kimi K3 vs Claude Opus 5.5Kimi K3 costs 1.3× less per input token than Claude Opus 5.5.Kimi K3 vs Claude Sonnet 4.5Same input price, and Kimi K3 holds 1M tokens against 200K for Claude Sonnet 4.5.Kimi K3 vs Claude Sonnet 4.6Same input price.Kimi K3 vs Claude Sonnet 5Claude Sonnet 5 costs 1.5× less per input token than Kimi K3.Kimi K3 vs Claude Sonnet 5.5Claude Sonnet 5.5 costs 1.5× less per input token than Kimi K3.Kimi K3 vs GPT-6 AstraKimi K3 costs 3.3× less per input token than GPT-6 Astra.
Kimi K3 appears in
Common questions
- How much does Kimi K3 cost on Amazon Bedrock?
- $3.00 per 1M input tokens and $15.00 per 1M output tokens in us-east-1. Cached input reads at $0.300, 10% of the input rate, which dominates the bill on agentic workloads that re-send a long prefix.
- Which AWS regions support Kimi K3?
- 31 of 31 regions: us-east-1, us-east-2, us-west-1, us-west-2, ca-central-1, ca-west-1, mx-central-1, eu-west-1, eu-west-2, eu-west-3, eu-central-1, eu-central-2, eu-north-1, eu-south-1, eu-south-2, ap-east-2, ap-northeast-1, ap-northeast-2, ap-northeast-3, ap-south-1, ap-south-2, ap-southeast-1, ap-southeast-2, ap-southeast-3, ap-southeast-4, ap-southeast-5, ap-southeast-6, ap-southeast-7, il-central-1, af-south-1, sa-east-1. Regions marked profile-only need a cross-region inference profile ID such as global.moonshotai.kimi-k3 rather than the bare model ID.
- What is the context window of Kimi K3?
- 1,000,000 tokens (1M).
- What is the model ID for Kimi K3 on Bedrock?
- moonshotai.kimi-k3. In regions where it is only reachable through a cross-region inference profile, use a prefixed ID instead: global.moonshotai.kimi-k3, in.moonshotai.kimi-k3, us.moonshotai.kimi-k3.