Kimi K3
Kimi K3 is Moonshot AI's open-source model with native visual understanding, always-on thinking, and a context window of 1.0M tokens, built for long-horizon software engineering and available through AI Gateway via Moonshot AI, Fireworks, Baseten, Morph, Nebius, Together AI, DigitalOcean. Your use is subject to Moonshot AI's Terms & Privacy Policies.
import { streamText } from 'ai'
const result = streamText({ model: 'moonshotai/kimi-k3', prompt: 'Why is the sky blue?'})Playground
Try out Kimi K3 by Moonshot AI. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.
Kimi K3
Kimi K3
Providers
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
| Provider |
|---|
| 1M | 131K | 4.5s | 38tps | $3/M | $15/M | Read:$0.3/M Write:— | — | +2 | 07/16/2026 | |||||
| 1M | 131K | 1.7s | 63tps | $3/MFast $4.50/M+1 more | $15/MFast $22.50/M+1 more | Read:$0.3/M+1 more Write:— | — | +2 | 07/16/2026 | |||||
| 1M | 131K | 3.6s | 106tps | $3/M | $15/M | Read:$0.3/M Write:— | — | +1 | 07/16/2026 | |||||
| 1M | 1M | 1.0s | 40tps | $2.90/MFast $4.50/M | $14/MFast $22.50/M | Read:$0.29/M Write:— | — | +2 | 07/16/2026 | |||||
| 1M | 131K | 1.0s | 67tps | $3/M | $15/M | — | +2 | 07/16/2026 | ||||||
| 1M | 131K | 4.3s | 67tps | $3/M | $15/M | Read:$0.3/M Write:— | — | +2 | 07/16/2026 | |||||
| 1M | 131K | 2.2s | 46tps | $3/M | $15/M | Read:$0.3/M Write:— | — | +2 | 07/16/2026 |
P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.
P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.
Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.
More models by Moonshot AI
| Model |
|---|
| 1M | 1.1s | 99tps | $4.50/M | $22.50/M | Read:$0.45/M Write:— | — | +2 |    | 07/27/2026 | ||||
| 262K | 0.5s | 165tps | $1.90/M | $8/M | Read:$0.38/M Write:— | — | +2 | | 06/15/2026 | ||||
| 262K | 0.2s | 164tps | $0.74/MFast $1.90/M | $3.50/MFast $8/M | Read:$0.15/M Write:— | — | +2 |   +1 | 06/12/2026 | ||||
| 262K | 0.3s | 347tps | $0.95/M | $4/M | Read:$0.16/M Write:— | — | +1 | +2 | 04/20/2026 | ||||
| 262K | 0.4s | 106tps | $0.60/M | $3/M | Read:$0.1/M Write:— | — | +1 |   | 01/26/2026 | ||||
| 216K | 0.5s | 59tps | $0.47/M | $2/M | Read:$0.14/M Write:— | — | | 11/06/2025 |
About Kimi K3
Kimi K3, released July 16, 2026, is an open-source model from Moonshot AI with a context window of 1.0M tokens and native visual understanding. It accepts text, image, and video input. Thinking mode is always on, so every response includes a deliberation pass you can't switch off.
Kimi K3 handles software engineering that spans many turns, knowledge work across large document sets, and reasoning problems that need sustained attention. Moonshot AI points to tasks where code meets visual and spatial reasoning as the strongest fit, which covers frontend development, game development, and computer-aided design (CAD) workflows.
Native visual understanding changes how those pipelines compose. A coding agent reads a screenshot of a broken layout or a screen recording of a reproduction without a separate vision model in the pipeline. Design references and diagrams feed the same request as the prompt.
AI Gateway routes Kimi K3 across Moonshot AI, Fireworks, Baseten, Morph, Nebius, Together AI, DigitalOcean, including US-based providers for teams with data residency and compliance requirements. Provider selection and fallback sit behind one model ID, which gives you failover and more available throughput than a single provider offers. To keep inference in US data centers, set inferenceRegion with scope zone and geo region us. Regional inference lists above the standard rate, so check the pricing panel on this page.
For lower latency, set the speed option to fast and keep the model ID on moonshotai/kimi-k3. Requests route to the faster serving path and fall back to standard speed when the fast tier isn't available. You can also call kimi-k3-fast directly, which pins every request to that tier at a higher per-token rate. Zero Data Retention is configured per request with zeroDataRetention or turned on for every request from AI Gateway dashboard settings, and support varies by provider.
Use the identifier moonshotai/kimi-k3 with the AI SDK or any supported interface like Chat Completions, Responses, or Messages. Kimi K3 supports a context window of 1.0M tokens and completions up to 1M tokens per request, at $2.90 per million input tokens and $14 per million output tokens.
What To Consider When Choosing a Provider
- Configuration: Thinking mode is always on, so budget output tokens for reasoning on top of the answer and note the completion cap of 1M tokens per request. Image and video inputs consume context faster than text of the same apparent length, so measure representative payloads against the window of 1.0M tokens rather than word counts. If latency matters more than rate, the fast serving path costs more per token, so compare both before you move production traffic. US-only inference and Zero Data Retention are request-level or key-level settings, not separate model IDs.
- Zero Data Retention: AI Gateway supports Zero Data Retention for this model via direct gateway requests (BYOK is not included). To configure this, check the documentation.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
When to Use Kimi K3
Best for
- Long-Horizon Coding Agents: Engineering sessions that run across many turns and tool calls
- Visual and Spatial Coding: Frontend, game development, and CAD work that pairs code with imagery
- Screenshot-Driven Debugging: Reproduction captures that feed straight into the coding loop
- Large Document Reasoning: Knowledge work that fits inside the context window of 1.0M tokens
- US Data Residency: Deployments that must run inference on US-based providers
Consider alternatives when
- Latency-Sensitive Interfaces: Kimi K3 Fast serves the same model on a lower-latency path
- Optional Thinking Mode: A non-thinking Kimi K2 variant answers without a reasoning pass
- Short Single-Turn Prompts: Deliberation adds output tokens without changing a simple answer
- Cost-Sensitive Traffic: An earlier Kimi variant may meet your quality bar for less
Conclusion
Kimi K3 pairs a context window of 1.0M tokens with native visual understanding and always-on thinking, aimed at engineering work that runs long and mixes code with imagery. Set the model ID to moonshotai/kimi-k3 and AI Gateway routes across Moonshot AI, Fireworks, Baseten, Morph, Nebius, Together AI, DigitalOcean with automatic failover. Add the speed option when a session needs the faster path.