Kimi K3 is live on Runware
Moonshot's 2.8-trillion-parameter frontier LLM, with a 1M-token context and native image and video input, through Runware's OpenAI-compatible endpoint.
- Parameters
- 2.8T
- Token context
- 1M
- Terminal-Bench 2.1
- 88.3
- Cache hit rate
- 90%+
Every workflow, one endpoint.
One API, OpenAI-compatible endpoint. Point your existing SDK at Runware and go.
- Chat & reasoning
- Agentic coding
- Vision understanding
- 1M-token context
- Tool use
Kimi K3 benchmarks
Moonshot's published evals, thinking effort maxed for every model. Kimi K3 leads outright on agentic coding endurance and browsing, and effectively ties GPT-5.6 Sol on terminal work, at $3.00 per million input tokens and $0.30 on cache hits.
| Benchmark | Kimi K3 | GPT-5.6 Sol | Fable 5 | Opus 4.8 | GPT-5.5 | GLM-5.2 |
|---|---|---|---|---|---|---|
| Terminal-Bench 2.1 | 88.3 | 88.8 | 84.6 | 84.6 | 83.4 | 82.7 |
| Program Bench | 77.8 | 77.6 | 76.8 | 71.9 | 70.8 | 63.7 |
| SWE Marathon | 42.0 | 39.0 | 35.0 | 40.0 | 14.0 | 13.0 |
| BrowseComp | 91.2 | 90.4 | 88.0 | 84.3 | 84.4 | — |
Moonshot-published figures, all models at max thinking effort. Fable 5 results include potential fallbacks; GPT-5.6 Sol results include potential cyberguards. Dash: not reported.
Built for real workloads
Long-running agents and oversized codebases, plus pipelines that previously required separate vision and reranking models.
Coding agents
Multi-step engineering across large codebases; K3 leads Program Bench and SWE Marathon and beats Opus 4.8 on Terminal-Bench 2.1.
Long-document analysis
Entire contract libraries and research archives: 1M tokens fits them in one pass, no chunking, no retrieval layer.
Multimodal reasoning
Visual debugging and QA flows, with screenshots and video reasoned over natively.
Autonomous agents
Loads new tools mid-conversation via system messages and enforces strict JSON Schema output, so long-horizon loops stay on rails.
High-volume inference
Automatic context caching with no configuration needed: hit rates above 90% on coding workloads and input cost drops to $0.30/M on hits.
Drop-in migration
OpenAI-compatible: change the base URL and model ID; streaming and tool calls carry over untouched, as does structured output.
Kimi K3 pricing
Live now, under the same usage-based pricing as every other model on Runware. Automatic context caching drops input cost to $0.30/M on hits, no configuration needed.
- Input
- $3.00/1M tokens
- Input on cache hits
- $0.30/1M tokens
- Output
- $15.00/1M tokens
Same key and billing as every other model on the platform, no dedicated infrastructure to provision.
Frequently asked questions
What is Kimi K3?
Moonshot AI's frontier LLM, released July 16, 2026: 2.8 trillion parameters with 16 of 896 experts active per pass, a 1M-token context window and native multimodal input, with reasoning always on.
How much does it cost on Runware?
$3.00 per million input tokens, $0.30 on cache hits, and $15.00 per million output, under the same usage-based pricing as every other model on the platform.
What makes K3 different?
A 1M-token context window combined with frontier agentic coding performance: 88.3 on Terminal-Bench 2.1, above Claude Opus 4.8's 84.6. Thinking mode can't be switched off, only tuned, and automatic context caching hits over 90% on coding workloads.
Is Kimi K3 live on Runware?
Yes. It's live now through Runware's OpenAI-compatible endpoint, under the same key and billing as every other model on the platform.
Do I need a new integration?
No. The endpoint is OpenAI-compatible: change the base URL and model ID, and streaming, tool calls, and structured output carry over unchanged.
What workloads is it best for?
Agentic coding, long-document analysis, multimodal reasoning, and long-horizon agents: it loads new tools mid-conversation and enforces strict JSON Schema output, so autonomous loops stay on rails.
Already integrated with Kimi K3 somewhere else?
Since the endpoint is OpenAI-compatible, most of the change is just the base URL, model ID, and auth. Our Migration Skills and docs cover the rest. See the migration guide for details.
Bring your workload. The switch is on us.
Already running an LLM in production? We'll credit your Runware account so you can replay your real traffic on Kimi K3 and compare cost and quality against your current provider, before you spend a cent of your own.
- Tell us your current provider and monthly volume
- We set you up with testing credits
- Run your real prompts, keep what wins
Claim your migration credits
Tell us your current provider and use case along with your monthly volume. We'll set you up with testing credits and dedicated RPM so you can benchmark Kimi K3 on Runware against what you run today.