Is Kimi K3 Available on EvoLink? Current API Status
kimi-k3. Developers can review current pricing on the Kimi K3 model page and use the verified request contract in the EvoLink API documentation.EvoLink has now completed the route, compatibility, pricing, and production checks that were still pending when this tracker was first published. The route is live, but teams should still verify workload-specific latency, output usage, tool behavior, and fallback policies before making K3 their default model.
Kimi K3 status as of July 16, 2026
| Question | Current status | What developers should do |
|---|---|---|
| Has Moonshot released Kimi K3? | Yes | Treat K3 as an official upstream model, not a rumor |
| Is Moonshot's direct API live? | Yes | Direct Moonshot customers can evaluate the documented kimi-k3 route |
| Is Kimi K3 available on EvoLink? | Yes | Evaluate the live route against production workloads |
| Is there an EvoLink model ID? | kimi-k3 | Use the documented ID rather than a Kimi Code alias |
| Is EvoLink pricing available? | Yes | Check the live pricing section on the model page |
| When did EvoLink launch the route? | July 17, 2026 | Treat this article as the launch-status record |
| Should teams prepare evaluations? | Yes | Build replayable tasks, budgets, and fallback policies now |
kimi-k3 route, live pricing, and published API documentation.What Moonshot has officially confirmed
Moonshot's official documentation lists:
- direct API model ID
kimi-k3; - 2.8 trillion parameters;
- Kimi Delta Attention and Attention Residuals;
- a 1,048,576-token context window;
- text, image, and video input;
- always-on reasoning;
reasoning_effortwithmaxas the current supported level;- tool calling,
tool_choice, dynamic tool loading, structured output, and automatic context caching; - direct prices of ¥2/MTok cached input, ¥20/MTok uncached input, and ¥100/MTok output.
These are Moonshot facts. For EvoLink-specific pricing and request behavior, use the current model page and API documentation rather than assuming every direct-API detail is identical.
Why gateway integration needs separate verification
An OpenAI-compatible upstream API reduces integration work, but it does not remove the need for route testing.
| Verification area | Why it matters for K3 |
|---|---|
| Model naming | EvoLink must publish the exact supported route ID |
| Reasoning fields | Multi-turn requests need complete assistant messages and reasoning_content handling |
| Parameter compatibility | K3 uses reasoning_effort, not the K2.x thinking control |
| 1M context | The gateway must accept, route, meter, and time out very large requests correctly |
| Streaming | Reasoning and final-answer deltas must be represented consistently |
| Tool calls | Tool IDs, arguments, dynamic definitions, and follow-up messages need compatibility tests |
| Structured output | JSON Schema behavior should be checked against the gateway response |
| Multimodal input | Image and video upload or URL handling may differ from Moonshot's direct interface |
| Billing and caching | Cache hits, input/output usage, retries, and failed requests need reliable accounting |
| Capacity and fallback | Launch demand can expose latency, 429, 5xx, and timeout behavior |
Publishing a route before these checks would create a worse developer experience than waiting for a verified integration.
What developers should use now
The useful preparation work is provider-independent:
- Put model choice behind configuration.
- Keep a current production route as the baseline.
- Build a 20–50 task K3 evaluation set using real coding, research, multimodal, and tool workflows.
- Define acceptable latency, cost, retry rate, and reviewer effort.
- Decide whether K3 would be a default, specialist, premium, or escalation route.
- Preserve a fallback for provider errors and capacity limits.
What changed when EvoLink support was verified
This URL is designed to remain useful through the integration lifecycle.
The verified EvoLink launch added:
- the July 17, 2026 launch date;
- the canonical Kimi K3 model page;
- the verified EvoLink model ID
kimi-k3; - live pricing through the existing pricing system;
- verified Chat Completions and Anthropic Messages request paths;
- published context, output, and integration guidance in the API docs.
Kimi K3 API, Kimi K3 pricing, and EvoLink model-ID intent. This article remains the integration-status and launch-history record.What developers should still verify
Route availability does not prove that K3 is the best default for every workload. Before broad production rollout, verify:
- actual latency and output-token usage on representative tasks;
- tool, reasoning, streaming, and multimodal behavior used by the application;
- cache-hit behavior and completed-task cost;
- timeout, retry, and fallback behavior;
- current pricing from EvoLink rather than Moonshot's direct price table.
That fact boundary protects developers from building against a route that does not exist yet.
Continue the Kimi K3 Evaluation
Availability is only the first decision. Use the next guide that matches the production question your team needs to answer.
| Next decision | Guide |
|---|---|
| Compare K3 with OpenAI's flagship coding route | Kimi K3 vs GPT-5.6 Sol |
| Compare K3 with Anthropic's premium long-task route | Kimi K3 vs Claude Opus 4.8 |
| Measure latency, output use, cache value, and successful-task cost | Kimi K3 Token Efficiency |
FAQ
Is Kimi K3 available on EvoLink?
kimi-k3 model ID and follow the current EvoLink API documentation.Is Kimi K3 officially released?
Yes. Moonshot published K3 in its official model list, quickstart, pricing page, and direct API examples on July 16, 2026.
Can I use kimi-k3 as the EvoLink model ID?
kimi-k3 for both supported Kimi K3 request paths. Do not substitute the Kimi Code product alias k3.How much will Kimi K3 cost on EvoLink?
When will EvoLink add Kimi K3?
EvoLink launched the verified Kimi K3 route on July 17, 2026. The model page and API documentation are the current sources for model ID, pricing, and supported request behavior.
Why not expose the route immediately if Moonshot is OpenAI-compatible?
Compatibility still needs verification across reasoning fields, tool calls, streaming, multimodal inputs, 1M context handling, billing, caching, timeouts, and fallback behavior.
What should I use while waiting?
Should I test Kimi K3 through Moonshot directly?
That depends on your procurement, data, regional, and account requirements. If you test it directly, keep the evaluation portable so the same workload can also be repeated against the live EvoLink route.
