TL;DR: NVIDIA’s live API catalog and model reference expose Kimi K2.6 as moonshotai/kimi-k2.6. NVIDIA does not list Kimi K3. This is an internal trial/evaluation route only: NVIDIA’s trial terms say not for production without a separate NVIDIA or service-provider subscription. Use Moonshot’s direct API or released K3 weights when you need the newest Kimi flagship.

August 1 evidence boundary: The production restriction is validated in NVIDIA’s public trial terms. The exact signup payment requirement, account quota, expiry, and account rate limits remain unresolved. Do not label this route free, production-ready, or suitable for autonomous fallback.

1
2
3

Need NVIDIA's current hosted Kimi? → Kimi K2.6 on NIM
Need the newest Kimi flagship? → Kimi K3 via Moonshot or released weights
Need a stable production service? → Use a separately subscribed production service, not this trial

What NVIDIA currently offers

The live NVIDIA API catalog includes moonshotai/kimi-k2.6. The Kimi K2.6 NIM reference describes a 1T-parameter mixture-of-experts model with 32B active parameters, a 256K context window, text and image input, and thinking and instant modes.

That identity matters. Kimi K3 is newer, but it is not an NVIDIA NIM route in the official catalog checked August 1. Do not rename a K2.6 response, benchmark, trial, or model ID as K3.

Five-minute evaluation API check

Create an NVIDIA developer account, open the Kimi K2.6 model page, and generate an API key if the trial is available to your account. Then test the documented OpenAI-compatible endpoint:

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11

export NVIDIA_API_KEY="nvapi-your-key-here"

curl https://integrate.api.nvidia.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $NVIDIA_API_KEY" \
  -d '{
    "model": "moonshotai/kimi-k2.6",
    "messages": [{"role": "user", "content": "Return only: NIM K2.6 ready"}],
    "max_tokens": 128,
    "temperature": 0.6
  }'

Confirm the response model identity, HTTP status, token accounting, latency, and any signed-in quota before connecting a test agent. A successful trial request proves evaluation access at that moment; it does not prove an evergreen free entitlement or production permission.

OpenClaw trial/evaluation configuration

Use NVIDIA’s base URL and exact provider model ID only in an isolated, non-production evaluation profile supported by your OpenClaw version:

1
2
3

NVIDIA_API_KEY=nvapi-your-key-here
NVIDIA_BASE_URL=https://integrate.api.nvidia.com/v1
NVIDIA_EVALUATION_MODEL=moonshotai/kimi-k2.6

Do not enable this trial endpoint as an autonomous or production fallback. Before a bounded evaluation:

  1. Pin the exact model ID and record the checked date.
  2. Run a small read-only prompt and one tool-call test.
  3. Disable unattended execution and set token and retry limits in the surrounding agent.
  4. Check NVIDIA’s data, licensing, retention, and account-specific trial terms.
  5. Remove the trial profile after evaluation; use a separately subscribed service for production.

NVIDIA’s endpoint is useful for internal compatibility testing and evaluation only. It is a separate product from Moonshot’s direct Kimi API: provider behavior, retention, availability, and tool handling can differ even when the underlying model name is similar.

K2.6 is not K3

Kimi K3 is Moonshot’s latest flagship in this stack, with a 1M context window and released weights under the Kimi K3 License. NVIDIA’s current hosted route is K2.6. Choose based on the actual requirement:

RequirementRoute to evaluate
NVIDIA-hosted OpenAI-compatible trialmoonshotai/kimi-k2.6 on NIM
Newest managed Kimi flagshipkimi-k3 through Moonshot
Self-hosted K3 evaluationOfficial K3 weights and license
Cheaper routine Kimi codingKimi K2.7 Code through Moonshot

The Kimi access guide keeps those plans, models, and prices separate. The Smart Spend guide explains why a trial route is not the same measure as accepted-result cost.

Sources and status

Related: Free Stack, Kimi K3, Kimi access, and OpenClaw provider policies.

Last verified: August 1, 2026. NVIDIA listed Kimi K2.6, not K3. Trial use is not for production without a separate subscription; payment method, quota, expiry, and account rate limits remain unresolved.