How much does Kimi K2.6 cost on Velqa?

Kimi K2.6 costs $0.940 per million input tokens and $4.113 per million output tokens, in USD. It is included from the Dev plan up.

Can I use Kimi K2.6 without a subscription?

Yes. Kimi K2.6 can be called with prepaid Boost credit, without a monthly plan. Trying it in the playground does need an account, though: anonymous playground access is limited to the demo model.

Is Kimi K2.6 compatible with the OpenAI API?

Yes. Point your client at https://api.velqa.dev/v1 and set the model to "kimi-k2.6" — Kimi K2.6 answers on the standard chat completions endpoint, streaming included.

Kimi K2.6 API — pricing and access

Agentic coding SOTA, longues sessions

Input: $0.940 USD / 1M tokens
Output: $4.113 USD / 1M tokens
Context: 131k
Available on: Dev and above
Provider: Moonshot AI

Kimi K2.6 is the model to reach for as a coding agent: refactoring on an existing codebase, generating patches, autonomous development sessions that stretch across many successive calls. It requires the Dev plan or above, and its 131k window is enough to hold a long conversation history without losing the project's context.

Against Kimi K3, its bigger sibling in the same family, the difference is clear: K3 scales to a 1M-token context and reasons more deeply, but it's outside any plan, billed per token on Boost credit, and noticeably slower — K2.6 remains the right default as long as the task fits within 131k. Against GLM-5.2, a Dev-tier neighbor at a close price, K2.6 is specialized for code while GLM-5.2 targets general conversation.

It is not the right choice for high-volume chat or repeated short answers: the cost per token is higher than that case needs, and GLM-4.7 or DeepSeek V4 Flash cover it for much less.

Measured on Velqa

Time to first token: 0.55 s
Throughput: 21.6 tokens/s

Median of 5 streamed calls against api.velqa.dev, 2026-08-10.

Results announced by the provider

SWE-Bench Pro : 58.6 % source (2026-04-21)

Call it

OpenAI-compatible endpoint — change the base URL and the model id, nothing else.

curl https://api.velqa.dev/v1/chat/completions \
  -H "Authorization: Bearer $VELQA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kimi-k2.6",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Related models

FAQ

How much does Kimi K2.6 cost on Velqa?: Kimi K2.6 costs $0.940 per million input tokens and $4.113 per million output tokens, in USD. It is included from the Dev plan up.
Can I use Kimi K2.6 without a subscription?: Yes. Kimi K2.6 can be called with prepaid Boost credit, without a monthly plan. Trying it in the playground does need an account, though: anonymous playground access is limited to the demo model.
Is Kimi K2.6 compatible with the OpenAI API?: Yes. Point your client at https://api.velqa.dev/v1 and set the model to "kimi-k2.6" — Kimi K2.6 answers on the standard chat completions endpoint, streaming included.