Inference APIs
Compare/Chat

Kimi K2.6 vs Kimi K2.7 Code

Two open-weight chat models on the same endpoint and API key, so switching between them is a one-word change. Below: what each costs for three realistic workloads, how they differ, and measured speed.

Inference APIs prices are read live from the price list.

Short answer
  • Cost: Kimi K2.7 Code is cheaper in all three workloads, by 3–8%.
  • Speed (measured): Kimi K2.6 0.52 s to first token and 14 tok/s; Kimi K2.7 Code 0.87 s and 41 tok/s.

Side by side

Kimi K2.6Kimi K2.7 Code
Served byInference APIsInference APIs
Model authorMoonshot AIMoonshot AI
Model idmoonshotai/Kimi-K2.6moonshotai/Kimi-K2.7-Code
Input price$0.98 / 1M tokens$0.89 / 1M tokens
Output price$4.55 / 1M tokens$4.42 / 1M tokens
Context window262K tokens262K tokens
CapabilitiesChat, Reasoning, Coding, Tool callingChat, Reasoning, Coding, Tool calling
WeightsOpenOpen
StatusAvailableAvailable
LimitsNo per-minute or per-day request or token caps; usage draws on a prepaid balanceNo per-minute or per-day request or token caps; usage draws on a prepaid balance
Time to first token0.52 s0.87 s
Output speed13.9 tokens / s40.7 tokens / s

What three workloads cost

List prices applied to the same work. The cheaper side of each row is in bold.

WorkloadKimi K2.6Kimi K2.7 CodeDifference
Chat assistant — 10,000 turns of 800 tokens in, 300 out$21.49$20.385%
Long prompts or RAG — 10,000 requests of 8,000 in, 500 out$101$93.308%
Generation-heavy — 10,000 requests of 500 in, 2,000 out$95.90$92.853%

Kimi K2.7 Code is cheaper in all three workloads, by 3–8%. Reasoning models bill their thinking as output tokens, so real output counts run higher than the visible answer; treat the generation-heavy row as a floor for them.

When to choose which

Choose Kimi K2.6 if
  • Time to first token matters: 0.52 s against 0.87 s in our measurement
  • Your code or prompts were written for Kimi K2.6 (it is the most-referenced Kimi id on GitHub) and you want the exact model
  • Agentic coding tasks where the K2.6 behaviour is what you tested against
  • You need full-precision weights; our upstream serves this model at FP4
Choose Kimi K2.7 Code if
  • You stream long answers: 41 tokens per second against 14
  • Cost is the deciding factor; it is cheaper in every workload above
  • Coding agents: it is the coding-tuned model of Moonshot's Kimi family
  • Speed matters: about 14 tokens per second in our measurement, the slowest chat model here
  • You just want a current Kimi: K2.7 Code is faster and K3.1 Pro is stronger

Price, context and speed are measurable; answer quality on your task is not something a table can settle. Both take the same request, so the honest test is to run your own prompts through each in the playground.

Measured speed

Medians of three streamed runs on 2026-09-17, public endpoint, a prompt that asks for about 120 words. Time to first token is the first token of any kind, reasoning included; output speed counts every generated token from that point. Reasoning models then think before the visible answer starts: Kimi K2.6 began answering after — s and Kimi K2.7 Code after 37.34 s at default settings, which you can shorten with the reasoning controls on each model page. Expect ±30% with time of day. Method and raw numbers: speed measurements.

Trying both

Same endpoint, same key. Change one string:

cURL
for MODEL in "moonshotai/Kimi-K2.6" "moonshotai/Kimi-K2.7-Code"; do
  curl -s https://api.inferenceapis.com/v1/chat/completions \
    -H "Authorization: Bearer $INFERENCE_API_KEY" -H "Content-Type: application/json" \
    -d "{\"model\": \"$MODEL\", \"max_tokens\": 500, \"messages\": [{\"role\": \"user\", \"content\": \"Summarise the plot of Hamlet in two sentences.\"}]}" \
    | jq -r '.model, .choices[0].message.content, .usage'
done

FAQ

Which is cheaper, Kimi K2.6 or Kimi K2.7 Code?

Kimi K2.7 Code is cheaper in all three workloads, by 3–8%. The table above uses list prices: Kimi K2.6 $0.98 / 1M tokens input, $4.55 / 1M tokens output; Kimi K2.7 Code $0.89 / 1M tokens input, $4.42 / 1M tokens output.

How do I switch between them?

They are on the same endpoint and key. Change the model field from moonshotai/Kimi-K2.6 to moonshotai/Kimi-K2.7-Code and nothing else.

Why does Kimi K2.6 use more output tokens than the visible answer?

It is a reasoning model: it thinks before it answers and the thinking is billed as output tokens. Budget for that in output-heavy workloads, and set max_tokens to a few hundred or more so the answer is not cut off.

Spotted a price or limit that has changed? Tell us and we will re-check the provider page.