Kyma APIKyma API
Moonshot

Moonshot

Kimi K3

Kimi K3 is a 2.8T open-weight reasoning model built for long-horizon agentic workflows and large-repo analysis. Developers should reach for it when they need a million-token context window with vision input and reliable tool execution.

Modalities

Text+Image → Text

Below release

None reported

Weights

Published

moonshotai/Kimi-K3

Where it sits in the catalogue Kyma measures

Every number against every text model Kyma prices per token — a stated rule, not a chosen line-up.

Price · input#64/71

$3.768

output $18.837 · cached $0.405

median $1.013 · best $0.0494

Price · output#63/70

$18.837

per 1M tokens generated

median $3.531 · best $0.218

Availability · 30d#38/54

98.9%

908 observations since 2026-07-29

median 99.9% · best 100.0%

Throughput

52 tok/s

from traffic, 7d — real prompts, not a probe

median 35.7 tok/s · best 365.1 tok/s

Response time

2.79 s

from traffic, 7d — real prompts, not a probe

median 2.96 s · best 0.89 s

Context

1.05M

max output 32,768

published by Moonshot, not measured here

Tick above each rail is this model, below it the other 70. Dashed rule is the field median, solid is its best. Better is left; the axis stops at the 90th percentile, so a few models sit past its right edge.

Usage

How much this model is actually called here.

Rank

#17

of 101 active models

Tokens served

45.4M

all-time

Platform share

1.0%

of all tokens

Tokens · last 14 daysSep 26 → Oct 9

How it behaves under real clients

The same model answering different prompt shapes — measured, not benchmarked.

ClientRequestsTokensThroughputTo first tokenp95 totalCompleted
OpenClaw98828.9M47 tok/s1.62 s31 s100%

Grouped by the client that sent the request. Not a benchmark: the same model on different prompt shapes. Throughput and time-to-first-token are medians; p95 is the slowest response in twenty.

Pricing

Pay per token. Cached input bills at this model’s own cached rate, listed below.

$3.768 /1M input$18.837 /1M output
Hobby10 req/day · 2K in / 500 out
~$5.09/mo
Production1,000 req/day · 2K in / 500 out
~$509/mo
Scale20,000 req/day · 2K in / 500 out
~$10,173/mo
+ Estimate your workload
1,000
2,000
500
30%

Estimated monthly cost

$448

$14.94 / day on Kimi K3

Same workload on:

Kimi K2.7 Code$132-71%
Kimi K2.6$102-77%

Estimates use list pricing with cached input at this model's own cached rate. Actual bills depend on real token counts, and every response includes its exact cost.

When to use Kimi K3

Updated 2026-07-29

Where this model earns its cost — and where it doesn't.

Kimi K3 is Moonshot’s 2.8T open-weight multimodal model, designed as a successor to K2.7. It accepts text and image inputs and outputs text, with native support for structured outputs, tool calling, and explicit reasoning steps. The model operates with a 1,048,576-token context window and a maximum output length of 32,768 tokens.

On Kyma, the model runs through an OpenAI-compatible endpoint with automatic request failover and exact cost reporting in the usage.cost field. Prompt caching is supported, reducing repeated prefix costs to this model's cached input rate. The platform serves it at a medium speed tier.

The 32,768-token output cap means it is not suited for generating extremely long documents in a single pass. As a premium-tier model, it carries higher per-token costs than lighter alternatives, and its medium throughput requires planning for latency-sensitive applications.

Agentic Workflow Execution

Handles multi-step coding and tool execution across extended sessions without losing context.

Large Repository Analysis

Ingests entire codebases or documentation sets within its million-token window for cross-file reasoning.

Vision-Enabled Document Review

Processes image inputs alongside text to extract and reason over multimodal data.

Structured Data Extraction

Outputs strictly formatted JSON or XML for reliable downstream parsing and API integration.

Not ideal for: It is not the right choice for high-throughput, low-latency chat or generating outputs longer than 32,768 tokens.

How it compares

Against the peers people actually weigh it against.

SpecKimi K3Kimi K2.7 CodeKimi K2.6
Input /1M$3.768$1.009$0.7856
Output /1M$18.837$4.774$3.667
Context1M262K262K
ToolsYesYesYes
ReasoningYesYesYes
Throughput52 tok/s33 tok/s29 tok/s

Quick start

Up and running in under two minutes.

  1. 1

    Create an API key

    Sign up and grab a key from the dashboard. Kimi K3 needs a top-up — the signup credit covers the free tier.

    Get API key →
  2. 2

    Make your first request

    Drop in your key and send a chat completion — fully OpenAI-compatible.

    curl https://kymaapi.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kimi-k3",
    "messages": [
      {"role": "user", "content": "Explain prompt caching in one paragraph."}
    ]
  }'
  3. 3

    Stream responses

    Add "stream": true to receive tokens as they arrive.

    curl https://kymaapi.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kimi-k3",
    "stream": true,
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

FAQ

Common questions about this model.

What is the context window of Kimi K3?

Kimi K3 has a 1M-token context window — roughly 1542 pages of text in a single request.

How much does the Kimi K3 API cost?

$3.768 per 1M input tokens and $18.837 per 1M output tokens, with cached input at $0.405/1M — 89% off the input rate on repeated prompt prefixes. No subscription; you pay only for what you use.

Does Kimi K3 support function calling?

Yes — Kimi K3 supports tool/function calling and structured outputs (JSON mode), so it works with agent frameworks out of the box.

Are the weights for Kimi K3 publicly available?

Yes. Moonshot publishes Kimi K3's weights as moonshotai/Kimi-K3, so you can download and run the model yourself (https://huggingface.co/moonshotai/Kimi-K3, read 2026-08-14). Kyma serves it because it is convenient and has failover behind it, not because it is the only way to reach it.

Is Kimi K3 ever served below the precision its creator released it at?

Not as far as Kyma can see. Kimi K3 was released by Moonshot at mxfp4 + mxfp8 (https://huggingface.co/moonshotai/Kimi-K3, read 2026-08-14), and no route serving it here reports a format below that, as checked on 2026-09-21. Read that as the absence of a claim rather than as a guarantee: a route publishes its precision only where it chooses to, and most state nothing either way.

How do I use Kimi K3?

Kyma is OpenAI-compatible: point your SDK's base URL at https://kymaapi.com/v1, use your Kyma API key, and set the model to kimi-k3. Signing up is free, but this model needs a top-up: the $0.50 signup credit covers the free tier only.

Does Kyma support prompt caching for this model?

Yes, repeated prompt prefixes are cached automatically and billed at this model's cached input rate.

What happens if the serving path fails during a request?

Kyma routes every request through automatic failover, so degraded paths are silently rerouted without dropping the call.

Can I use this model for image analysis?

Yes, Kimi K3 accepts both text and image inputs, though it only outputs text.

Needs a top-up — the signup credit covers the free tier.Create account →

More models by Moonshot

ModelContextInputOutput
MoonshotKimi K2.7 Code262K$1.009$4.774
MoonshotKimi K2.6262K$0.7856$3.667