Kimi K3

moonshotai/Kimi-K3

Moonshot AI's frontier reasoning model: 1M context, thinking, and tool calling, served with the lowest average latency of any provider measured on the Requesty gateway.

thinkingtool calling

Input: $3.00 / 1M
Output: $15.00 / 1M
Cached: $0.45 / 1M
Context: 1M
Type: Chat
Maker: Moonshot
Released: 2026-07-27

Positioning

The largest reasoning model in the sference catalog and the default pick for hard planning turns: long-horizon agentic workloads, planning-heavy coding sessions, and anything where the model needs to think before it answers. Kimi K3 trades speed for depth — for short interactive turns, the GLM 5.3 family is cheaper and faster; when the question is hard, Kimi K3 is the one that reasons its way through.

Thinking is supported on the OpenAI-shaped endpoints with thinking: {"type": "enabled"}.

Compared to the portfolio

Intelligence vs price

Chat models on sference

Index

44/100

Blended

$6.00/1M

↖ Smarter for less

$0.25$0.50$1.00$2.00

44$6.00

Kimi K3

GLM 5.3

DeepSeek V4.1 Flash

GLM 5.3 Flash

↑ IndexBlended $ / 1M · log →

Artificial Analysis Intelligence Index v4.3 (0–100), measured across all providers by Artificial Analysis, not sference specifically. Blended price weights input and output 3:1. Hover a point for the reasoning-effort variant scored. Source

Model	Context	Input	Output	Index	Vision
Kimi K3	1M	$3.00	$15.00	44	—
GLM 5.3	1M	$1.20	$4.20	45	—
DeepSeek V4.1 Flash	1M	$0.50	$1.50	39	✓
GLM 5.3 Flash	1M	$0.20	$0.60	42	✓
DeepSeek V4 Flash (0731)	1M	$0.28	$0.56	—	—
Clef 27Bdecisions	64K	$0.24	—	—	—

Serverless rates per 1M tokens at realtime priority, confirmed per model when your account is provisioned. Dedicated deployments are billed per GPU-hour on monthly commitments.

Benchmarks

Average latency — Requesty live gateway comparison, mid-August 2026426 mslower is better

source

Output throughput — Requesty live gateway comparison, mid-August 202676 tok/s

source

Use it

POST /v1/chat/completions: Realtime, flex (service_tier: "flex")
POST /v1/responses: Realtime, flex, and the 24h async window (background: true)
POST /v1/messages: Anthropic Messages shape, realtime only

curl https://api.sference.com/v1/chat/completions \
  -H "Authorization: Bearer $SFERENCE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "moonshotai/Kimi-K3",
    "messages": [{ "role": "user", "content": "Say hello in one sentence." }]
  }'

OpenAI-compatible; most clients switch with a base-URL change. Quickstart · Python SDK · Claude Code

Generated from the live catalog (GET /v1/models), so pricing, context, and capabilities always match the API. Machine-readable version: https://sference.com/models/moonshotai/Kimi-K3.md