Online

Kimi K3 Free

Moonshot AI · OpenAI-compatible API

moonshotai/kimi-k3-free

Kimi K3 capabilities at zero token cost after at least $10 cumulative net recharge.

Recharge to use Kimi Free →Quickstart ↓

Free

Input$0

Cache Read$0

Cache Write—

Output$0

Context: 1M
Max Output: 1M
Tool Calling: ✓
Reasoning: ✓
Vision: ✓
Streaming: ✓

Catalog updated: 2026-10-21.

Overview

The same context, maximum output and capabilities as Kimi K3, with zero token prices after at least $10 cumulative net recharge. This free route is especially slow; expect long waits.

Tasks and selection tradeoffs

Multi-document research draft

Build a referenced synthesis from supplied sources, then check every citation.

Large-context code planning

Combine architecture notes and source excerpts to propose staged changes.

Task suggestions based on catalog features and price, not model quality benchmarks.

Choose your tool

OpenAI SDKCall from Python or JavaScript Vercel AI SDKBuild a TypeScript application

Choose a model and tool for your task →

Route acceptance record

2026-10-21

Test date	Endpoint	Capability	Route test
2026-10-20	`POST /v1/chat/completions`	Text response	Passed
2026-10-20	`POST /v1/chat/completions`	Streaming	Passed
2026-10-20	`POST /v1/chat/completions`	Reasoning	Passed
2026-10-21	`POST /v1/chat/completions`	JSON mode (json_object)	Passed
2026-10-21	`POST /v1/chat/completions`	Tool calling	Passed
2026-10-21	`POST /v1/chat/completions`	Image input	Passed

Small acceptance samples on the stated date. Full context and output limits are catalog declarations; long-context quality, complete coding workflows and sustained stability were not established by these checks.

Pricing

Prices in USD per 1M tokens.

Input$0

Cache Read$0

Cache Write—

Output$0

Example task: Synthesize several long source documents

Assume 80,000 aggregate input tokens and 6,000 billable output tokens across all calls. No cache hit.

80,000 × $0 / 1M + 6,000 × $0 / 1M = $0.000000

If usage actually reports 60,000 of those input tokens as cached, replace that portion at the cached-input rate ($0/1M): $0.000000. Cached tokens are part of total input, never added on top.

Illustrative calculation using the 2026-10-21 catalog snapshot. Include every agent call and retry, repeated history and billable reasoning output; settle against actual usage and current Console prices.

Estimate your monthly cost

Uses the 2026-10-21 catalog snapshot, independently of the live prices above. USD per 1M tokens; an estimate, not a bill.

Estimate includes standard text input, cache reads and text output only. Long-context premiums, service tiers, cache writes, image output and tool fees are excluded.

Model

Total input tokens / request

Billable output tokens / request

Cache-hit tokens / request

Requests / month

Cached share of input

Cache-hit share = cache-hit tokens ÷ total input. Changing total input keeps the current share; dragging the slider updates cache-hit tokens. Output includes billable reasoning. Count agent steps and retries as requests.

Estimated monthly cost

—USD / month

Kimi K3 Free

Uncached input: —
Cache read: —
Billable output: —

Connect this model →

Calculation and billing basis

Monthly cost = requests × [input × (1 − cached share) × input rate + input × cached share × cache-read rate + output × output rate] / 1,000,000.

Cached tokens are part of total input, never added on top. Use actual cache-read hits from usage; repeating a prompt does not guarantee a hit. Missing rates are unconfirmed, not $0. Separate cache-write, storage and other additional fees are excluded. Settle against actual usage and current Console prices.

Enable JavaScript to use the calculator. The worked example above remains available.

Usage limits

This free route is especially slow; allow long waits and use a bounded output budget.
See the current context and maximum output in the model specifications above. Input and requested output share the context budget.
The context and capability flags describe the public catalog. They do not establish a particular tool workflow or a quality score.
Start with one representative task. Check correctness, actual usage and response time before increasing traffic.
Use the integration examples to connect your application and handle tool results.

Kimi K3 Free · Kimi K3 capabilities at zero token cost after at least $10 cumulative net recharge. Only completed recharge principal minus refunds counts; grants and fees do not. Spending your balance keeps access; refunds below $10 block new requests. This free route is especially slow; expect long waits. Qwen allowances and recharge tiers do not apply. Need faster responses? Use paid Kimi K3 →

API parameters

Parameter / protocol field	Usage
`model / messages`	Use the exact model ID and chat message list
`tools / tool_calls / tool messages`	Use tools to define functions and role=tool to return their results
`stream / stream_options.include_usage`	Use SSE streaming with final usage
`max_tokens`	Set an output budget within the model and account limits

Parameters vary by model. Keep model-specific controls separate from shared OpenAI-compatible fields.

API

OpenAI-compatible API

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.iteracompute.com/v1",
    api_key=os.environ["ITERACOMPUTE_API_KEY"],
)
response = client.chat.completions.create(
    model="moonshotai/kimi-k3-free",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.iteracompute.com/v1",
  apiKey: process.env.ITERACOMPUTE_API_KEY,
});
const response = await client.chat.completions.create({
  model: "moonshotai/kimi-k3-free",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

curl https://api.iteracompute.com/v1/chat/completions \
  -H "Authorization: Bearer $ITERACOMPUTE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "moonshotai/kimi-k3-free",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

moonshotai/kimi-k3-freeView Docs →

Base URL: https://api.iteracompute.com/v1
Endpoint: POST /v1/chat/completions
Model ID: moonshotai/kimi-k3-free
Authentication: Authorization: Bearer ITERACOMPUTE_API_KEY

View Docs

FAQ

How do I use Kimi K3 Free with the OpenAI SDK?

Set base_url to https://api.iteracompute.com/v1 and model to moonshotai/kimi-k3-free. Authenticate with your IteraCompute API key.

What does Kimi K3 Free cost?

Input, cached input and output tokens cost $0 after at least $10 cumulative net recharge. This free route is especially slow; expect long waits. Fair-use limits apply and free capacity has no SLA.

What context length is available?

See the model specifications above for the current context and maximum output. Input and requested maximum output share the context budget.

Why does Kimi K3 Free return 403 model_recharge_required?

At least $10 cumulative net recharge is required: completed recharge principal minus refunds, excluding grants and fees. Spending balance keeps access; refunds below $10 block new requests. Recharge in the Console before retrying. Qwen allowances and recharge tiers do not apply.

Ready for your first request?

Recharge to use Kimi Free →