- 1M context
- Multimodal
- Reasoning
- Responses API
- NEW · Oct 23
Kimi K3.1 Pro on QuickSilver Pro
Kimi K3.1 Pro — Moonshot reports a 1M-token context and plans to release full weights by November 4, 2026.
- 1M context
- 944K max output
- Vision
- Tools
- Reasoning · on by default
- Streaming
- JSON Schema output
You pay · input / output per 1M
$2.00 / $10.00
At list price
same rates as OpenRouter
Pricing comparison ($/1M tokens)
Bar length = price relative to the list price
| Provider | Input | Output | vs QSP |
|---|---|---|---|
| QuickSilver Pro | $2.00 | $10.00 | — |
| OpenRouter(moonshotai/kimi-k3.1-pro) | $2.00 | $10.00 | same |
Moonshot AI via OpenRouter list source: openrouter.ai/api/v1/models/moonshotai/kimi-k3.1-pro/endpoints
At a glance
- Context
- 1M tokens
- Input / 1M
- $2.00
- Output / 1M
- $10.00
- Thinks by default
- Yes
- Max output
- 944K
- Latency · live
- —
Long-context coding and image-based workflows.
When is Kimi K3.1 Pro the right call?
Curated from catalog capabilities and published prices, not a benchmark.
When to use
Use for coding, images and tool workflows over a large context.
- Long documents and codebases, up to 1M tokens of context
- Agents that call tools, with strict JSON Schema output
- Prompts that include images
- Multi-step reasoning, on by default
When to use something else
Choose another model if you need forced named functions; these endpoints reject that tool_choice.
Quickstart (curl)
Get an API key →curl https://api.quicksilverpro.io/v1/chat/completions \
-H "Authorization: Bearer $QSP_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "kimi-k3.1-pro",
"messages": [{"role": "user", "content": "Hello!"}]
}'import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.quicksilverpro.io/v1",
api_key=os.environ["QSP_KEY"],
)
response = client.chat.completions.create(
model="kimi-k3.1-pro",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.quicksilverpro.io/v1",
apiKey: process.env.QSP_KEY,
});
const response = await client.chat.completions.create({
model: "kimi-k3.1-pro",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);curl https://api.quicksilverpro.io/v1/responses \
-H "Authorization: Bearer $QSP_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "kimi-k3.1-pro",
"input": "Hello!"
}'import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.quicksilverpro.io/v1",
api_key=os.environ["QSP_KEY"],
)
response = client.chat.completions.create(
model="kimi-k3.1-pro",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)OpenAI-compatible. One-line migration via base_url.
Gateway behavior
Compatibility notes for this model.
prompt- Prompts up to 1M tokens.
max_tokens- Up to 944K output tokens.
- /v1/chat/completions: Supported
- /v1/responses: Supported
- streaming: Supported
- tools: Supported
- image input: Supported
- JSON Schema: Supported
- reasoning: Supported
Where the price comes from
- Provider reference
- $2.00 / $10.00openrouter.ai/api/v1/models/moonshotai/kimi-k3.1-pro/endpoints
- Catalog verified
- Prompt cache · not compared
- $0.20 read
usage.cost = prompt_tokens × $2.00/1M + completion_tokens × $10.00/1M
FAQ
Common questions
Per million tokens: $2.00 input / $10.00 output; cached input $0.20, at Moonshot endpoint list parity.
Reasoning is on by default. Our upstream probes verified reasoning: { enabled: false }. The 16/64-token probes bounded total completion tokens, including reasoning.
Tools with auto or required selection, JSON Schema, image input and streaming usage passed on both endpoints. Forced named functions returned 404. ZDR requests succeeded. OpenRouter also lists video input; video was not tested.
Use model="kimi-k3.1-pro" with base_url=https://api.quicksilverpro.io/v1. The advertised context is 1M tokens and output limit is 944K tokens; launch probes used at most 128 output tokens.