- 1M context
- Multimodal
- Reasoning
- Responses API
- NEW · Nov 9
Inkling 2 Small on QuickSilver Pro
Inkling 2 Small from Thinking Machines Lab. Open-weight multimodal reasoning with 594B total and 17B active parameters. $0.165 input / $0.55 output per million tokens.
- 1M context
- 944K max output
- Vision
- Tools
- Reasoning · on by default
- Streaming
- JSON Schema output
You pay · input / output per 1M
$0.165 / $0.55
10% more expensive
on both legs vs OpenRouter
Pricing comparison ($/1M tokens)
Bar length = price relative to the highest price shown
| Provider | Input | Output | vs QSP |
|---|---|---|---|
| QuickSilver Pro | $0.165 | $0.55 | — |
| OpenRouter(thinkingmachines/inkling-2-small) | $0.15 | $0.50 | 10% more expensive |
Thinking Machines Lab list source: openrouter.ai/thinkingmachines/inkling-2-small
At a glance
- Context
- 1M tokens
- Input / 1M
- $0.165
- Output / 1M
- $0.55
- Thinks by default
- Yes
- Max output
- 944K
- Latency · live
- —
Open-weight multimodal reasoning with 594B total and 17B active parameters.
When is Inkling 2 Small the right call?
Curated from catalog capabilities and published prices, not a benchmark.
When to use
Choose Inkling 2 Small for workflows using text input, image input, text output, streaming, reasoning, tool calling and JSON Schema. Image-based JSON and streaming automatic tool calls passed upstream probes.
- 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
The maximum output is 944K tokens within a 1M-token context. Reasoning is billed as output and small budgets can leave no visible answer. Reasoning is always on: requests that disable it are rejected. Forced required/named tool choices are not verified for this route.
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": "inkling-2-small",
"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="inkling-2-small",
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: "inkling-2-small",
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": "inkling-2-small",
"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="inkling-2-small",
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
- $0.15 / $0.50openrouter.ai/thinkingmachines/inkling-2-small
- Catalog verified
- Prompt cache · not compared
- $0.033 read
usage.cost = prompt_tokens × $0.165/1M + completion_tokens × $0.55/1M
FAQ
Common questions
$0.165 input / $0.55 output per million tokens; cache reads $0.033 per million tokens.
Chat Completions and Responses. Verified capabilities: text input, image input, text output, streaming, reasoning, tool calling and JSON Schema. Audio, video and file input have not been tested by QSP.
Set base_url=https://api.quicksilverpro.io/v1, use your QSP API key and model="inkling-2-small". Preserve complete assistant messages, including reasoning_details, across tool turns.