- 1M context
- Multimodal
- Reasoning
- Responses API
- NEW · Nov 21
Inkling 2 Mini on QuickSilver Pro
Inkling 2 Mini from Thinking Machines Lab. Open-weight multimodal looped transformer with 26.4B total and 3.4B active parameters. $0.11 input / $0.44 output per million tokens.
- 1M context
- 66K max output
- Vision
- Tools
- Reasoning · on by default
- Streaming
- JSON Schema output
You pay · input / output per 1M
$0.11 / $0.44
10% more expensive
on both legs vs Published reference
Pricing comparison ($/1M tokens)
Bar length = price relative to the highest price shown
| Provider | Input | Output | vs QSP |
|---|---|---|---|
| QuickSilver Pro | $0.11 | $0.44 | — |
| Published reference(thinkingmachines/inkling-2-mini) | $0.10 | $0.40 | 10% more expensive |
Thinking Machines Lab list source: thinkingmachines.ai
At a glance
- Context
- 1M tokens
- Input / 1M
- $0.11
- Output / 1M
- $0.44
- Thinks by default
- Yes
- Max output
- 66K
- Latency · live
- —
Lowest-priced Inkling for text, images and automatic tools.
When is Inkling 2 Mini the right call?
Curated from catalog capabilities and published prices, not a benchmark.
When to use
Choose Inkling 2 Mini as the lowest-priced Inkling, below Inkling 2 Small, for text input, image input, text output, streaming, reasoning, tool calling and JSON Schema. Small probes passed text, image recognition, streaming, automatic tools, strict JSON Schema and low or disabled reasoning.
- 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
Use Inkling 2 Small when you need its larger output budget. Inkling 2 Mini allows 66K output tokens in a 1M-token context. Very long inputs depend on availability of the full-context route. Named forced tools passed on the primary route but are unavailable on the fallback. Reasoning counts as output; small budgets may leave no visible answer. Compare latency on your workload; these probes do not establish a speed ranking.
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-mini",
"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-mini",
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-mini",
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-mini",
"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-mini",
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 66K 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
- $0.10 / $0.40thinkingmachines.ai
- Catalog verified
- Prompt cache · not compared
- $0.022 read
usage.cost = prompt_tokens × $0.11/1M + completion_tokens × $0.44/1M
FAQ
Common questions
$0.11 input / $0.44 output per million tokens; cache reads $0.022 per million tokens. Reasoning tokens are charged once as output.
Chat Completions and Responses. Supported capabilities: text input, image input, text output, streaming, reasoning, tool calling and JSON Schema. Set reasoning={enabled:false} to disable reasoning or reasoning={effort:"low"} for low effort. 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-mini". Preserve complete assistant messages, including reasoning_details, across tool turns.