Inkling Small
thinkingmachines/inkling-smallInkling-Small is a Mixture-of-Experts transformer (276B total, 12B active) with native reasoning over audio and images and variable thinking effort.
TM
Inkling
Inkling is an open-weight multimodal Mixture-of-Experts model from Thinking Machines Lab with 975B total and 41B active parameters. It takes text, image and audio input with a 524K-token context window and targets reasoning, coding and tool use.
Context
524K
Max output
472K
Input /1M
$1.00
Output /1M
$4.05
Blended /1M
$1.76
AcceptsTextImageAudioProducesTextTokenizer Other
Providers
FastRouter routes your requests to this provider. You can also bring your own key.
ProviderInput /1MOutput /1MContextMax outputLatencyThroughputFeaturesDetails
Together AINVFP4
togetherInput /1M$1.00
Output /1M$4.05
Context524K
Max output472K
Latency—
Throughput—
Supports tool callingSupports reasoning
Supported parameters
Request parameters you can send with this model.
Core (Sampling & basic generation)
- max_tokens
- Maximum tokens to generate.
- min_p
- Minimum probability threshold for sampling.
- stop
- Sequences where generation stops.
- temperature
- Controls randomness of output.
- top_k
- Limits sampling to top K tokens.
- top_p
- Nucleus sampling threshold.
Penalties (Token Penalties)
- frequency_penalty
- Penalizes frequent tokens.
- presence_penalty
- Penalizes tokens already present.
- repetition_penalty
- Penalizes repeated tokens.
Reasoning (Reasoning Controls)
- include_reasoning
- Include reasoning trace in the response.
- reasoning
- Provider-specific reasoning configuration.
- reasoning_effort
- Reasoning effort before answering.
Tool Use (Function Calls & Tools)
- tool_choice
- How the model should use tools.
- tools
- Tool/function definitions available to the model.
Performance
Median throughput and time to first token per provider over the last week.
Throughput
Latency
Make your first API call
OpenAI-compatible. Point your SDK at FastRouter, or call the API directly.
Replace
<FASTROUTER_API_KEY> with your key · Get your key →Installfrom openai import OpenAI
client = OpenAI(
base_url="https://api.fastrouter.ai/api/v1", # FastRouter base URL
api_key= "<FASTROUTER_API_KEY>", # Replace with your FastRouter API key
)
completion = client.chat.completions.create(
model="thinkingmachines/inkling", # Replace with your model ID
messages=[
{ "role": "user", "content": "What is the meaning of life?" }
]
)
print(completion.choices[0].message.content)
Frequently asked questions
More models from Thinking Machines
Model scores sourced from ArtificialAnalysis