thinkingmachinesNot yet certifiedReleased 11/12/2026

Inkling 2 Small

Inkling 2 Small is Thinking Machines Lab’s second-generation multimodal Mixture-of-Experts model, with 594 billion total parameters and 17 billion active per token. It combines text and image understanding with controllable reasoning for coding, tool use, and professional knowledge work.

View API reference ↓
Input / output priceFrom$0.30 / $1.00per 1M
24h uptime99.19%

Listed for reference. Inference Bureau dispatches only to certified routes, so requests for this model are refused until one is certified. See certified models.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inferencebureau.com/v1",
  apiKey: process.env.IB_API_KEY,
});

const res = await client.chat.completions.create({
  model: "thinkingmachines/inkling-2-small",
  messages: [{ role: "user", content: "Why is the sky blue?" }],
});

console.log(res.choices[0].message.content);

Providers

Dispatch routes requests across these providers and fails over between them without changing the model. Restrict or order providers with team Directives. Prices are gateway list prices before the platform fee.

ProviderContextMax outputLatencyThroughputInputOutputCacheCapabilitiesZDRNo trainingRegionsStatus
DeepInfra262K262K0.5 s—$0.30$1.00Read $0.030Write —6 featuresNoYesGlobalListed
modal1.05M131K0.5 s120 tps$0.30$1.00Read $0.030Write —5 featuresYesYesGlobalListed
nebius1.05M262K0.5 s60 tps$0.30$1.00Read $0.060Write —6 featuresYesYesGlobalListed
Together AI1.05M262K0.5 s544 tps$0.30$1.00Read $0.030Write —6 featuresYesYesGlobalListed

Uptime

24 hours

Request success rate per provider.

DeepInfra100.00%
modal97.72%
nebius99.08%
Together AI99.96%

Throughput

last hour

P50 output tokens per second.

Together AI544 tps
modal120 tps
nebius60 tps
DeepInfra—

Latency

last hour

P50 time to first token.

Together AI0.5 s
nebius0.5 s
DeepInfra0.5 s
modal0.5 s

Getting started

Create a key on the API Keys page and set it as IB_API_KEY. See the quickstart.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inferencebureau.com/v1",
  apiKey: process.env.IB_API_KEY,
});

const res = await client.chat.completions.create({
  model: "thinkingmachines/inkling-2-small",
  messages: [{ role: "user", content: "Why is the sky blue?" }],
});

console.log(res.choices[0].message.content);

Top-level parameters

Standard Chat Completions parameters work as documented. These have model-specific behavior.

ParameterTypeRequiredDescription
modelstringYesModel ID in the form creator/model, e.g. thinkingmachines/inkling-2-small. Must be allowed by your team's Directives.
max_tokensnumberNoHard cap on generated tokens, and the basis for the balance reserved per request. Inkling 2 Small supports up to 262,144 output tokens.
reasoning{ effort: 'low' | 'medium' | 'high' }NoReasoning effort, mapped to the provider's native configuration. Reasoning tokens count toward output usage.
toolsTool[]NoFunction definitions the model can call. Tool calls are returned in choices[].message.tool_calls.
Supportedmax_tokenstemperaturestoptoolstool_choicereasoninginclude_reasoningresponse_formatstructured_outputs

Input limits

InputSourcesLimits
Text—Prompt and response share the 1.05M-token context window
ImageURL, base64Sent as image_url content parts; counts as input tokens

More models by thinkingmachines

ModelContextInputOutputCacheRelease
thinkingmachines/inkling-small1M$0.45$1.20Read $0.100Write —07/30/2026
thinkingmachines/inkling256K$1.00$4.05Read $0.17Write —07/15/2026