Inkling Small

Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of the Inkling family and is suited for reasoning, coding, agentic workflows, retrieval-augmented generation, instruction following, and multilingual conversation.

thinkingmachines/inkling-small

Organization: Thinking Machines
Family: ling
Providers: 11
Context: 1,048,576
Output limit: 1,048,576
Knowledge: —
Release: 2026-07-30
Updated: 2026-07-30
Weights: Open
Input: text, image, audio
Output: text
Capabilities: Tools, Reasoning, Temperature

Providers

Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.

14 offers · USD per million tokens

Provider	Model ID	Context	Output	Input / output · 1M	Reasoning	Tools	Structured	Details
Arcee	thinkingmachines/inkling-small	262,144	262,144	$0.50 / $1.20	Yes	Yes	—	View
Baseten	thinkingmachines/inkling-small	1,048,576	32,768	$0.50 / $1.20	Yes	Yes	Yes	View
Deep Infra	thinkingmachines/Inkling-Small	524,288	1,048,576	$0.45 / $1.20	Yes	Yes	Yes	View
Eden AI	deepinfra/thinkingmachines/Inkling-Small	524,288	1,048,576	$0.45 / $1.20	Yes	Yes	Yes	View
Hugging Face	thinkingmachines/Inkling-Small	524,288	1,048,576	$0.50 / $1.20	Yes	Yes	—	View
Kilo Gateway	thinkingmachines/inkling-small:free	1,048,576	262,144	$0.00 / $0.00	Yes	Yes	No	View
Kilo Gateway	thinkingmachines/inkling-small	524,288	262,144	$0.45 / $1.20	Yes	Yes	No	View
LLMTR	thinkingmachines/inkling-small	262,144	262,144	$0.58 / $1.44	Yes	Yes	—	View
NanoGPT	thinkingmachines/Inkling-Small	524,288	32,768	$0.50 / $1.20	No	Yes	No	View
NanoGPT	thinkingmachines/Inkling-Small:thinking	524,288	32,768	$0.50 / $1.20	Yes	Yes	No	View
DeepInfravia OpenRouter	thinkingmachines/inkling-small fp8	524,288	262,144	$0.45 / $1.20	Yes	Yes	No	View
Thinking Machinesvia OpenRouter	thinkingmachines/inkling-small:free nvfp4	1,048,576	262,144	$0.00 / $0.00	Yes	Yes	No	View
Pioneer	thinkingmachines/inkling-small	1,000,000	131,072	$0.50 / $1.20	Yes	Yes	—	View
Vercel AI Gateway	thinkingmachines/inkling-small	1,000,000	1,000,000	$0.45 / $1.20	Yes	Yes	—	View

Prices and limits apply to each offer. A dash means the value is not provided. OpenRouter offers show the hosting provider and routing channel separately.

Pricing

Compare token rates and cache charges across available routes and hosting configurations.

USD per million tokens

Input from$0.00Per 1M input tokens

Output from$0.00Per 1M output tokens

Available offers14Across 11 providers

Lowest listed input and output prices across the offers above; they may belong to different providers. These are base rates, before conditional pricing, discounts or additional fees.

Endpoint price comparisonLatest observed snapshot · 2 lowest-priced configurations

InputOutput

Thinking Machinesthinkingmachines/nvfp4

$0.00$0.00

DeepInfradeepinfra/fp8

$0.45$1.20

thinkingmachines/inkling-smallObserved Oct 4, 2026, 11:31 AM UTC

Input: $0.45
Output: $1.20
Cache read: $0.10

thinkingmachines/inkling-small:freeObserved Oct 4, 2026, 11:31 AM UTC

Input: $0.00
Output: $0.00

Hosting prices through OpenRouter All endpoints and cache rates

Endpoint	Input / 1M	Output / 1M	Cache read / 1M	Cache write / 1M
DeepInfradeepinfra/fp8	$0.45	$1.20	$0.10	—
Thinking Machinesthinkingmachines/nvfp4	$0.00	$0.00	—	—

Each row is a hosting configuration. Open an offer in Providers for its full pricing conditions and additional fees. Endpoint observations may differ from the routing catalog's base price.

Performance

Review reported latency and output-throughput percentiles from the latest observed rolling window.

Latest 30-minute observation

Time to first token · milliseconds

Latency distributionRolling 30-minute snapshot · 2 endpoints

P50P75P90P99

DeepInfradeepinfra/fp8

837–19,594 ms

Thinking Machinesthinkingmachines/nvfp4

1,092–4,554.8 ms

All latency percentiles 2 endpoints

Endpoint	P50	P75	P90	P99
DeepInfradeepinfra/fp8	837 ms	1,317 ms	2,024.2 ms	19,594 ms
Thinking Machinesthinkingmachines/nvfp4	1,092 ms	1,669 ms	2,279.8 ms	4,554.8 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 2 endpoints

P50P75P90P99

DeepInfradeepinfra/fp8

48–140.56 t/s

Thinking Machinesthinkingmachines/nvfp4

118–338 t/s

All throughput percentiles 2 endpoints

Endpoint	P50	P75	P90	P99
DeepInfradeepinfra/fp8	48 t/s	59 t/s	78 t/s	140.56 t/s
Thinking Machinesthinkingmachines/nvfp4	118 t/s	168 t/s	220 t/s	338 t/s

Percentiles describe the observed request distribution. These are snapshots of a rolling window, not a historical time series.

Uptime

Compare successful request rates across the latest 5-minute, 30-minute, and 24-hour observations.

Successful requests by window

Availability by endpointCurrent overlapping windows · 2 endpoints

Endpoint5 minutes30 minutes24 hours

DeepInfradeepinfra/fp8Observed Oct 4, 2026, 11:31 AM UTC

—

100%

99.98%

Thinking Machinesthinkingmachines/nvfp4Observed Oct 4, 2026, 11:31 AM UTC

100%

99.92%

99.94%

Reported by OpenRouter at the time of collection; rate-limited requests are excluded. A dash means no measurement was reported. This is not a live availability check.

Benchmarks

Review attributed evaluation results on each source's original scale.

External evaluations

thinkingmachines/inkling-smallObserved Oct 4, 2026, 11:31 AM UTC

Benchmark profileArtificial Analysis · shared source scale from 0 to 60

Coding

52.9

Agentic

23.5

Intelligence

25.7

thinkingmachines/inkling-small:freeObserved Oct 4, 2026, 11:31 AM UTC

Benchmark profileArtificial Analysis · shared source scale from 0 to 60

Coding

52.9

Agentic

23.5

Intelligence

25.7

Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not OpenAI Suite ratings.

Detailed evaluations

Evaluation scoresAccuracy or item F1 · higher is better

gpqa diamondThinking Machines: Inkling Small

86.56%

tau bench verified airlineThinking Machines: Inkling Small

60.667%

Evaluation	Configuration	Source	Results	Details
gpqa diamond	Thinking Machines: Inkling Smallthinkingmachines/inkling-small-20260730	OpenRouter	86.56%	Details
Composite indices	Inkling Smallthinkingmachines/inkling-small-20260730	Artificial Analysis	Intelligence 25.7 · Coding 52.9 · Agentic 23.5	Details
tau bench verified airline	Thinking Machines: Inkling Smallthinkingmachines/inkling-small-20260730	OpenRouter	60.667%	Details

Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 4, 2026.

Technical details & API

Explore specifications, supported parameters, reasoning controls, and API identifiers for each OpenRouter route.

Current route specifications

thinkingmachines/inkling-smallObserved Oct 4, 2026, 11:31 AM UTC

Context: 524,288
Maximum output: 262,144
Tokenizer: Other
Input: text, image, audio
Output: text
Moderation: No
Added to OpenRouter: 2026-07-30

Base URLhttps://openrouter.ai/api/v1

Model IDthinkingmachines/inkling-small

Version IDthinkingmachines/inkling-small-20260730

Weights IDthinkingmachines/Inkling-Small

Reasoning

Required: No
Enabled by default: Yes
Default effort: high
Supported efforts: max, high, medium, low, minimal, none

Supported parameters

frequency_penalty
include_reasoning
logit_bias
max_tokens
min_p
presence_penalty
reasoning
reasoning_effort
repetition_penalty
seed
stop
temperature
tool_choice
tools
top_k
top_p

thinkingmachines/inkling-small:freeObserved Oct 4, 2026, 11:31 AM UTC

Context: 1,048,576
Maximum output: 262,144
Tokenizer: Other
Input: text, image, audio
Output: text
Moderation: No
Added to OpenRouter: 2026-07-30

Base URLhttps://openrouter.ai/api/v1

Model IDthinkingmachines/inkling-small:free

Version IDthinkingmachines/inkling-small-20260730

Weights IDthinkingmachines/Inkling-Small

Reasoning

Required: No
Enabled by default: Yes
Default effort: high
Supported efforts: max, high, medium, low, minimal, none

Supported parameters

frequency_penalty
include_reasoning
max_tokens
presence_penalty
reasoning
reasoning_effort
seed
stop
temperature
tools
top_p

Frequently asked questions

Answers based on the model metadata and serving offers currently in the catalog.

How much does Inkling Small cost?

Listed rates start at $0.00 per million input tokens and $0.00 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer Inkling Small?

There are 14 cataloged offers across 11 providers. Compare model IDs, prices and limits in Providers.

What is the context window?

The cataloged model context is 1,048,576 tokens. Each serving endpoint may apply a different limit.

Does it support tools and structured output?

Tool calling: Yes. Structured output: Not reported. Support can vary by endpoint.

Resources

Apache-2.0

Hugging Face ↗

Catalog history · 2 recorded revisions

Metadata observations since this model was first cataloged. These are not model release versions.

Sep 14, 2026 · 3137cd4e85c9
Sep 12, 2026 · f1ae507a6e93