How much does Inkling 2 Small cost?

Inkling 2 Small costs $0.15/M input tokens and $0.50/M output tokens, with separate rates for Cache Read at $0.03/M tokens.

What is the context length of Inkling 2 Small?

Inkling 2 Small has a 1,048,576 token context window. It supports up to 1,048,576 completion tokens.

Does Inkling 2 Small support tool calling and structured outputs?

Yes. Inkling 2 Small accepts tools for function calling. It also supports structured outputs via a JSON schema in response_format.

What inputs and outputs does Inkling 2 Small support?

Inkling 2 Small accepts text and images as input and returns text.

Which providers serve Inkling 2 Small?

Inkling 2 Small is served by 6 providers on OpenRouter: Prime Intellect, DeepInfra, Modal, Nebius Token Factory, Together, and Cloudflare. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

When was Inkling 2 Small released?

Inkling 2 Small was released on November 9, 2026.

The free Inkling 2 Small endpoint is only available for use with agentic harnesses. Do not upload any confidential information or personal data (e.g., voices and images of people's faces). Your usage of this free endpoint, including prompts and outputs, is logged and used to improve Thinking Machines Lab's models, products, and services. The logged session data will be disassociated from your account and other persistent identifiers before being used for these purposes.

By using this free endpoint, you agree to the TML Free Research API Terms of Service. For more information about Thinking Machines Lab's data processing practices, see this Privacy Notice.

Thinking Machines: Inkling 2 Small

thinkingmachines/inkling-2-small

Model weights

Compare

Inkling 2 Small is an open-weight multimodal mixture-of-experts reasoning model from Thinking Machines Lab, with 17B active parameters out of 594B total. It is the first model in the second Inkling generation. It was trained with reinforcement learning on long-horizon coding tasks across many agent harnesses, and is suited for agentic coding, autonomous research, agentic knowledge work and retrieval-augmented generation, with English and general multilingual support. It accepts text and image input (no audio), supports tool calling and variable reasoning effort, and has a 1M-token context window.

Modalities

In / out price

$0.15 / $0.50per 1M

Context

1.0M

Released

Nov 9, 2026

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick: Balanced (price + speed), Nitro (fastest), or Floor (cheapest).

Latency / throughput


	$0.30	$1.00	$0.03	0.40s	186 tok/s	99.77%
	$0.30	$1.00	$0.03	0.42s	341 tok/s	99.68%
	$0.30	$1.00	$0.03	0.87s	206 tok/s	98.85%
5% off	$0.30$0.285	$1.00$0.95	$0.03$0.0285	0.90s	195 tok/s	98.67%
	$0.15	$0.50	$0.03	1.20s	117 tok/s	99.25%
	$0.30	$1.00	$0.06	0.82s	71 tok/s	97.21%

Input $0.30Output $1.00
186 tok/s99.77% uptime
Input $0.30Output $1.00
341 tok/s99.68% uptime
Input $0.30Output $1.00
206 tok/s98.85% uptime
Input $0.285Output $0.95
5% off
195 tok/s98.67% uptime
Input $0.15Output $0.50
117 tok/s99.25% uptime
Input $0.30Output $1.00
71 tok/s97.21% uptime

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Weighted average

Input

$0.04524/M tokens

Output

$0.8628/M tokens

Inkling 2 Small — Price history

Price history

No effective price data for this selection

$0.0356	$0.500	95.3%	17.7%
$0.0456	$0.950	93.3%	7.8%
$0.0463	$1.000	94.0%	59.2%
$0.0474	$1.000	93.6%	3.1%
$0.0497	$1.000	92.7%	10.4%
$0.0725	$1.000	94.8%	1.8%

Effective in $0.0356Effective out $0.500
Token share
17.7%
Effective in $0.0456Effective out $0.950
Token share
7.8%
Effective in $0.0463Effective out $1.000
Token share
59.2%
Effective in $0.0474Effective out $1.000
Token share
3.1%
Effective in $0.0497Effective out $1.000
Token share
10.4%
Effective in $0.0725Effective out $1.000
Token share
1.8%

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Throughput

341tok/s

P50, best across providers

Latency

0.40s

P50, best provider

Reasoning effortLatency / throughput

AutoExacto benchmarks

GPQA DiamondTAU-BenchDeepInfra90.2%70.7%Nebius Token Factory91.4%65.3%Together91.4%64.0%Prime Intellect91.1%63.3%Modal90.9%63.3%

+1 more providers

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Uptime (3d)

99.99%

Availability (3d)

99.48%

Availability over the last 3 days

Last 72 hours

Availability 99.48%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

99.77%

Without Routing

98.53%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

Benchmarks

Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.

Benchmark score summary for Thinking Machines: Inkling 2 Small (Artificial Analysis and Vals AI)
Source	Benchmark	Score
Artificial Analysis	Inkling 2 Small Intelligence Index	30.6
Artificial Analysis	Inkling 2 Small HLE	44.1%
Artificial Analysis	Inkling 2 Small AA-LCR	83.3%
Artificial Analysis	Inkling 2 Small GDPval-AA	56.5%
Artificial Analysis	Inkling 2 Small SciCode	52.3%
Artificial Analysis	Inkling 2 Small AA-Omniscience Accuracy	33.8%
Artificial Analysis	Inkling 2 Small AA-Omniscience Non-Hallucination Rate	73.3%
Vals AI	Inkling 2 Small BioMysteryBench	70.0%
Vals AI	Inkling 2 Small CyberBench v1.1	72.7%
Vals AI	Inkling 2 Small EMB v1.1	69.5%
Vals AI	Inkling 2 Small Finance Agent v2.1	67.5%
Vals AI	Inkling 2 Small Vals Finance Index	61.5%
Vals AI	Inkling 2 Small HLAB-Vals-1.1	21.7%
Vals AI	Inkling 2 Small Vals Legal Index	73.9%
Vals AI	Inkling 2 Small Legal Research Bench	46.6%
Vals AI	Inkling 2 Small MysteryMechanism	25.2%
Vals AI	Inkling 2 Small ProgramBench	0.5%
Vals AI	Inkling 2 Small SAGE	88.6%
Vals AI	Inkling 2 Small Vals Science Index	32.7%
Vals AI	Inkling 2 Small SRE Bench	1.9%
Vals AI	Inkling 2 Small SWE-bench Multimodal	43.1%
Vals AI	Inkling 2 Small Tax Agent Bench	38.9%
Vals AI	Inkling 2 Small Terminal-Bench 4.0	12.6%
Vals AI	Inkling 2 Small Terminal-Bench-Science	2.9%
Vals AI	Inkling 2 Small Vals Index	56.1%
Vals AI	Inkling 2 Small Vibe Code Bench v1.1	81.5%

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Claude Code

Claude Code is Anthropic's agentic coding tool that reads your entire codebase, plans and executes changes across files, runs tests, and iterates on failures, all from natural language prompts.

5.18Btokens

omp

new

2.42Btokens

OpenHands

AI coding agent that can run commands, browse the web, call APIs

2.24Btokens

Hermes Agent

Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.

699Mtokens

There are many coding agents, but this one is yours.

505Mtokens

Rest of OpenRouter

7.59B

Top 5 Apps

5.84B

Not currently available through EU in-region routing. In-region routing docs

More models from thinkingmachines

Inkling 2 Small (free)

Text1.0M contextFree

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.

Text524K context$0.45 / $1.20

Inkling Small (batch)

Text524K context$0.36 / $0.96

Inkling

Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems, retrieval-augmented generation, instruction following, and multilingual conversational applications. Its native image and audio understanding supports multimodal analysis alongside text.

Text524K context$1 / $4.05

Thinking Machines: Inkling 2 Small

Providers