---
title: "Thinking Machines: Inkling 2 Small — price, capability and what beats it · Undominated.ai"
canonical: https://undominated.ai/models/thinkingmachines__inkling-2-small/
description: "Thinking Machines: Inkling 2 Small: $0.300/M in, $1.00/M out. Independent capability scores, and alternatives compared under recorded workload and capability requirements."
---

# Thinking Machines: Inkling 2 Small — price, capability and what beats it · Undominated.ai

> Thinking Machines: Inkling 2 Small: $0.300/M in, $1.00/M out. Independent capability scores, and alternatives compared under recorded workload and capability requirements.

[Check base rates for this workload](/check/thinkingmachines__inkling-2-small/) [Cheaper alternatives](/alternatives/thinkingmachines__inkling-2-small/) [Family](/families/) [Compare models](https://undominated.ai/compare/?models=thinkingmachines%2Finkling-2-small) Comparison context

Choose up to three standard models in Compare.

Requirements and prompt length apply in Compare. This page keeps its stated price basis and workload controls.

MODEL PROOF

# Inkling 2 Small

Thinking Machines · 09 Nov 2026

 Balanced Summarise Chat Code gen Agentic

TRADE-OFF

## A stored alternative has an equal-or-higher score and an equal-or-lower price, with capability losses.

 **$0.475** / 1M tokens Balanced · 3 tokens in per 1 out

deal-only price: No offer passes the like-for-like test, so this price is a fallback: precision not disclosed. · precision not disclosed: The seller whose offer sets this price does not declare its serving precision. It is not read as full precision. · Serving precision differs between offers.

[GLM 5.3 Flash](/models/z-ai__glm-5.3-flash/) · Δ score 68.8 points · 69% lower measured price

 - 944K → 131K max output

Evidence as of 22 Nov 2026

 [openrouter/models](https://openrouter.ai/api/v1/models) [LMArena · cc-by-4.0](https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset) Independent LMArena score 1,402.6 ± 11.69 · 2,678 votes
 Context window 1.05M
 Maximum output 943.72K
 Input modalities text, image
 Output modalities text
 Published input price $0.300 / 1M tokens
 Published output price $1.00 / 1M tokens
 Pricing kind fixed

Inspect [complete billing conditions](#billing-details) and endpoint terms below.

Price from Cloudflare: no serving offer passes the like-for-like test, so this is a fallback. deal-only price precision not disclosed The seller whose offer sets this price does not declare its serving precision. It is not read as full precision.

Cheaper right now: $0.238/M at PrimeIntellect — 4-bit It does not pass the like-for-like test, so it never sets a rank.

 Every price dimension · USD per million tokens

| Input | $0.300 /M |
| --- | --- |
| Output | $1.00 /M |
| Cached input | $0.030 /M |
| Cache write | Unknown /M |
| Cache write 1h | Unknown /M |
| Reasoning | Unknown /M |

### Who sells it

The same weights, different shops. Cheapest is not like-for-like when serving precision differs.

Headline cheapest is a lower precision. Like-for-like at the best declared precision is $0.150/M from PrimeIntellect.

 6 provider offers · rates, limits and conditions

Rates are USD per million tokens. Endpoint terms can differ even when the quoted price and precision match. A listed parameter is a provider declaration, not a task-success test.

| Seller | Input | Output | Precision | Uptime (1d) |
| --- | --- | --- | --- | --- |
| Seller PrimeIntellect primeintellect/fp4 Endpoint terms Cached input /M $0.030 Context limit 1,048,576 tokens Output limit 943,718 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 100.00% | Input $0.150 | Output $0.500 | Precision fp4 | Uptime (1d) 100.00% |
| Seller DeepInfra deepinfra/fp4 Endpoint terms Cached input /M $0.029 Context limit 1,048,576 tokens Output limit 943,718 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount 5% · already included in these rates Uptime · last 30 minutes 100.00% | Input $0.285 | Output $0.950 | Precision fp4 | Uptime (1d) 100.00% |
| Seller Nebius nebius/fp4 Endpoint terms Cached input /M $0.060 Context limit 1,048,576 tokens Output limit 943,718 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 100.00% | Input $0.300 | Output $1.00 | Precision fp4 | Uptime (1d) 99.14% |
| Seller Modal modal/nvfp4 Endpoint terms Cached input /M $0.030 Context limit 1,048,576 tokens Output limit 131,072 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 100.00% | Input $0.300 | Output $1.00 | Precision nvfp4 | Uptime (1d) 100.00% |
| Seller Together together Endpoint terms Cached input /M $0.030 Context limit 1,048,576 tokens Output limit 943,718 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 100.00% | Input $0.300 | Output $1.00 | Precision undeclared | Uptime (1d) 99.91% |
| Seller Cloudflare cloudflare Endpoint terms Cached input /M $0.030 Context limit 1,048,576 tokens Output limit 943,718 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 100.00% | Input $0.300 | Output $1.00 | Precision undeclared | Uptime (1d) 100.00% |

### Independent scores

| LMArena Elo | 1402.6 default |
| --- | --- |
| LMArena row | Inkling 2 Small |

LMArena Elo under CC BY 4.0. Absence of another board is not a score of zero.

### Capability

| Context window | 1M |
| --- | --- |
| Max output | 943K |
| Input modes | text, image |
| Tool use | yes |
| Reasoning | always on |
| Open weights | Unknown |

### Provenance

| Price source | [openrouter.ai](https://openrouter.ai/api/v1/models) |
| --- | --- |
| Fetched | 2026-11-22 |
| Quality data | verified |

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...

## Questions this page answers

 What does Inkling 2 Small cost?

$0.300/M in, $1.00/M out in this catalogue, as of the fetch date on this page. That is the API row, not a subscription.

 Does Inkling 2 Small have an independent quality score?

Inkling 2 Small has an LMArena score in this catalogue.

 What beats Inkling 2 Small?

GLM 5.3 Flash has an equal-or-higher measured score and an equal-or-lower price, with capability trade-offs.

 Does this page use Artificial Analysis scores for Inkling 2 Small?

No. Artificial Analysis figures are not published here. Quality on this page is LMArena Elo where a score exists; otherwise the row is unrated.

 Is the cheapest Inkling 2 Small endpoint the same product?

Headline cheapest is a lower precision. Like-for-like at the best declared precision is $0.150/M from PrimeIntellect.

MODEL MONUMENT

## Save or share this proof

 Download proof card · 1200 × 630 Preview and more sharing options

Thinking Machines: Inkling 2 Small. Balanced workload. Alternative has a trade-off. Evidence as of 22 Nov 2026.

 Copy model link Download square card · 1080 × 1080 Copy landscape image Share landscape card

## Related

 - Higher score or lower price, with a named trade [GLM 5.3 Flash](/models/z-ai__glm-5.3-flash/)
- Nearby on the capability axis [MiniMax M2.7](/models/minimax__minimax-m2.7/)
- Same vendor [Inkling Small](/models/thinkingmachines__inkling-small/)
- Thinking Machines models [Thinking Machines](/providers/thinking-machines/)
- Where this model appears [effort](/effort/)
- Nearby on the capability axis [Grok 4.7](/models/x-ai__grok-4.7/)
- Same vendor [Inkling](/models/thinkingmachines__inkling/)
- Where this model appears [spreads](/spreads/)
- Nearby on the capability axis [GPT-5](/models/openai__gpt-5/)
- Same vendor [Inkling 2 Mini](/models/thinkingmachines__inkling-2-mini/)
- Where this model appears [traps](/traps/)
- Where this model appears [significance](/significance/)

## Badge

The verdict as one SVG, for a README or a docs page. It states this model's dominance status at the balanced workload on the LMArena lens, with the date it was computed, and it is rebuilt with the catalogue — so it changes when the verdict changes, including to one you would rather it did not.

 Markdown Copy
 [![Inkling 2 Small — Undominated.ai dominance verdict](https://undominated.ai/badge/thinkingmachines__inkling-2-small.svg)](https://undominated.ai/models/thinkingmachines__inkling-2-small/)
 HTML Copy
 <a href="https://undominated.ai/models/thinkingmachines__inkling-2-small/"><img src="https://undominated.ai/badge/thinkingmachines__inkling-2-small.svg" alt="Inkling 2 Small — Undominated.ai dominance verdict" height="36"></a>

Direct file: [https://undominated.ai/badge/thinkingmachines__inkling-2-small.svg](https://undominated.ai/badge/thinkingmachines__inkling-2-small.svg) — a static SVG, written by scripts/build-badges.mjs on every build, so the copy you embed is never older than the last deploy.

## Continue your investigation

 - [Explore model families](/families/)
- [Compare a shortlist](/compare/)
- [Check a model](/check/)
- [Understand the evidence](/methodology/)
