Inkling 2 Mini
Launch tracker · day 2
Inkling 2 Mini at launch: the first independent results
As of 21 Nov 2026, Inkling 2 Mini (Thinking Machines, released 20 Nov 2026) has independent results from Artificial Analysis (AA Intelligence Index v5.0.1 20.1) and ARC Prize (ARC-AGI-2 49.3%). It has no BenchLeader Index yet: the Index needs at least five independent results across two categories. It is listed at $0.15 in / $0.50 out per 1M tokens, with a 1M-token context window. Not yet measured by LMArena, Epoch AI, Vals AI, LiveBench, Scale AI and SWE-bench.
- Released
- 20 Nov 2026 (day 2)
- Provider
- Thinking Machines
- Price
- $0.15 in / $0.50 out per 1M tokens
- Context window
- 1M tokens
- Open weights
- Yes: thinkingmachines/Inkling-2-Mini
- BenchLeader Index
- Not yet (needs five results in two categories)
| Independent board | Results so far |
|---|---|
| Artificial Analysis | AA Intelligence Index v5.0.1 20.1 · AA-Omniscience v1.1 -8.6 · HLE-Diamond (AA) 15.2% · more below |
| ARC Prize | ARC-AGI-2 49.3% · ARC-AGI-1 84.5% |
Boards usually post results within days of a launch; this page is rebuilt every three hours.
Launch comparisons
Scores from independent publishers only; benchmark figures a provider publishes about its own model are not shown.
Good value at this level: no ranked model within 2 Index points costs three quarters of the price or less.
No cheaper ranked model scores higher: it is on the price frontier.
As of 21 Nov 2026, Inkling 2 Mini by Thinking Machines is not yet ranked on the BenchLeader Index, which needs at least five independent results across two categories. API pricing: $0.150 per 1M input tokens and $0.500 per 1M output tokens ($0.238 blended at 3:1), list price on 21 Nov 2026. It streams about 280 tokens/s (Artificial Analysis). Released 20 Nov 2026.
Key facts (as of 21 Nov 2026)
- Inkling 2 Mini API pricing: $0.150 per 1M input tokens and $0.500 per 1M output tokens ($0.238 blended at 3:1) (list price, 21 Nov 2026).
- Inkling 2 Mini streams about 280 tokens/s (Artificial Analysis, 21 Nov 2026).
- Inkling 2 Mini was released on 20 Nov 2026 (Thinking Machines).
In detail. Inkling 2 Mini is a Thinking Machines open-weights reasoning model, released 20 Nov 2026. It is not yet ranked: the index needs at least five independent results across two categories. At $0.238 per million tokens blended it is cheaper than most ranked models. Output speed of 280 tokens per second puts it in the fastest quarter, with a first answer in 9.7 s. It has been measured at 2 reasoning-effort settings; this summary describes the best-scoring one, and the tabs above switch between them. Last measured 20 Nov 2026.
- Blended price
- $0.238/M
- $0.150 in · $0.500 out
- via Artificial Analysis
- Output speed
- 280 tok/s
- measured by Artificial Analysis
- First answer
- 9.72 s
- first token 0.66 s
- Context
- 1.0M
- via OpenRouter
- Accepts
- Text · Images
- via models.dev, OpenRouter
- Cost per task
- $0.587
- 9 min a task, AA Index
- Tokens per task
- 152k
- 61% of it reasoning
- Released
- 20 Nov 2026
- Reasoning40
- Coding44
- Knowledge41
Versions
Thinking Machines has shipped 2 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.
| Model | Released | Index | Rank |
|---|---|---|---|
| NewInkling 2 Minithis page | 20 Nov 2026 | – | – |
| NewInkling Mini 1117 | – | – | – |
Reasoning-effort configurations
The same model behaves differently depending on how much it is allowed to think. Each row is one setting, scored only on the benchmarks that were run at that setting. “Not stated” collects results from publishers that did not say which setting they used; for a reasoning model that is usually its thinking mode, but we do not assume it. Pick a setting here or at the top of the page to see its price, speed and category scores.
| Effort | Index | Rank | Speed | First answer | Chat reply cost | Categories |
|---|---|---|---|---|---|---|
| xhigh | – | – | 280 tok/s | 9.72 s | $0.0002 | Reasoning 55 |
| not statedbest | – | – | 280 tok/s | 9.72 s | $0.0002 | Coding 44 · Knowledge 41 · Reasoning 40 |
Benchmark results
See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | xhigh | not stated | Source |
|---|---|---|---|
| HLE-Diamond (AA)effort not stated | – | 15.2%#116 | Artificial Analysis |
| ARC-AGI-1 | 84.5%#136 | – | ARC Prize |
| ARC-AGI-2 | 49.3%#132 | – | ARC Prize |
| CritPt v2 hard subset (AA)effort not stated | – | 17.0%#118 | Artificial Analysis |
Coding
| Benchmark | not stated | Source |
|---|---|---|
| Terminal-Bench 4.0 (AA)not in index | 5.6%#149 | Artificial Analysis |
| FrontierCode 2.0 (AA) | 15.1%#100 | Artificial Analysis |
Agents & tools
| Benchmark | not stated | Source |
|---|---|---|
| GDPval-AA v2.1not in index | 1319#118 | Artificial Analysis |
| Analyst Agent (AA)not in index | 46.3%#25 | Artificial Analysis |
| AutomationBenchnot in index | 41.8%#144 | Artificial Analysis |
| GDP.pdf (AA)not in index | 16.8%#132 | Artificial Analysis |
| EnterpriseOps-Gymnot in index | 42.0%#27 | Artificial Analysis |
| AA-Briefcase v1.1not in index | 1263#121 | Artificial Analysis |
| Terminal-Bench-Science 0.1 (AA)not in index | 1.4%#120 | Artificial Analysis |
Knowledge
| Benchmark | not stated | Source |
|---|---|---|
| AA-Omniscience v1.1 | -8.6#122 | Artificial Analysis |
| AA-Omniscience v1.1: accuracynot in index | 20.5%#141 | Artificial Analysis |
| AA-Omniscience v1.1: non-hallucinationnot in index | 63.4%#59 | Artificial Analysis |
Multimodal
| Benchmark | not stated | Source |
|---|---|---|
| Code2Video-AAnot in index | 870#24 | Artificial Analysis |
Composite
| Benchmark | not stated | Source |
|---|---|---|
| AA Intelligence Index v5.0.1not in index | 20.1#109 | Artificial Analysis |
API pricing: where to run it
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| io.net | 114 tok/s | 0.58 s | $0.080 | $0.350 | 262k | nvfp4 |
| Prime Intellect | 102 tok/s | 0.66 s | $0.075 | $0.300 | 1.0M | fp4 |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache at $0.015 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0002 | $0.0002 | 10.8 s |
| Summarize a 30-page report | 12,000 / 600 | $0.0021 | $0.0009 | 11.9 s |
| Code edit | 6,000 / 1,500 | $0.0017 | $0.0010 | 15.1 s |
| Agentic coding session | 60,000 / 4,000 | $0.011 | $0.0049 | 24.0 s |
| Structured extraction | 2,000 / 200 | $0.0004 | $0.0002 | 10.4 s |
More from Thinking Machines
Compare Inkling 2 Mini with…
See also
Questions people ask
- Why does Inkling 2 Mini have no BenchLeader Index score?
- The index needs at least five independent results across at least two categories, and as of 21 Nov 2026 Inkling 2 Mini does not have them yet. Launch-post scores are never used, so it is ranked once independent publishers have measured it.
- How much does Inkling 2 Mini cost per 1M tokens?
- As of 21 Nov 2026, Inkling 2 Mini costs $0.150 per 1M input tokens and $0.500 per 1M output tokens, $0.238 blended (three input tokens per output token).
- Is Inkling 2 Mini better than Inkling 2 Small?
- As of 21 Nov 2026, only one of these has enough independent results to rank; on price, Inkling 2 Mini is 2.0× cheaper. The head-to-head page has the benchmark-by-benchmark detail.
- When was Inkling 2 Mini released?
- Thinking Machines released Inkling 2 Mini on 20 Nov 2026. BenchLeader has results for it at 2 reasoning-effort settings.
Data as of 21 Nov 2026. Compare these configurations.
Cite as: BenchLeader, “Inkling 2 Mini: benchmarks, pricing, speed and rank”, data as of 21 Nov 2026, https://www.benchleader.com/models/inkling-2-mini.