Inkling 2 Small
Last verified November 7, 2026 · Thinking Machines pricing ↗$0.300/1M input · $1.00/1M output · 256K context · Thinking Machines
Inkling 2 Small costs $0.300 per 1M input tokens and $1.00 per 1M output tokens from Thinking Machines, with a 256K-token context window. A typical chat reply (1,500 tokens in, 400 out) costs $0.0008, or $8.50 per 10,000 requests. On that workload it is cheaper than 122 of the 168 other buyable models tracked here.
Count Tokens
—
Tokens
—
Input Cost
—
Output Cost
Estimate Monthly Cost
Monthly Cost Estimator
Quick:
<$0.0001/mo
Pick a preset above or enter custom usage
What Inkling 2 Small Costs Per Request
At $0.300 per 1M input and $1.00 per 1M output tokens, before caching or batch discounts.
| Workload | Input / output tokens | Per request | Per 10,000 requests |
|---|---|---|---|
| Chat reply | 1,500 / 400 | $0.0008 | $8.50 |
| RAG answer over retrieved docs | 8,000 / 600 | $0.0030 | $30.00 |
| Coding-agent step | 30,000 / 2,000 | $0.011 | $110.00 |
Inkling 2 Small vs Similarly Priced Models
Nearest buyable models by price, with the RAG answer above (8,000 in / 600 out) priced on each.
| Model | Input /1M | Output /1M | Context | RAG answer |
|---|---|---|---|---|
| Inkling 2 Small Thinking Machines | $0.300 | $1.00 | 256K | $0.0030 |
| MiMo-V2.6-Pro Xiaomi | $0.435 | $0.870 | 1.0M | $0.0040 |
| Qwen3-Next-80B-A3B-Thinking Alibaba | $0.150 | $1.20 | 262K | $0.0019 |
| Step 3.7 Flash StepFun | $0.200 | $1.15 | 262K | $0.0023 |
Alternatives to Inkling 2 Small
Pricing Details
Thinking MachinesLaunched November 5, 2026 on Tinker only. 594B total / 17B active. Text and image in, text out. CARD (Tinker pricing, read 2026-11-07): $0.30 input / $0.03 cached / $1.00 output on sampling and serverless; training $1.50 at 64K context, $3.00 at 256K. Serverless is a beta with a waitlist for production use. contextWindow is the 256K top tier Tinker sells; the model card says up to 1M. maxOutput 0 means no figure is published, and no API model ID was published as of 2026-11-07. WEIGHTS: Thinking Machines intends to release under Apache 2.0 'next week' after external safety testing; not public on 2026-11-07. Artificial Analysis Index v5.0.1 (read 2026-11-07): 30.63, $1.178 per task, of which cached reads $0.873 (about 29.09M tokens), cache writes $0.154, output $0.150 (149,778 tokens), 5.8x predecessor Inkling Small's $0.203. Other platforms promised 'in the coming weeks'.
Input / 1M tokens
$0.3
Output / 1M tokens
$1
Context Window
256K
Max Output
N/A
Price History
Launched at current price on 2026-11-05. No price changes recorded since.
Frequently Asked Questions
Common questions about Inkling 2 Small pricing and usage
How much does Inkling 2 Small cost?
Inkling 2 Small costs $0.3 per 1 million input tokens and $1 per 1 million output tokens. This pricing is set by Thinking Machines.
What tokenizer does Inkling 2 Small use?
Inkling 2 Small uses the cl100k_base tokenizer. This tokenizer has a vocabulary of ~100,000 tokens and is widely used across many models.
What is Inkling 2 Small's context window?
Inkling 2 Small supports a context window of 256K tokens (256,000 tokens).
How does Inkling 2 Small compare to other models?
On an 8,000-token-in, 600-token-out RAG answer, Inkling 2 Small costs $0.0030 per request. The nearest-priced alternatives cost: MiMo-V2.6-Pro (Xiaomi) $0.0040, Qwen3-Next-80B-A3B-Thinking (Alibaba) $0.0019, Step 3.7 Flash (StepFun) $0.0023. The table above lists their full rates and context windows.
How do I count tokens for Inkling 2 Small?
Use the token counter at the top of this page or visit the homepage calculator. Paste your text and it will show the exact token count and cost for Inkling 2 Small using the cl100k_base tokenizer.