Inkling with Jev
Inkling is a model from Thinking Machines, released 2026-07-17. It costs $1.00 per million input tokens and $4.05 per million output tokens, reads up to 524K tokens of context, and writes up to 471,859 tokens in one reply. Through llm11, set model to thinkingmachines/inkling.
- Input price
- $1.00 / 1M
- Output price
- $4.05 / 1M
- Context window
- 524K tokens
- Max output
- 472K tokens
- Cached input
- $0.170 / 1M
- Released
- 2026-07-17
- Accepts
- text, image, audio
- Intelligence index
- 25
Read from the provider's prompt cache
Artificial Analysis, via the catalogue
Read from the live catalogue and refreshed daily. At blended list price, 29% of the 332 priced models we can call cost more.
Using Inkling with Jev
Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. Inkling does the answering when Jev sends it work, or when you name it yourself. At list price Inkling falls in the llm11-balanced band, but no pack routes to it because it does not advertise structured output, which the verification checks rely on. You can still pin it: pass thinkingmachines/inkling as model and routing steps aside while verification still runs.
Jev is new, so we have not published results for Inkling with and without it, and this page does not invent any. Every response comes with a receipt that names the model that answered and what it cost against your most expensive model, so you can measure the pairing on your own traffic.
What a request costs
List price arithmetic, the same sum a receipt does. llm11 adds nothing per request; the only fee is on buying credits.
| Request | Tokens in / out | One | A thousand |
|---|---|---|---|
| Short chat turn | 500 / 200 | $0.00131 | $1.31 |
| Question over retrieved documents | 4,000 / 500 | $0.00602 | $6.03 |
| Long document summary | 30,000 / 1,000 | $0.034 | $34.05 |
Cheaper models to try
Nearest in price and below Inkling, each within a few points of it on the intelligence index.
| Model | Input / 1M | Output / 1M | Context | Index | Released |
|---|---|---|---|---|---|
| OpenAI GPT-5.4 Mini | $0.750 | $4.50 | 400K | 24.1 | |
| SpaceXAI Grok 4.3 | $1.25 | $2.50 | 1M | 24.9 | |
| Google Gemini 3.8 Flash | $0.750 | $3.75 | 1.05M | 40.9 | |
| Google Gemini 3.7 Flash | $0.750 | $3.75 | 1.05M | 39.1 |
Call it
Same OpenAI request shape. Naming the model pins it, so nothing is routed, and the answer is still checked.
python
from openai import OpenAI
client = OpenAI(base_url="https://www.llm11.com/v1", api_key="llm11_live_...")
res = client.chat.completions.create(
model="thinkingmachines/inkling",
messages=[{"role": "user", "content": "Hello"}],
)More from Thinking Machines
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Inkling Small | $0.450 | $1.20 | 524K |
Questions
- What is Inkling with Jev?
- Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. Inkling does the answering when Jev sends it work, or when you name it yourself. At list price Inkling falls in the llm11-balanced band, but no pack routes to it because it does not advertise structured output, which the verification checks rely on. You can still pin it: pass thinkingmachines/inkling as model and routing steps aside while verification still runs. Routing decisions are made by Jev, TypeSafe AI's System One model.
- Is Inkling a System One model?
- No. Inkling answers requests. The System One model is Jev, which decides which model answers each one, so the two do different jobs and llm11 uses both.
- How much does Inkling cost?
- $1.00 per million input tokens and $4.05 per million output tokens. A 4,000 token prompt with a 500 token answer costs about $0.00602, so a thousand of them is about $6.03. llm11 passes provider list price through and charges 5% when you buy credits.
- What is the Inkling context window?
- 524,288 tokens, with up to 471,859 tokens in a single reply.
- Does Inkling support tool calling and structured output?
- The catalogue lists tool calling and reasoning controls, but it does not list structured output.
- Can I use Inkling through llm11?
- Yes. Set model to thinkingmachines/inkling on the OpenAI-compatible endpoint and the request goes to it directly, with verification still running.
- Does Jev route to Inkling?
- Routing decisions are made by Jev, TypeSafe AI's System One model. At list price Inkling falls in the llm11-balanced band, but no pack routes to it because it does not advertise structured output, which the verification checks rely on. You can still pin it: pass thinkingmachines/inkling as model and routing steps aside while verification still runs.
- What is a cheaper alternative to Inkling?
- Nearest in price and below it: OpenAI GPT-5.4 Mini at $0.750 in and $4.50 out, SpaceXAI Grok 4.3 at $1.25 in and $2.50 out and Google Gemini 3.8 Flash at $0.750 in and $3.75 out. Nearest in price and below Inkling, each within a few points of it on the intelligence index.