mistralai
Inkling vs Mistral Large 4
43.9 overall · $1.05 / 1M
// thinkingmachines
Inkling
thinkingmachines/inkling
reasoningtool callingimage inputaudio inputprompt caching
Inkling costs $1.00 per 1M input tokens and $4.05 per 1M output tokens with a 524K-token context window.
A reasoning, tool-calling model from thinkingmachines, released Jul 17, 2026. On LiveBench it scores 47.0 overall — #26 of 28 benchmarked models — and ranks highest in data analysis (#19).
- Input / 1M
- $1.00
- Output / 1M
- $4.05
- Context
- 524K
- LiveBench overall
- 47.0 · #26
Specs and pricing
| Input price USD per 1M prompt tokens | $1.00 |
|---|---|
| Output price USD per 1M completion tokens, reasoning included | $4.05 |
| Blended price 3:1 input:output — #106 most expensive of 350 listed models | $1.76 |
| Cached input read Blank means not priced separately — not free | $0.170 |
| Cache write | — |
| Context window | 524,288 tokens |
| Max output | 471,859 tokens |
| Input modalities | text, image, audio |
| Tool calling | Yes |
| Extended reasoning | Yes |
| Knowledge cutoff | — |
| Listed | Jul 17, 2026 |
Benchmarks by category
LiveBench scores out of 100, with Inkling's rank among the 28 benchmarked models listed here. Run: inkling.
What Inkling costs to run
Monthly list cost across five workload shapes, using the published cached-input rate where there is one. A floor, not a quote — batch discounts and cache writes aren't included.
| Workload | Per month |
|---|---|
| Support chatbot 1.2K in / 400 out × 200K requests | $504.24/mo |
| RAG assistant 8K in / 600 out × 100K requests | $711.00/mo |
| Coding agent 40K in / 4K out × 20K requests | $659.20/mo |
| Document extraction 20K in / 1.5K out × 50K requests | $1,262/mo |
| Bulk classification 500 in / 20 out × 5M requests | $2,490/mo |
Compare Inkling with
The benchmarked models closest to it on overall score.
nvidia
Inkling vs Nemotron 3.5 Super VL
50.2 overall · $0.237 / 1M
meta
Inkling vs Muse Spark Open
51.6 overall · $2.00 / 1M
Inkling vs Gemma 4 31B
38.7 overall · $0.250 / 1M
qwen
Inkling vs Qwen3.8 27B
58.4 overall · $0.581 / 1M
stepfun
Inkling vs Step 5 Preview
58.6 overall · $1.43 / 1M
Inkling FAQ
How much does Inkling cost?
Inkling lists at $1.00 per 1M input tokens and $4.05 per 1M output tokens, with cached input reads at $0.170 per 1M. A RAG assistant handling 100K requests a month (8K tokens in, 600 out) comes to about $711.00 at list price.
What is the context window of Inkling?
Inkling accepts up to 524,288 tokens of context and can return up to 471,859 output tokens per response.
Does Inkling support tool calling?
Yes — Inkling supports tool (function) calling and exposes extended reasoning. It accepts text, image, audio input.
How does Inkling score on benchmarks?
On LiveBench release 2026-10-25 (run: inkling), Inkling scores 47.0 overall, ranking #26 of 28 benchmarked models.
What is the API model ID for Inkling?
On OpenRouter the model ID is "thinkingmachines/inkling". It was listed on Jul 17, 2026.
More from thinkingmachines
How these numbers are produced
- Price and specs — provider list data from OpenRouter, refreshed every 15 minutes. “Blended” is a 3:1 input:output mix.
- Scores and ranks — LiveBench release 2026-10-25. Ranks count only models that have a published run; a blank means “not evaluated”, never “bad”.
- Cost per point — the measured dollars LiveBench spent on the run, divided by the score it earned.
Published benchmarks rank models on someone else's tasks. Before committing, see LLM & agent evaluation for building an eval on your own.