// head_to_head
Qwen3.8 27B vs Inkling
Published LiveBench scores across all seven categories, live list pricing, context windows, and the measured cost of a point of capability — for both models, side by side.
Qwen3.8 27B is the cheaper of the two; neither can be ranked on quality here.
Neither model has a published LiveBench run, so this comparison covers price, context and declared capabilities only. A missing score means "not evaluated", not "worse" — the right way to separate these two is an eval on your own workload.
qwen
Qwen3.8 27B
- Blended / 1M
- $0.605
- Context
- 1M
- Released
- Aug 14, 2026
- Overall score
- Not evaluated
thinkingmachines
Inkling
- Blended / 1M
- $1.76
- Context
- 524K
- Released
- Jul 17, 2026
- Overall score
- Not evaluated
Specs and pricing
| Metric | Qwen3.8 27B | Inkling |
|---|---|---|
| LiveBench overall Mean of the seven LiveBench category scores, 0–100. Higher is better. | — | — |
| Cost per point Measured benchmark spend divided by overall score — dollars per point of capability. | — | — |
| Blended price / 1M 3:1 input:output mix, the usual shape of production traffic. | $0.605win | $1.76 |
| Input price / 1M | $0.040win | $1.00 |
| Output price / 1M | $2.30win | $4.05 |
| Cached input / 1M Price of an input token served from the prompt cache, where the provider publishes one. | $0.020win | $0.170 |
| Context window | 1Mwin | 524K |
| Max output tokens | 236K | 472Kwin |
What each one costs to run
Per-token prices are hard to feel. These are monthly list costs for both models across five workload shapes, using each provider's published cached-input rate where there is one.
| Workload | Qwen3.8 27B | Inkling |
|---|---|---|
| Support chatbot 1.2K in / 400 out × 200K requests | $192.15/mo | $504.24/mo |
| RAG assistant 8K in / 600 out × 100K requests | $161.92/mo | $711.00/mo |
| Coding agent 40K in / 4K out × 20K requests | $204.69/mo | $659.20/mo |
| Document extraction 20K in / 1.5K out × 50K requests | $211.49/mo | $1,262/mo |
| Bulk classification 500 in / 20 out × 5M requests | $319.90/mo | $2,490/mo |
Which should you pick?
You need to fit large documents in one call
Qwen3.8 27B
Wider context window — 1M against 524K.
Qwen3.8 27B vs Inkling FAQ
Which is better, Qwen3.8 27B or Inkling?
Qwen3.8 27B is the cheaper of the two; neither can be ranked on quality here. Neither model has a published LiveBench run, so this comparison covers price, context and declared capabilities only. A missing score means "not evaluated", not "worse" — the right way to separate these two is an eval on your own workload.
Is Qwen3.8 27B cheaper than Inkling?
Qwen3.8 27B is cheaper. On a 3:1 input:output blend, Qwen3.8 27B lists at $0.605 per million tokens and Inkling at $1.76 — Qwen3.8 27B is 2.9× cheaper. Input and output are priced separately — Qwen3.8 27B charges $0.040 in and $2.30 out, Inkling charges $1.00 and $4.05 — so the model that looks cheaper flips depending on how output-heavy your workload is.
Does Qwen3.8 27B or Inkling have a bigger context window?
Qwen3.8 27B has the larger context window: 1M for Qwen3.8 27B against 524K for Inkling. Note that a window you can fill is not a window you should fill — retrieval quality usually degrades well before the limit, and you pay for every token you put in it.
Do Qwen3.8 27B and Inkling support prompt caching?
Both publish a cached-input rate: $0.020 per million for Qwen3.8 27B and $0.170 for Inkling, against full input rates of $0.040 and $1.00. On a workload with a long stable prefix — a system prompt, a tool schema, a retrieved corpus — that changes the economics more than the headline price does.
Related comparisons
How these numbers are produced
- Price — provider list price from OpenRouter, refreshed every 15 minutes. “Blended” is a 3:1 input:output mix.
- Scores — LiveBench release 2026-09-02, using their own category map. Each model shows its strongest 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.
- “Win” — awarded only past a threshold: one full point on a benchmark score, 10% on a price, 25% on a context window. Anything tighter reports as a tie, because effort settings alone move a LiveBench score by more than that.
Published benchmarks rank models on someone else's tasks. Before committing, see LLM & agent evaluation for building an eval on your own.