// head_to_head
GPT-6.1 Sol 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.
GPT-6.1 Sol scores higher, Inkling costs less — it depends on your workload.
GPT-6.1 Sol is ahead by 9.7 points overall, and Inkling lists 2.3× cheaper per blended million tokens. Whether 9.7 points is worth that depends on how much a wrong answer costs you. The two cost measures disagree here, which is worth knowing: Inkling has the lower sticker price, but GPT-6.1 Sol earns each point of capability for less — $0.0755 against $0.1766 — because per-token rates do not predict how many tokens a model actually spends on a task.
openai
GPT-6.1 Sol
- Blended / 1M
- $4.00
- Context
- 1.1M
- Released
- Sep 29, 2026
- Overall score
- 81.6
thinkingmachines
Inkling
- Blended / 1M
- $1.76
- Context
- 524K
- Released
- Jul 17, 2026
- Overall score
- 71.9
Specs and pricing
| Metric | GPT-6.1 Sol | Inkling |
|---|---|---|
| LiveBench overall Mean of the seven LiveBench category scores, 0–100. Higher is better. | 81.6win | 71.9 |
| Cost per point Measured benchmark spend divided by overall score — dollars per point of capability. | $0.0755win | $0.1766 |
| Blended price / 1M 3:1 input:output mix, the usual shape of production traffic. | $4.00 | $1.76win |
| Input price / 1M | $2.00 | $1.00win |
| Output price / 1M | $10.00 | $4.05win |
| Cached input / 1M Price of an input token served from the prompt cache, where the provider publishes one. | $0.100win | $0.170 |
| Context window | 1.1Mwin | 524K |
| Max output tokens | 128K | 472Kwin |
Benchmarks by category
An overall score averages away the thing you probably care about. These are the seven LiveBench categories scored separately — GPT-6.1 Sol on top, Inkling below, both out of 100.
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 | GPT-6.1 Sol | Inkling |
|---|---|---|
| Support chatbot 1.2K in / 400 out × 200K requests | $1,143/mo | $504.24/mo |
| RAG assistant 8K in / 600 out × 100K requests | $1,440/mo | $711.00/mo |
| Coding agent 40K in / 4K out × 20K requests | $1,336/mo | $659.20/mo |
| Document extraction 20K in / 1.5K out × 50K requests | $2,655/mo | $1,262/mo |
| Bulk classification 500 in / 20 out × 5M requests | $5,050/mo | $2,490/mo |
Which should you pick?
You are running this at volume
GPT-6.1 Sol
Lowest measured cost per point of capability at $0.0755 per point — the gap compounds with every request.
Quality matters more than the bill
GPT-6.1 Sol
Highest overall LiveBench score of the two at 81.6.
The workload is coding or agentic work
GPT-6.1 Sol
Leads on agentic coding — 54.5 against 49.4.
You need to fit large documents in one call
GPT-6.1 Sol
Wider context window — 1.1M against 524K.
You are cost-constrained
Inkling
Cheaper on blended list price at $1.76 per million tokens.
GPT-6.1 Sol vs Inkling FAQ
Which is better, GPT-6.1 Sol or Inkling?
GPT-6.1 Sol scores higher, Inkling costs less — it depends on your workload. GPT-6.1 Sol is ahead by 9.7 points overall, and Inkling lists 2.3× cheaper per blended million tokens. Whether 9.7 points is worth that depends on how much a wrong answer costs you. The two cost measures disagree here, which is worth knowing: Inkling has the lower sticker price, but GPT-6.1 Sol earns each point of capability for less — $0.0755 against $0.1766 — because per-token rates do not predict how many tokens a model actually spends on a task.
Is GPT-6.1 Sol cheaper than Inkling?
Inkling is cheaper. On a 3:1 input:output blend, GPT-6.1 Sol lists at $4.00 per million tokens and Inkling at $1.76 — Inkling is 2.3× cheaper. Input and output are priced separately — GPT-6.1 Sol charges $2.00 in and $10.00 out, Inkling charges $1.00 and $4.05 — so the model that looks cheaper flips depending on how output-heavy your workload is.
GPT-6.1 Sol vs Inkling: which scores higher on benchmarks?
GPT-6.1 Sol scores 81.6 and Inkling scores 71.9 overall on LiveBench, the mean of its seven categories. That is a 9.7-point lead for GPT-6.1 Sol. Category scores differ from the overall figure — a model can lead on reasoning and trail on coding, which the per-category table above breaks out.
Which gives better value for money, GPT-6.1 Sol or Inkling?
GPT-6.1 Sol. Cost per point divides the measured dollars LiveBench spent running the benchmark by the score it earned, so it captures something token pricing misses: a reasoning model can emit many times more tokens than its per-token rate suggests. GPT-6.1 Sol works out at $0.0755 per point and Inkling at $0.1766.
Does GPT-6.1 Sol or Inkling have a bigger context window?
GPT-6.1 Sol has the larger context window: 1.1M for GPT-6.1 Sol 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 GPT-6.1 Sol and Inkling support prompt caching?
Both publish a cached-input rate: $0.100 per million for GPT-6.1 Sol and $0.170 for Inkling, against full input rates of $2.00 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 2026-06-25, 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.