Model index · Text · text generation · reasoning · open weights · Thinking Machines · released 2026-07-17
Inkling pricing
Served by 5 providers from $1.73 to $1.76 per 1M tokens on the standard tier.
A reasoning model — the headline price is not the whole bill
This model thinks before it answers, and those thinking tokens are billed at the output rate while never appearing in the response. A request can therefore cost several times what the per-1M figure suggests, and the multiplier depends on your prompts rather than on anything we can publish. Compare it against other reasoning models — the alternatives below are ordered to put those first.
Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...
Thinking Machines · 952.38B parameters · apache-2.0 · first published 2026-07-17 · Text model · text generation · 1.05M context · description as published by the source, not written by us
Open weights: thinkingmachines/Inkling · 952.38B parameters counted from the weight files · licence apache-2.0 · 0.1M downloads in the last 30 days . Parameter count and licence come from the public weights registry, not from a seller — and the download figure exists only for models published this way, so it is not a market-wide popularity measure.
$1.73
Cheapest standard /1M — OpenRouter (default route)
1.05M
Native context window
6
Providers serving it
—
Quality not measured yet
Quality not measured yet
We measure models on request rather than pre-scoring the whole catalog, so this one has no score yet. Absence of a score is not a low score.
At 1M requests/month (1500 in / 500 out tokens), moving from Together to DeepInfra saves about $75/month.
Illustrative traffic shape, stated so you can check it against your own. Same weights both sides — but confirm quantisation and context below before switching.
Every provider and service tier
Standard on-demand rows first, cheapest of each group first. Tiers are not interchangeable — see the note below the table.
| Provider | In /1M | Out /1M | Blended /1M | Tier | Region | Source |
|---|---|---|---|---|---|---|
| DeepInfra cheapest standard | $0.9500 | $4.05 | $1.73 | standard | — | third_party |
| OpenRouter (default route) * resells other hosts | $0.9500 | $4.05 | $1.73 | standard | — | provider_api |
| DeepInfra | $0.9500 | $4.05 | $1.73 | standard | — | provider_api |
| BaseTen | $1.00 | $4.05 | $1.76 | standard | — | third_party |
| Together | $1.00 | $4.05 | $1.76 | standard | — | third_party |
| OpenRouter (default route) * resells other hosts | $0.5000 | $2.02 | $0.8813 | batch | — | provider_api |
Not every row is the same product
This table mixes service tiers, and they are not interchangeable. Rows marked standard are ordinary on-demand requests. The others trade delivery for price:
- batch — submitted as a batch and collected later, typically within 24 hours — not for interactive use
Every comparison elsewhere on this site uses the standard tier, so a model is never shown at a queued rate beside another model's on-demand rate.
Cheaper if your workload can wait: batch at $0.8812 per 1M on OpenRouter — 49% below standard , submitted as a batch and collected later, typically within 24 hours — not for interactive use.
* OpenRouter chooses a host for each request, and the figure above is what its default choice costs — not a fixed rate for this model. Selecting a specific host through the same account costs whatever that host charges, which is why this row can sit above or below the hosts listed beside it. Token rates are passed through from the underlying provider with no markup, so the per-1M price above is what that host charges directly — OpenRouter's own charge sits on funding instead: 5.5% (min $0.80) by Stripe or 5% by Coinbase to buy credits, 5% of the equivalent spend if you bring your own provider key. So budget about 5% above the rate shown unless you already hold credit. Fee schedule.
Compare Inkling with alternatives
One model per vendor, ordered by how prominent the vendor is and how many independent providers serve the model — hosts only carry what customers ask for, so that is a real demand signal. This is not traffic or popularity data, which we do not have. Every alternative below does the same job — text generation — because a price comparison between a generator and, say, an upscaler is arithmetic rather than advice. Prices on both sides are standard on-demand rates, so the comparison is like for like — a discounted batch or flex rate is never shown against another model’s standard rate.
| Alternative | Vendor | $/1M | vs Inkling | Quality | Kind | Context | Hosts |
|---|---|---|---|---|---|---|---|
| DeepSeek V3.2 | DeepSeek | $0.2413 StreamLake | 86% cheaper | 60/100 | reasoning open weights | 164k | 16 |
| Claude Haiku 4.5 | Anthropic | $2.00 Anthropic | 16% dearer | 60/100 | reasoning | 200k | 8 |
| GPT-5.1 | OpenAI | $1.72 OpenAI | 0% cheaper | 80/100 | reasoning | 400k | 5 |
| Qwen3 Max | Alibaba | $1.56 Alibaba | 10% cheaper | 100/100 | reasoning | 262k | 3 |
| Kimi K2.5 | MoonshotAI | $0.7875 DigitalOcean | 54% cheaper | 75/100 | reasoning open weights | 262k | 14 |
| Grok 4.3 | xAI | $1.56 xAI | 9% cheaper | 100/100 | reasoning | 1M | 4 |
| Mistral Medium 3.5 | Mistral | $3.00 Mistral | 74% dearer | not measured | reasoning | 262k | 1 |
| GLM 5.1 | Z.ai | $1.48 StreamLake | 14% cheaper | not measured | reasoning open weights | 205k | 18 |
Prices are the cheapest host for each model, blended at a 3:1 input:output ratio. "Quality" is our own probe suite where we have run it — see what it measures. A cheaper alternative is only a real saving if it also passes on the capability your workload needs.
6 of these alternatives cost less than Inkling — the cheapest being DeepSeek V3.2 at $0.2413 per 1M tokens blended (86% cheaper).
Cheaper is not automatically better: check the quality column, and confirm the context window and capabilities your workload depends on before switching.
Before you switch
Identical weights do not guarantee identical output. Check that the cheaper host serves the model at full precision rather than a quantised copy, that its context window matches what you need, and that its rate limits carry your peak traffic. A cheaper host that cannot take your throughput is not cheaper — it is an outage.
Move to DeepInfra without a rewrite
VernaOne fronts every provider on this page with one API, so switching host is a config change — with automatic fallback if quality or latency regresses.
Try VernaOne free →Frequently asked
How much does Inkling cost?
The cheapest standard-tier provider is DeepInfra at $1.73 per 1M tokens blended (3:1 input:output). A batch tier is available at $0.8812, 49% less, if the work can be collected later. Prices change often; verify with the provider before budgeting.
Which provider is best for Inkling?
Cheapest is not automatically best. Compare quantisation (a lossy copy of the weights changes output), the context window each host actually serves, and rate limits. Where a provider serves less context than the model's native window we flag it in the table above.
Can I switch providers for Inkling without changing code?
Yes, if you route through an abstraction. VernaOne exposes one API across every provider listed here, so switching host is a config change and you keep automatic fallback if the new one degrades.
← All models · Generated catalog of AI models and every provider that serves them, with normalised prices in USD per 1,000,000 tokens. Blended prices assume a 3:1 input:output ratio.