Best models

Best free AI models

Every model in the live reference catalogue with a zero list price, ranked by the intelligence index (Artificial Analysis, 0-100) with vendor list prices per million tokens. 0 qualify today.

Ranked by the intelligence index

Strongest first; price breaks ties. Value is index points per blended dollar. Click a model for its full specification, or compare two side by side.

No model in the catalogue publishes this index with these requirements right now.

What to weigh for free use

Some providers list models at no charge - previews, rate-limited tiers, community endpoints. They are not where a product runs, but they are where a prototype starts and an evaluation runs, and some of them score surprisingly well. This list is every model with a zero list price, strongest first.

Free comes with conditions the list price does not show: rate limits, data-use terms, and models that are withdrawn without notice. Read the provider's terms before a prototype depends on one, and treat the index as the only thing here that is comparable.

A router makes free models safe to use: declare them as targets with a low quality prior and the router tries them where the quality floor allows, falls back when they fail or rate-limit, and records in the trace what each one returned - a free evaluation harness. When the budget arrives the same catalogue gains paid targets and nothing else changes: the free models keep the requests they answered well, the paid ones take the rest, and the savings ledger shows what the free tier is still worth against the model you would have paid for.

The rule, in OpenSmartRoute

Declare the models as targets and let the rule send the hard requests to the strongest one and the rest to the best value; the trace names the rule that fired.

yaml

# rules.yaml - free: the strongest qualifying model for the hard requests, the best value for the rest
rules:
  - name: free-hard
    when: { max_complexity: 0.3 }
    prefer: [strongest-model]
    weight: 0.8
  - name: free-default
    when: { max_complexity: 0.45 }
    prefer: [best-value-model]
    weight: 0.6

Try a request Price a workload

Frequently asked

Are there free LLM APIs?: Yes - the ranking above lists every model in the catalogue with a zero list price, strongest first. Check each provider's rate limits and terms.
Can I use a free model in production?: Only with a fallback. The router treats a free model as a target that can fail or rate-limit and escalates to a paid one when it does.
Do free models train on my data?: Some do; the model pages show the data policy of each endpoint offered on this deployment, and a data-boundary rule keeps sensitive requests away from them.

Best models for other tasks

For the business

What it means for which models you pay for.

Catalogue of every vendor
The right model, not the famous one
Price, context, abilities and benchmark indexes side by side, with the model that fits each task named.
The rankings
89% less
Lower cost per request
On the 150-prompt benchmark the router spent 89% less than sending every prompt to the reference model, and the judged quality went up, not down.
Read the benchmark
Per million tokens, every model
Prices you can compare
The catalogue prints input and output prices and what three typical monthly workloads cost on each.
The model catalogue

Which LLM is the cheapest for our workload?: The best-for pages rank the live catalogue per task by the index that measures it, and the router picks the cheapest model that meets your quality rule for each request.
How much can we save on our LLM bill?: On the public benchmark the router saved 89% against sending everything to the reference model. Import last month's provider bill on the bill page and the estimate is computed on your own traffic before you change a line of code.
How often do model prices change?: The catalogue is refreshed from the vendors' price lists; each model page shows the date of its data.

Let the router pick the free use model per request.

The ranking above is where to start; the router finishes the job - the strongest qualifying model for the hard requests, the best value for the rest, and every decision explained.

Create a free account Price a workload

Free plan, no card. Fifteen thousand decisions a month with the full trace.

What to weigh for free use

The rule, in OpenSmartRoute

Declare the models as targets and let the rule send the hard requests to the strongest one and the rest to the best value; the trace names the rule that fired.

yaml

# rules.yaml - free: the strongest qualifying model for the hard requests, the best value for the rest
rules:
  - name: free-hard
    when: { max_complexity: 0.3 }
    prefer: [strongest-model]
    weight: 0.8
  - name: free-default
    when: { max_complexity: 0.45 }
    prefer: [best-value-model]
    weight: 0.6

Frequently asked

Are there free LLM APIs?

Yes - the ranking above lists every model in the catalogue with a zero list price, strongest first. Check each provider's rate limits and terms.

Can I use a free model in production?

Only with a fallback. The router treats a free model as a target that can fail or rate-limit and escalates to a paid one when it does.

Do free models train on my data?

Some do; the model pages show the data policy of each endpoint offered on this deployment, and a data-boundary rule keeps sensitive requests away from them.

Best free AI models

Ranked by the intelligence index

What to weigh for free use

The rule, in OpenSmartRoute

Frequently asked

Related

Best models for other tasks

What it means for which models you pay for.

The right model, not the famous one

Lower cost per request

Prices you can compare

Let the router pick the free use model per request.

Best free AI models

Ranked by the intelligence index

What to weigh for free use

The rule, in OpenSmartRoute

Frequently asked

Related

Best models for other tasks

What it means for which models you pay for.

The right model, not the famous one

Lower cost per request

Prices you can compare

Let the router pick the free use model per request.