Light
Easy tasks: formatting, short edits, quick replies.
- 1GPT-6 LunaInput $0.13Output $0.65
- 2DeepSeek V4.1 FlashInput $0.39Output $1.56
- 3Gemini 3.1 Flash-LiteInput $0.33Output $1.95
- 4Gemini 3.5 Flash-LiteInput $0.39Output $3.25
Custom pricing for production workloads
Jev Router
Jev Router sends every request to the right model and saves your credits: low-cost models for easy work, top models for hard work.
typesafe/jev-routerJev Router rates every request for difficulty and sends it to a model that fits.
Stronger models cost more. Jev Router pays for the strong one only when the task needs it.
Pick a request and see how Jev rates it and which model answers.
“Format this JSON config”
Easy
Routed to the Light tier
Price per 1M input tokens
One tier for each level of task difficulty. The first model in a tier answers, and the rest are backups, in order.
Easy tasks: formatting, short edits, quick replies.
Medium tasks: summaries, reviews, multi-step work.
Hard tasks: complex reasoning, tricky code, planning.
USD per 1M tokens, at AI/ML API list prices.
Total for 7 tasks
With Jev Router$0.25
All on Claude Opus 5.5$0.49
Saved48%
Illustrative token counts. Costs use the list prices above. Routing fee not included.
Set your monthly volume and task mix. The totals update as you go.
Medium requests (Standard tier)30%
Monthly estimate. Assumes 3,000 input and 600 output tokens per request, each answered by its tier’s first model. Includes one Jev routing decision per request, at 3,000 input tokens.
One model is either too expensive for easy work or too weak for hard work.
| Criteria | Jev Router | One top model | One low-cost model | Your own router |
|---|---|---|---|---|
| Cost of easy tasks | From $0.13 per 1M input tokens | Full top-model price | Low | Low |
| Quality on hard tasks | Top models | Top model | Often falls short | Depends on your rules |
| Setup | Change 2 lines | Change 2 lines | Change 2 lines | Weeks of work |
| Backup if a model fails | Automatic | None | None | If you build it |
| Tasks per $1 in the example | 28 | 14 | Varies | Varies |
Swipe the table sideways to see all four options.
Keep your OpenAI-compatible code. Change the base URL and the model name. Already on AI/ML API? Change only the model name.
import osfrom openai import OpenAI client = OpenAI( base_url="https://api.aimlapi.com/v1", api_key=os.environ["AIMLAPI_KEY"],) resp = client.chat.completions.create( model="typesafe/jev-router", messages=[{"role": "user", "content": "Summarize this contract"}],) print(resp.model_extra["meta"]["model"]) # the model Jev Router picked
Highlighted code is all you change.
Two things: the Jev routing step, and the tokens used by the model that answers. Both are billed at standard AI/ML API rates and appear in your usage log.
Only the eight models listed on this page, in three tiers.
Another provider serves the same model. If none can, the next model in the same tier answers.
No. Requests Jev rates as hard go to the Heavy tier: Claude Opus 5.5 first, GPT-6 Astra as backup.
Yes. The meta.model field in every response names it. Without streaming, the x-aimlapi-model header does too.
When you need the same model every time, such as for evaluations or audited workflows. You can use Jev Router and pinned models side by side.