---
title: "Pricing — Tarka"
description: "Price an agent on Tarka or in your own infrastructure, and see the unit prices for model APIs and managed compute, billed from prepaid credit."
url: "https://tarkahq.com/pricing/"
---

Pricing

# Price your agent. Pay for what it uses.

Start from one of the example agents and move the sliders to your volume to see what it costs on Tarka, or with any part in your own infrastructure. The unit prices below come from the billing catalog.

[Price an agent](https://tarkahq.com/pricing/#calculator) [Unit prices](https://tarkahq.com/pricing/#unit-prices)

## Price an agent like these.

Pick an example to fill in the table, move any slider to your own volume, and choose where each component runs: on Tarka, or in your own infrastructure with a Tarka cell.

Start from an example agent **Personal assistant** One host per person **Order fulfillment** One background agent **Customer support** Shared by all your customers **Fitness coach** One host per athlete

Where it runs All on Tarka Only models on Tarka All in your account Currency

| Component | Where it runs | On Tarka | Your infrastructure |
| --- | --- | --- | --- |
| Agent hosts agent host One host for each person<br>Hosts running | Agent hosts: where it runs Tarka Yours | On Tarka €91.25 20 × 1 vCPU · 2 GiB · Europe | Your infrastructure ≈ €155 5 vCPU · 9 GiB · 40 GiB disk |
| Language model model inference Every message and reply<br>Model<br>Requests a month | Language model: where it runs Tarka Yours | On Tarka €10.93 60M in · 4M out · Europe | Your infrastructure €9,198–17,581 4× B200 · 614 GB |
| Speech speech Voice notes in, spoken replies out<br>Voice minutes a month | Speech: where it runs Tarka Yours | On Tarka €0.00 3,000 minutes of audio · Free for a limited time | Your infrastructure €263–986 1 GPU · 24–48 GB |
| Documents documents Reading scans and PDFs<br>Pages a month | Documents: where it runs Tarka Yours | On Tarka — not used | Your infrastructure — not needed |
| Code sandboxes code sandbox Running code the agent writes<br>Sandbox runs a month | Code sandboxes: where it runs Tarka Yours | On Tarka — not used | Your infrastructure — not needed |
| Batch jobs batch job Scheduled and batch work<br>Job hours a month | Batch jobs: where it runs Tarka Yours | On Tarka — not used | Your infrastructure — not needed |
| Files and source object storage hosted git Buckets and repositories<br>GiB kept | Files and source: where it runs Tarka Yours | On Tarka — not used | Your infrastructure — not needed |
| Cell services gateway Gateway and ingress for the parts you run | With any part in yours | On Tarka Included part of the platform | Your infrastructure — only with a part in your infrastructure |
| Tarka cell License, updates and support | With any part in yours | On Tarka Included part of the platform | Your infrastructure — only with a part in your infrastructure |
| Per month In EUR, from the personal assistant example |  | On Tarka €102.18 billed by use | Your infrastructure — nothing runs in your infrastructure |

Agent hosts run in Europe and are billed for allocated CPU and RAM while they run: about €4.56 a month for each of the 20 hosts, before model calls. The model’s tokens cost €10.93 a month on Tarka at this volume, while one copy of DeepSeek V4.1 Flash on your own GPUs rents for €9,198–17,581 a month before staff, monitoring and a second copy. Run the model yourself when rules require it or your volume would keep the GPUs busy; otherwise call it on Tarka.

Tarka amounts use price list 2026-11-04.1: Agent Hosts, batch jobs and sandboxes in Europe by allocated CPU and RAM over running time, models per token, audio second or page; storage is metered but not charged yet. Each example sets the sliders to a rough month of its use and brings its host size, model and tokens per request. Your-infrastructure figures are estimates: one copy of the model on B200 GPUs at $3.50–6.69 an hour and smaller GPUs at $0.40–1.50, other servers and disks at on-demand cloud list prices, with no staff, monitoring or second copy. Tarka’s cell fee is a placeholder. Amounts in currencies other than USD and EUR use market rates of 23 October 2026.

## Unit prices.

One account for model APIs, speech, documents and managed compute, billed from prepaid credit. Current rates come directly from the billing catalog.

Catalog 2026-11-04.1 · release verified 2026-11-04 · [Live catalog](https://tarka.rest/control/v1/pricing)

Display currency

Prepaid usage, with $5.00 starter credit once per approved account. No subscription is required. EUR amounts use the catalog’s conversion factor; your account’s billing currency applies.

## Model pricing

Utilities are free for a limited time. Regular prices are crossed out below; the current price is zero. Inference models and compute products keep their listed prices.

| Model | Input / 1M tokens | Cached input / 1M | Output / 1M | Audio / second | Successful page |
| --- | --- | --- | --- | --- | --- |
| `deepseek-v4.1-flash` | $0.33 | $0.0066 | $1.32 | — | — |
| `deepseek-v4.1-flash-eu` | $0.33 | $0.0066 | $1.32 | — | — |
| `glm-5.3` | $1.375 | $0.264 | $4.40 | — | — |
| `glm-5.3-flash` | $0.1485 | $0.0297 | $0.495 | — | — |
| `glm-5.3-flash-eu` | $0.1485 | $0.0297 | $0.495 | — | — |
| `glm-ocr` Free for a limited time | — | — | — | — | ~~$0.001~~ $0.00 |
| `glm-ocr-nepali` Free for a limited time | — | — | — | — | ~~$0.001~~ $0.00 |
| `himalaya-bf16` | Free | — | — | — | — |
| `himalaya-bf16-private` No Tarka content capture | $0.05 | $0.01 | $0.10 | — | — |
| `himalaya-gemma-4-bf16` | Free | — | — | — | — |
| `himalaya-gemma-4-bf16-private` No Tarka content capture | $0.08 | $0.02 | $0.20 | — | — |
| `himalaya-gemma-4-q4` | Free | — | — | — | — |
| `himalaya-gemma-4-q4-private` No Tarka content capture | $0.06 | $0.02 | $0.16 | — | — |
| `himalaya-gemma-4-q8` | Free | — | — | — | — |
| `himalaya-gemma-4-q8-private` No Tarka content capture | $0.07 | $0.02 | $0.18 | — | — |
| `himalaya-q4` | Free | — | — | — | — |
| `himalaya-q4-private` No Tarka content capture | $0.03 | $0.01 | $0.06 | — | — |
| `himalaya-q8` | Free | — | — | — | — |
| `himalaya-q8-private` No Tarka content capture | $0.04 | $0.01 | $0.08 | — | — |
| `kimi-k3` | $2.97 | $0.297 | $14.85 | — | — |
| `kokoro` Free for a limited time | — | — | — | ~~$0.0001~~ $0.00 | — |
| `nepali-parler-tts` Free for a limited time | — | — | — | ~~$0.0003~~ $0.00 | — |
| `paddleocr-vl-1.6` Free for a limited time | — | — | — | — | ~~$0.001~~ $0.00 |
| `piper` Free for a limited time | — | — | — | ~~$0.00005~~ $0.00 | — |
| `pp-doclayout-v3` Free for a limited time | — | — | — | — | ~~$0.00025~~ $0.00 |
| `qwen3-asr` Free for a limited time | — | — | — | ~~$0.00003~~ $0.00 | — |
| `qwen3-tts` Free for a limited time | — | — | — | ~~$0.0004~~ $0.00 | — |
| `qwen3.8-flash-next` | Free | — | — | — | — |
| `whisper-large-v3` Free for a limited time | — | — | — | ~~$0.00005~~ $0.00 | — |
| `whisper-nepali-medium` Free for a limited time | — | — | — | ~~$0.00006~~ $0.00 | — |

Speech recognition is measured by processed input audio; speech generation by output audio duration, including generated audio whose delivery began. Documents are measured by successful pages. Utility calls do not add token charges. Private endpoints retain billing metadata.

## EU compute pricing

| Product | vCPU / 720 hours | GiB RAM / 720 hours | 1 vCPU + 1 GiB / 720 hours |
| --- | --- | --- | --- |
| agents | $3.00 | $1.00 | $4.00 |
| jobs | $4.50 | $1.50 | $6.00 |
| sandboxes | $6.00 | $2.00 | $8.00 |

720 hours is a comparison period, not a monthly fee or cap. Charges use allocated CPU and RAM over running time. Existing grandfathered Agent Hosts remain free. New hosts stop when prepaid credit runs out and can be resumed after a top-up; their data is retained.

## Compute · US East

US East has separate prices. The total depends on your size and its minimum hourly charge. Your existing EU resources keep their current prices.

| Product | 1 vCPU + 1 GiB RAM + 1 GiB scratch / hour | Minimum running time |
| --- | --- | --- |
| agents | [Quote your stack](https://tarkahq.com/console/compute/hosted-agents) | 60 seconds |
| jobs | $0.1511443 | 60 seconds |
| sandboxes | $0.1511443 | 60 seconds |

The hourly examples include the minimum charge for that size. Agent Hosts are quoted per stack, including all application and platform workloads. Larger CPU, memory or scratch allocations need a new quote. No runtime charge applies if execution never starts. Network access and persistent storage are not included in these examples; their prices and availability must be confirmed before creation.

## Estimate your usage

Model Input tokens (including cached) Cached input tokens Output tokens $1.65

EU compute product vCPU RAM (GiB)  Running hours $4.00

Actual usage is rounded per request or cumulative compute runtime. This estimate excludes free starter credit.

## Create an account and price your first agent.

Sign up, then request the products you need from the console.

[Create an account](https://tarkahq.com/console?auth=signup) [Read the docs](https://tarkahq.com/docs/)