> ## Documentation Index
> Fetch the complete documentation index at: https://docs.convocore.app/llms.txt
> Use this file to discover all available pages before exploring further.

# Credits

> How Convocore credits work — 1 USD = 1,000 credits, plan allotments, usage fees, and LLM token rates by model tier.

<Tip>
  Visit your **Billing** page (bottom left) for the **Pricing Calculator**, or compare plans and model rates on [convocore.ai/pricing](https://www.convocore.ai/pricing).
</Tip>

***

## Simple & Transparent Pricing

**Our latest new billing system is simple:**

<Note>
  **1 USD = 1,000 Credits**

  That's it! Easy to understand, easy to calculate. No complex pricing tiers or confusing calculations.
</Note>

This means:

* \$1 gets you 1,000 credits
* \$10 gets you 10,000 credits
* \$100 gets you 100,000 credits

***

## How Credits Work

* **Allocation**: Free workspaces get a **one-time 500-credit trial**. Paid v2 plans include monthly credits (Starter 5k → Elite 120k). You can buy top-ups from Billing (overage on Pro+).
* **Consumption**: Each feature or service consumes credits based on complexity (base interaction + model tokens + voice/crawl, etc.)
* **Balance tracking**: Monitor usage in the dashboard (quota banners + Billing)
* **Transparency**: Credit costs are defined below so you know what you're paying for
* **Rollover**: Unused monthly credits (including purchased top-ups) carry to the next billing cycle. Each cycle adds your plan’s monthly quota on top of your remaining balance.

***

## Credit Usage Pricing

Understand how your credits are consumed across different features:

| Feature            | Usage                                | Cost                     |
| ------------------ | ------------------------------------ | ------------------------ |
| **Interaction**    | Each user interaction on any channel | \$0.0010 per interaction |
| **Custom Channel** | Custom channel fee                   | \$0.0010 per channel     |
| **Crawler**        | For each page crawled                | \$0.0010 per page        |

***

## LLM model pricing (by plan tier)

Plans unlock **model tiers**. Higher plans include every lower tier. Rates below are **platform USD per 1M tokens** (with credits), matching [convocore.ai/pricing](https://www.convocore.ai/pricing).

* **1 credit = $0.001** · **1,000 credits = $1**
* Plus **1 interaction credit (\$0.001)** per reply on top of token cost
* “\~\$ / msg” ≈ a typical turn (\~2,500 input + 300 output tokens) — real usage varies

| Tier  | Unlocked on | What it’s for                                   |
| ----- | ----------- | ----------------------------------------------- |
| **4** | Free+       | Value & speed (default new agents use Qwen 3.5) |
| **3** | Starter+    | Advanced / tool-ready                           |
| **2** | Pro+        | Thinking & high reliability                     |
| **1** | Business+   | Flagship                                        |

### Tier 4 — Value & speed (Free+)

| Model                 | In / 1M | Out / 1M | \~\$ / msg |
| --------------------- | ------- | -------- | ---------- |
| Nemotron Nano 30B     | \$0.090 | \$0.360  | \~\$0.0003 |
| GPT 5 Nano            | \$0.060 | \$0.480  | \~\$0.0003 |
| Gemma 4 26B MoE       | \$0.105 | \$0.300  | \~\$0.0004 |
| Gemini 2.5 Flash-Lite | \$0.120 | \$0.480  | \~\$0.0005 |
| Llama 3.3 70B         | \$0.195 | \$0.600  | \~\$0.0007 |
| GPT-4o Mini           | \$0.225 | \$0.900  | \~\$0.0008 |
| Qwen-Turbo Latest     | \$0.600 | \$0.300  | \~\$0.0016 |
| Qwen 3.5 397B         | \$0.900 | \$5.40   | \~\$0.0039 |

### Tier 3 — Advanced (Starter+)

| Model                 | In / 1M | Out / 1M | \~\$ / msg |
| --------------------- | ------- | -------- | ---------- |
| Gemini 3.1 Flash-Lite | \$0.375 | \$2.25   | \~\$0.0016 |
| GPT 5 Mini            | \$0.375 | \$3.00   | \~\$0.0018 |
| Qwen-Max / Qwen-Plus  | \$0.600 | \$1.80   | \~\$0.0020 |
| Gemini 2.5 Flash      | \$0.360 | \$3.00   | \~\$0.0018 |
| Kimi-K2.6             | \$1.43  | \$6.00   | \~\$0.0054 |
| Claude Haiku 4.5      | \$1.50  | \$7.50   | \~\$0.0060 |
| DeepSeek-V4-Pro       | \$2.63  | \$5.25   | \~\$0.0081 |

### Tier 2 — Thinking & high reliability (Pro+)

| Model             | In / 1M | Out / 1M | \~\$ / msg |
| ----------------- | ------- | -------- | ---------- |
| GPT-5.6 Luna      | \$0.260 | \$1.56   | \~\$0.0011 |
| GPT-5             | \$1.88  | \$15.00  | \~\$0.0092 |
| Gemini 3.5 Flash  | \$2.25  | \$13.50  | \~\$0.0097 |
| GPT-4.1           | \$3.00  | \$12.00  | \~\$0.011  |
| GPT-5.2           | \$2.63  | \$21.00  | \~\$0.013  |
| Gemini 3.1 Pro    | \$3.00  | \$18.00  | \~\$0.013  |
| GPT-4o            | \$3.75  | \$15.00  | \~\$0.014  |
| Claude Sonnet 4.5 | \$4.50  | \$22.50  | \~\$0.018  |

### Tier 1 — Flagship (Business+)

| Model                       | In / 1M | Out / 1M | \~\$ / msg |
| --------------------------- | ------- | -------- | ---------- |
| o3-mini                     | \$1.65  | \$6.60   | \~\$0.0061 |
| Grok 4.5                    | \$3.00  | \$9.00   | \~\$0.010  |
| GPT-5.6 Terra               | \$2.60  | \$15.60  | \~\$0.011  |
| Kimi-K3                     | \$4.50  | \$22.50  | \~\$0.018  |
| Claude Opus 4.5 / 4.6 / 4.7 | \$7.50  | \$37.50  | \~\$0.030  |
| GPT-5.6 Sol                 | \$7.50  | \$45.00  | \~\$0.032  |
| o1                          | \$22.50 | \$90.00  | \~\$0.083  |

<Note>
  **Bring your own API keys (BYOK)** to cut LLM credit usage dramatically (often up to \~20x on heavy models). On the **v2-2026** catalog, BYOK + premium (Tier 1) models are included on **Business** and higher (or via the BYOK add-on).
</Note>

<Warning>
  Model lists and rates track the live catalog and can change as new models ship. Always treat [convocore.ai/pricing](https://www.convocore.ai/pricing) as the source of truth for the full table.
</Warning>

***

## Optimizing Credit Consumption

To help you minimize your credit usage:

<img src="https://mintlify.s3.us-west-1.amazonaws.com/convocore-app/images/meta-tut/20.PNG" alt="1" />

* Add your own API Keys to dramatically decrease your credits usage.

<img src="https://mintlify.s3.us-west-1.amazonaws.com/convocore-app/images/meta-tut/21.PNG" alt="2" />

* This option MUST be selected for decreases your credits usage properly.

***

## Purchasing additional credits

If your allocation is insufficient: **Billing** (bottom left) → choose a credit package / top-up → complete payment.

Overage / top-up credits are available on **Pro+** on the v2 catalog.

<Tip>
  Use the **Pricing Calculator** on Billing (or the plan calculator on [convocore.ai/pricing](https://www.convocore.ai/pricing)) to estimate monthly credit needs.
</Tip>

<Note>
  Maintaining an adequate credit balance keeps AI usage uninterrupted for the billing period.
</Note>

***

## Saving credits & optimizing usage

One of our users complained credits were being consumed quickly. By changing the following 2 settings, we decreased about 95% of their credits usage:

### 1. Use the latest widget code

The legacy widget code uses an expensive CDN, prompting us to charge a small amount of credits on every visit. The new script uses a different, more efficient CDN (vg-bunny, which is the current latest), thus saving a significant amount of credits.

### 2. Disable autostart & initial prompt

The autostart feature combined with initial prompt can drain credits quickly — for every visit you can spend up to 50 credits if the prompt & output are long.

**By disabling autostart:**

* You save 1 credit fee for the base fee of the interaction

**By disabling the initial prompt:**

* You save up to 100 credits per visit since you're not going to prompt the AI unless the user explicitly asks for it
* By default, the autostart option is off for this reason

***

## Next steps

* **[Billing](./billing)** — Manage your subscription and payment methods
* **[Provider cost estimates](./provider-cost-estimates)** — Voice STT / TTS rates
* **[Voice pricing](../voice/pricing)** — Per-minute call stack
* **[Live pricing](https://www.convocore.ai/pricing)** — Full model + plan tables