Credits are Voxcode’s unit of AI usage. Every request you make consumes credits based on the model you choose and the number of tokens processed.
10 credits ≈ $1 USD
How credits are calculated
Credits are consumed based on the number of input tokens (your message, code context, conversation history) and output tokens (the model’s response) in each request.
const inputCost = (inputTokens / 1000) * model.creditsPerInputToken;
const outputCost = (outputTokens / 1000) * model.creditsPerOutputToken;
const totalCost = inputCost + outputCost;
BYOK (Bring Your Own Key) models do not consume Voxcode credits. When you use BYOK, your provider bills you directly for token usage.
Model pricing
Voxcode groups models into three tiers. The tier a model belongs to also determines which plan gives you access to it.
Free models (!)
Free models cost zero Voxcode credits regardless of how many tokens you use. These are fully capable models — a great starting point for most tasks.
| Model | Input / 1K tokens | Output / 1K tokens |
|---|
| Gemini 2.5 Flash | — | — |
| Gemini 3 Flash Preview | — | — |
| Qwen 3 Coder Plus | — | — |
| Claude Haiku 4.5 | — | — |
| OpenAI o4 Mini High | — | — |
| Qwen 3 Max | — | — |
| Cogito V2 Llama 405B | — | — |
Beta models (*)
Beta models are experimental or cutting-edge releases. Most have very low credit costs, and some are free.
| Model | Input / 1K tokens | Output / 1K tokens | Avg cost |
|---|
| MiMo-V2-Flash | Free | Free | Free |
| GPT-OSS-120B (Free) | Free | Free | Free |
| GPT-OSS-120B | 0.00039 credits | 0.0019 credits | ~0.0015 credits |
| Grok 4.1 Fast | 0.002 credits | 0.005 credits | ~0.004 credits |
| Nex AGI Deepseek V3.1 | 0.0027 credits | 0.01 credits | ~0.008 credits |
| MiniMax M2.1 | 0.0027 credits | 0.0112 credits | ~0.009 credits |
| GPT 5.1 Codex Mini | 0.0025 credits | 0.02 credits | ~0.015 credits |
| GPT 5.1 Codex | 0.0125 credits | 0.1 credits | ~0.076 credits |
Premium models ($)
Premium models are the most capable models available in Voxcode, suited for complex, multi-step, or high-stakes tasks.
| Model | Input / 1K tokens | Output / 1K tokens | Avg cost |
|---|
| GPT 5.1 Codex | 0.0125 credits | 0.1 credits | ~0.076 credits |
| Gemini 2.5 Pro | 0.0125 credits | 0.1 credits | ~0.076 credits |
| Gemini 3 Pro Preview | 0.02 credits | 0.12 credits | ~0.091 credits |
| Claude Sonnet 4.5 | 0.03 credits | 0.15 credits | ~0.114 credits |
| Grok 3 | 0.03 credits | 0.15 credits | ~0.114 credits |
| Claude Opus 4.5 | 0.05 credits | 0.25 credits | ~0.19 credits |
Token estimation guide
Not sure how many tokens your request will use? Use these rough estimates as a guide.
| Request type | Approximate tokens |
|---|
| Short question | 50–200 tokens |
| Code snippet | 100–500 tokens |
| Full component | 500–2,000 tokens |
| Complex conversation | 2,000–8,000 tokens |
| System prompt + context | 1,000–3,000 tokens |
Estimated requests per plan
The table below shows how many typical requests (1K input + 500 output tokens) you can make with each plan’s monthly credit allowance.
| Model | 20 credits (Free) | 100 credits (Starter) | 250 credits (Premium) |
|---|
| GPT-OSS-120B (Free) | ~4,444 requests | ~22,222 requests | ~55,555 requests |
| Grok 4.1 Fast | ~444 requests | ~2,222 requests | ~5,555 requests |
| Qwen 3 Coder Plus | ~571 requests | ~2,857 requests | ~7,142 requests |
| Claude Sonnet 4.5 | ~190 requests | ~952 requests | ~2,380 requests |
| Claude Opus 4.5 | ~114 requests | ~571 requests | ~1,428 requests |
Best practices
- Start with free models. Free and beta models handle the vast majority of coding tasks well. Use them to build your workflow before reaching for premium options.
- Use fast models for simple tasks. Quick questions, syntax lookups, and one-liner fixes don’t need a top-tier model. Grok 4.1 Fast or Gemini 2.5 Flash are fast and cost almost nothing.
- Reserve premium models for complex work. Multi-file refactors, architectural decisions, and difficult debugging sessions are where Claude Opus or GPT 5.1 Codex justify their higher cost.
- Consider BYOK for heavy usage. If you regularly hit your credit limit, the Premium plan’s BYOK support lets you use your own API keys with no Voxcode credit consumption. See the BYOK guide for setup instructions.
You can monitor your current credit balance at any time in Settings → Usage. Top-up credits are available from your avatar → Manage Subscription whenever you need more.
