BotConnector
Sign in Workspace Open App
Transparent Economics · Local & Cloud Hybrid

Simple, transparent pricing.
Choose how you run AI.

BotConnector lets you choose how your AI workloads run. Run supported open models locally on your own hardware with zero cloud fees, or use BotConnector Cloud from the same account with Free Starter and flexible PAYG.

$0 Cloud Inference Fee on Local Hardware
19 Free Cloud Models in Starter
Transparent PAYG by Account Activation
No Forced Expiring Subscriptions
PRICING TIERS

Three transparent ways to compute

Choose between hardware you already own and BotConnector cloud services based on your workload, privacy boundaries, and model capacity requirements.

Self-Hosted

Local Inference

Run open models directly on your hardware via loopback. Zero cloud inference fees.

$0
Forever free · uses your own hardware
  • ✓ BotConnector fee: $0 cloud inference fee
  • ✓ Local inference path: model execution stays on loopback; cloud-only features remain separate
  • ✓ Compute source: Physical CPU, GPU, RAM/VRAM
  • ✓ Token limits: Unlimited offline generation
  • ✓ Supported models: Qwen, Llama, DeepSeek, Mistral GGUFs
Frontier Compute

Pay-As-You-Go (PAYG)

Access frontier models and large context capacity on demand with transparent billing.

Usage-Based
Pay per token · activated per account
  • ✓ Account activation: Top-up credits when you need them
  • ✓ Frontier intelligence: Large-scale reasoning & multimodal models
  • ✓ Developer API: Hosted endpoint for applications & agents
  • ✓ High limits: Dedicated capacity without dynamic fair-use queue
  • ✓ Balance control: Transparent token counting & margin
CURRENT PAYG RATES

Concrete rates before you top up

These customer rates are generated from the same verified billing registry used by the BotConnector billing engine. Models with unverified or stale pricing are not shown.

ⓘ
Top-up options: $10 · $25 · $50 · $100. PAYG credits are only for BotConnector AI service usage, are non-transferable, and are not cash-redeemable outside an approved refund. Applicable taxes may be added at checkout.
Model Input / 1M tokens Output / 1M tokens Rate note
GLM 5.3 Flash$0.105$0.35Value Pick · Promotional rate
DeepSeek V4.1 Flash$0.161$0.483Value Pick · Promotional rate
GLM 5.2$0.7601$2.43Value Pick · Promotional rate
MiniMax M3$0.3375$1.35Competitive rate · Standard rate
Qwen3.5 397B A17B$0.2322$1.3932Value Pick · up to 128K input tokens · Standard rate
Qwen3.5 397B A17B$0.5805$3.483Value Pick · up to 256K input tokens · Standard rate
Kimi K3$2.625$13.6875Value Pick · Standard rate
Qwen3.8 Flash$0.1271$0.4298Competitive rate · Standard rate
GPT-5.6 Luna$0.225$1.35Frontier access · Standard rate
GPT-5.6 Terra$2.25$13.5Frontier access · Standard rate
GPT-5.6 Sol$4.5$22.5Frontier access · Promotional rate · ends 2026-11-22
Claude Sonnet 5$2.25$11.25Frontier access · Standard rate
Claude Opus 5$5.625$28.125Frontier access · Standard rate
Gemini 3.8 Flash$0.8438$4.2188Frontier access · Promotional rate · ends 2027-01-01
Gemini 3.8 Flash Flex$0.4219$2.1094Frontier access · Promotional rate · ends 2027-01-01
Gemini 3.7 Flash$0.8438$4.2188Frontier access · Promotional rate · ends 2027-01-01
Gemini 3.7 Flash Flex$0.4219$2.1094Frontier access · Promotional rate · ends 2027-01-01
Gemini 3.6 Flash$0.8438$4.2188Frontier access · Promotional rate · ends 2027-01-01
Gemini 3.6 Flash Flex$0.4219$2.1094Frontier access · Promotional rate · ends 2027-01-01
Gemini 3.5 Flash$1.6875$10.125Frontier access · Standard rate
Gemini 3.5 Flash Flex$0.8438$5.0625Frontier access · Standard rate
Gemini 3.5 Flash Lite$0.3375$2.8125Frontier access · Standard rate
Gemini 3.5 Flash Lite Flex$0.1688$1.4063Frontier access · Standard rate
Gemini 3.1 Flash Lite$0.2813$1.6875Frontier access · Standard rate
Gemini 3.1 Flash Lite Flex$0.1406$0.8438Frontier access · Standard rate
Gemini 3.1 Pro Preview$2.25$13.5Frontier access · up to 200K input tokens · Standard rate
Gemini 3.1 Pro Preview$4.5$20.25Frontier access · up to 1M input tokens · Standard rate
Gemini 3.1 Pro Preview Flex$1.125$6.75Frontier access · up to 200K input tokens · Standard rate
Gemini 3.1 Pro Preview Flex$2.25$10.125Frontier access · up to 1M input tokens · Standard rate
Solar Mini 4$0.06$0.24Promotional rate · ends 2026-10-23
Solar Pro 4$0.108$0.432Promotional rate · ends 2026-10-10

Available PAYG media rates

ModelBilling unitRate
Gemini 3.1 Flash Imageimage · 1k$0.075375 / image
Gemini 3.1 Flash Lite Imageimage · 1k$0.0378 / image
FLUX.2 [klein] 4Bimage · actual-cost$0.012 / image
ⓘ
Rates are in USD and may change when upstream pricing changes. BotConnector refreshes this table only from prices that pass billing verification. Balance is deducted from recorded actual usage. Generated: 2026-09-27.
CURATED SELECTION

Free Cloud models available with Starter

Choose directly in BotConnector without separate cloud credentials. Models marked Free are available to Starter users with dynamic fair-use when shared capacity is under pressure.

General, Reasoning & Agent Free Starter
  • ✓
    GPT-6 Luna · OpenAI · Launch Access: 1M tokens/month on Starter now · Included with Pro when subscriptions launch
  • ✓
    Ling 3.0 Flash · Fast general reasoning · Free
  • ✓
    GLM-5.3 Flash · 1M Context Window · Free
  • ✓
    DeepSeek V4 Flash · Math & Code Reasoning · Free
  • ✓
    NVIDIA Nemotron 3 Nano · Lightweight Ingestion · Free
  • ✓
    Tencent Hy3 · Fast Production · Free
  • ✓
    Xiaomi MiMo V2.5 · Workflow Automation · Free
  • ✓
    Mistral Nemo · High Efficiency · Free
Coding, Multimodal & Fast Chat Free Starter
  • ✓
    Qwen3.7 Flash · Vision & Language · Free
  • ✓
    MiniMax M3 · Fast Context Processing · Free
  • ✓
    Mistral Medium 3.5 · Structured Output · Free
  • ✓
    Qwen3 Coder Plus · Agentic Programming · Free
  • ✓
    Qwen3.8 Omni Flash · Multimodal Speed · Free
  • ✓
    Agnes 3.0 Flash · Rapid Task Execution · Free
  • ✓
    Space Bunny Alpha · Creative & Chat · Free
ⓘ
Starter accounts do not have a rigid daily message limit for normal usage. Dynamic fair-use applies to ensure shared capacity availability. Availability may adjust based on upstream capacity.
ECONOMIC COMPARISON

Local Hardware vs Cloud Economics

A clear breakdown of costs, trade-offs, and operational characteristics between computing modes.

Attribute Local On-Device Inference BotConnector Cloud (Free & PAYG)
Inference Cost $0 / token (Uses your machine electricity) Free for Starter models; transparent token pricing for PAYG
Privacy Boundary Model execution stays on loopback (127.0.0.1); cloud-only supporting features remain separate Encrypted transit to official vendor & inference APIs
Offline Operation Local model inference can run without internet after runtime and model setup Requires stable internet connection
Hardware Dependency Requires sufficient RAM/VRAM matched to model size Runs on any device (phone, tablet, thin laptop)
Model Size Limit Bounded by workstation RAM/VRAM capacity Up to 1M token context windows & frontier parameter scales
Setup Time Download model weights once via Ollama/GGUF Instant access without local downloads or disk usage
FREQUENTLY ASKED QUESTIONS

Billing, access, and usage details

Do I need a credit card to use BotConnector?

No. Starter accounts can access all Free Cloud models and all Local AI capabilities immediately without providing credit card or billing details.

How does Pay-As-You-Go (PAYG) billing work?

PAYG is activated on your account when you choose to use frontier models that exceed Starter Free Cloud tiers. Billing is metered purely on input and output tokens consumed, with transparent rates and credit balances.

Does BotConnector charge for running local models?

Never. Local models run on your own machine hardware through loopback runtimes (like Ollama or LM Studio). BotConnector provides the interface, advisor, and CLI tooling for free.

What does dynamic fair-use mean?

Starter Free Cloud models are provided using pooled inference capacity. When system traffic spikes, requests are dynamically queued to ensure all users receive fair access without sudden hard lockouts.

Choose the AI workflow that fits your budget and privacy requirements.