Simple, Transparent Pricing

Pay per token. No subscriptions. No minimum spend.

Open-weight models. No content filtering. 85% to providers.

$5 (≈₹425)
Free credit on signup
85%
Goes to providers
15%
Platform fee

Model Pricing

ModelCategoryTierPrice / 1M tokensProvider Earns (85%)
Qwen 2.5 0.5BLLMP2P$1.00 (₹85)$0.85 (₹72)
Llama 3.2 1BLLMP2P$1.00 (₹85)$0.85 (₹72)
LiquidAI LFM2 350M Q4LLMP2P$0.50 (₹43)$0.43 (₹37)
LiquidAI LFM2 350M Q8LLMP2P$0.50 (₹43)$0.43 (₹37)
Phi-3 Mini 4KLLMP2P$2.50 (₹213)$2.13 (₹181)
Llama 2 7B ChatLLMP2P$4.00 (₹340)$3.40 (₹289)
Mistral 7B InstructLLMP2P$4.00 (₹340)$3.40 (₹289)

Prices are per 1 million tokens. All models support text and code generation.
Payments processed in INR via Razorpay. INR amounts shown at ≈₹85/USD. Minimum charge: $0.001 per request.
Audio models (STT, TTS, VAD) coming soon.

Orchestration Pricing

Multi-Step Workflows

Orchestrated workflows (research, code generation, agent, map-reduce) are billed at the same base model rate per step — no surcharge. Orchestration is a core differentiator, not an add-on.

1x

No surcharge per step

Budget cap

Set max_cost_usd per workflow

Free

Conversation memory

Use POST /v1/workflows/estimate to preview costs before running a workflow. Conversation memory is included at no extra charge.

Storage Limits (free tier)

100 chats

conversations per user

90-day

auto-cleanup of inactive data

Why Choose Nataris?

💰

Pay-Per-Use

No subscriptions, no minimum spend. Pay only for the tokens you use.

🔒

No Prompt Logging

Prompts are processed on distributed devices, not stored in centralized logs. Provider agreements prohibit data retention.

🌍

People-Powered

85% of every dollar goes directly to real people running inference on their devices — not to data centers.

Instant Start

$5 free credit on signup. No credit card required to start. Test all models before committing.

Ready to Get Started?

Sign up and get $5 free credit to test any model.