ConsoleApp

Choose the right plan

Pay only for what you use. All plans include platform access and basic features

Free

$0

For personal projects and experiments

  • 500 Agent calls
  • 500 MB storage
  • 1,000 Knowledge base searches
  • $5 services grant
Start for free

Developer

$29

For individual developers

  • 3,000 Agent calls
  • 1 GB storage
  • 5,000 Knowledge base searches
  • $5 services grant
Get Started
Popular

Team

$79

For small teams and startups

  • 10,000 Agent calls
  • 5 GB storage
  • 20,000 Knowledge base searches
  • $5 services grant
Get Started

Business

$149

For growing businesses

  • 30,000 Agent calls
  • 10 GB storage
  • 50,000 Knowledge base searches
  • $5 services grant
Get Started

Compare plans

Detailed comparison of all features

FeatureFreeDeveloperTeamBusiness
Pricing
Price ($)$0$29$79$149
Yearly subscription$0$290$790$1,490
Included in plan
Agent calls5003,00010,00030,000
LLM/API calls5003,00010,00030,000
Knowledge base searches5002,0008,00015,000
Vector storage500 MB1 GB5 GB10 GB
File storageNo1 GB5 GB10 GB
Custom graph hostingNo1 podUp to 10 podsUnlimited
Admins-+1+5Unlimited
MonetizationNoNoNoYes
SupportCommunity (2 days)Email (8 hours)Telegram (4 hours)Priority 24/7 (2 hours)
Overage pricing
Agent call-$0.01$0.0095$0.008
LLM call-$0.003$0.00275$0.0025
External API call-$0.00075$0.00065$0.0006
Knowledge base search-$0.002$0.0018$0.0016
Additional services
Hosting simple graph-$10 per pod$9 per pod$8 per pod
Hosting complex graph-$19 per pod$17 per pod$15 per pod
Hosting AI service-$35 per pod$32 per pod$28 per pod
Vector storage-$3 per GB$3 per GB$3 per GB
Knowledge base search-$0.002 per request$0.002 per request$0.002 per request
PDF OCR recognition$0.003 per page$0.003 per page$0.003 per page$0.003 per page
File storage (S3)$0.06 per GB$0.06 per GB$0.06 per GB$0.06 per GB

Pricing examples

Real usage scenarios with detailed cost breakdown

Solo developer (MVP)

A developer building an MVP support chatbot using a pre-built template. Testing with a small group of 10 users. Uploaded 500 MB of company documentation. Averaging 60 agent requests per day.

What they use:

  • 1 agent on pre-built template (support chatbot)
  • 1,800 calls per month (60/day × 30 days)
  • 500 MB document storage

Monthly cost: $29

Fits in Developer plan ($29): includes 3,000 calls + 1 GB storage. No graph hosting needed (uses pre-built template)

Product team

A team of 8 people building a SaaS product. Created a custom support agent with Intercom integration and a knowledge base from documentation. The agent handles ~300 requests per day from test users and the team.

What they use:

  • 1 agent on medium graph (support with integrations)
  • 9,000 calls per month (300/day × 30 days)
  • 2 GB documentation and FAQ
  • 3 admins (PM, Tech Lead, Support Lead)

Monthly cost: $96

Team plan $79 (includes 10,000 calls, fits within limit) + 1 medium pod × $17 = $79 + $17 = $96

SaaS company with monetization

A SaaS platform with 5,000 active users runs 2 types of agents: a simple FAQ bot (handling main traffic, scaled to 10 pods) and a complex analytics agent with integrations (running on 3 pods). Averaging 50,000 requests per day.

What they use:

  • 2 agents: simple graph on 10 pods + medium graph on 3 pods
  • 1,500,000 calls per month (50,000/day × 30 days)
  • 15 GB document storage
  • 10 administrators

Monthly cost: $12,034

Business plan $149 (includes 30,000 calls) + overage: 1,470,000 calls × $0.008 = $11,760 + graph hosting: 10 simple pods × $8 = $80, 3 medium pods × $15 = $45. Total: $149 + $11,760 + $80 + $45 = $12,034

Available LLM models

Current prices for tokens of popular language models

+
ProviderModelRequestResponse
anthropicclaude-3-5-haiku-20241022$4 per 1M tokens$0.8 per 1M tokens
claude-3-5-sonnet-20241022$15 per 1M tokens$3 per 1M tokens
claude-3-7-sonnet-20250219$15 per 1M tokens$3 per 1M tokens
claude-3-haiku-20240307$1.25 per 1M tokens$0.25 per 1M tokens
claude-3-opus-20240229$75 per 1M tokens$15 per 1M tokens
claude-haiku-4-5-20251001$5 per 1M tokens$1 per 1M tokens
claude-opus-4-1-20250805$75 per 1M tokens$15 per 1M tokens
claude-opus-4-20250514$75 per 1M tokens$15 per 1M tokens
claude-sonnet-4-5-20250929$15 per 1M tokens$3 per 1M tokens
claude-sonnet-4-20250514$15 per 1M tokens$3 per 1M tokens
coherererank-english-v3.0$0 per 1M tokens$0 per 1M tokens
rerank-multilingual-v3.0$0.002 per 1M tokens$0.002 per 1M tokens
mistralcodestral-embed-2505$0 per 1M tokens$0.15 per 1M tokens
codestral-latest$0.9 per 1M tokens$0.3 per 1M tokens
devstral-medium-2507$2 per 1M tokens$0.4 per 1M tokens
devstral-medium-latest$2 per 1M tokens$0.4 per 1M tokens
devstral-small-2505$0.3 per 1M tokens$0.1 per 1M tokens
devstral-small-2507$0.3 per 1M tokens$0.1 per 1M tokens
magistral-medium-latest$5 per 1M tokens$2 per 1M tokens
magistral-small-latest$1.5 per 1M tokens$0.5 per 1M tokens
ministral-3b-latest$0.04 per 1M tokens$0.04 per 1M tokens
ministral-8b-latest$0.1 per 1M tokens$0.1 per 1M tokens
mistral-embed$0 per 1M tokens$0.1 per 1M tokens
mistral-large-latest$6 per 1M tokens$2 per 1M tokens
mistral-medium-latest$2 per 1M tokens$0.4 per 1M tokens
mistral-moderation-latest$0 per 1M tokens$0.1 per 1M tokens
mistral-saba-latest$0.6 per 1M tokens$0.2 per 1M tokens
mistral-small-latest$0.3 per 1M tokens$0.1 per 1M tokens
open-mistral-7b$0.25 per 1M tokens$0.25 per 1M tokens
open-mixtral-8x7b$0.7 per 1M tokens$0.7 per 1M tokens
open-mixtral-8x22b$6 per 1M tokens$2 per 1M tokens
pixtral-12b$0.15 per 1M tokens$0.15 per 1M tokens
pixtral-large-latest$6 per 1M tokens$2 per 1M tokens
voxtral-mini-2507$0.04 per 1M tokens$0.04 per 1M tokens
voxtral-small-2507$0.3 per 1M tokens$0.1 per 1M tokens
openaibabbage-002$0.6 per 1M tokens$0.15 per 1M tokens
chatgpt-4o-latest$15 per 1M tokens$5 per 1M tokens
codex-mini-latest$6 per 1M tokens$1.5 per 1M tokens
computer-use-preview-2025-03-11$12 per 1M tokens$3 per 1M tokens
davinci-002$2 per 1M tokens$2 per 1M tokens
gpt-3.5-turbo-0125$1.5 per 1M tokens$0.5 per 1M tokens
gpt-3.5-turbo-instruct$2 per 1M tokens$1.5 per 1M tokens
gpt-4-turbo-2024-04-09$30 per 1M tokens$10 per 1M tokens
gpt-4.1$8 per 1M tokens$2 per 1M tokens
gpt-4.1-2025-04-14$8 per 1M tokens$2 per 1M tokens
gpt-4.1-mini$1.6 per 1M tokens$0.4 per 1M tokens
gpt-4.1-mini-2025-04-14$1.6 per 1M tokens$0.4 per 1M tokens
gpt-4.1-nano$0.4 per 1M tokens$0.1 per 1M tokens
gpt-4.1-nano-2025-04-14$0.4 per 1M tokens$0.1 per 1M tokens
gpt-4.5-preview-2025-02-27$150 per 1M tokens$75 per 1M tokens
gpt-4o$10 per 1M tokens$2.5 per 1M tokens
gpt-4o-2024-08-06$10 per 1M tokens$2.5 per 1M tokens
gpt-4o-audio-preview-2024-12-17$10 per 1M tokens$2.5 per 1M tokens
gpt-4o-mini-2024-07-18$0.6 per 1M tokens$0.15 per 1M tokens
gpt-4o-mini-audio-preview-2024-12-17$0.6 per 1M tokens$0.15 per 1M tokens
gpt-4o-mini-realtime-preview-2024-12-17$2.4 per 1M tokens$0.6 per 1M tokens
gpt-4o-mini-search-preview-2025-03-11$0.6 per 1M tokens$0.15 per 1M tokens
gpt-4o-mini-transcribe$5 per 1M tokens$1.25 per 1M tokens
gpt-4o-mini-tts$0 per 1M tokens$0.6 per 1M tokens
gpt-4o-realtime-preview-2024-12-17$20 per 1M tokens$5 per 1M tokens
gpt-4o-search-preview-2025-03-11$10 per 1M tokens$2.5 per 1M tokens
gpt-4o-transcribe$10 per 1M tokens$2.5 per 1M tokens
gpt-5$10 per 1M tokens$1.25 per 1M tokens
gpt-5-chat-latest$0 per 1M tokens$0 per 1M tokens
gpt-5-mini$2 per 1M tokens$0.25 per 1M tokens
gpt-5-nano$0.4 per 1M tokens$0.05 per 1M tokens
gpt-image-1$0 per 1M tokens$5 per 1M tokens
o1-2024-12-17$60 per 1M tokens$15 per 1M tokens
o1-mini-2024-09-12$4.4 per 1M tokens$1.1 per 1M tokens
o1-pro-2025-03-19$600 per 1M tokens$150 per 1M tokens
o3-mini-2025-01-31$4.4 per 1M tokens$1.1 per 1M tokens
o4-mini-2025-04-16$4.4 per 1M tokens$1.1 per 1M tokens
o4-mini-deep-research-2025-06-26$8 per 1M tokens$2 per 1M tokens