Pricing

For AI agents: docs.octen.ai/overview/pricing.md

Overview

Our pricing combines pay-as-you-go API billing with an optional plan: a Search Plan or a QPS Plan.

Start on Free

New accounts start on Free at 10 QPS. Add credits to raise it to 20 QPS.

Top up your balance

API charges are deducted from your balance in real time.

Pay as you go

Charges are based on actual resource consumption (API calls, tokens).

All new users receive $5 in free balance upon registration.

Search Plans

Plan	Price	Image Search
Standard	$20 / month, $50 / quarter, $180 / year	1,000 / month
Plus	$100 / month, $1,000 / year	5,000 / month

Unlimited Web Search, no overage fees. Requests may queue at busy times; requests that can’t be served aren’t charged. Full content ($0.5 / 1k results, no free results), extra Image Search, and other APIs are billed pay as you go. One plan at a time: a Search Plan or a QPS Plan. Available for personal accounts with prepaid billing.

QPS Plans

Free tier:

Plan	Web Search QPS	Monthly Price	Notes
Free	Up to 10 (20 after you add credits)	$0	Default tier for every new account

Broad Search and Pulse Search share the Web Search QPS limit. QPS plans, with guaranteed throughput and SLA:

Plan	Web Search QPS	Monthly Price	Best For
Builder	Up to 50	~~$2,999~~ $2,099 (30% off)	Early-stage teams going to production
Pro	Up to 200	$13,999	Growing production workloads
Max	Up to 500	$33,999	High-volume production at scale

Broad Search and Pulse Search share the Web Search QPS limit. Embedding limits, in tokens per minute (TPM):

Plan	Embedding TPM	VL Embedding TPM
Free	1,000,000	200,000
Builder	2,500,000	500,000
Pro	10,000,000	2,000,000
Max	25,000,000	5,000,000

API Pricing

Octen Pulse

Octen Pulse includes Pulse Search.

API	Search API Call	Full Content
Pulse Search (lite)	$0.1 / 1k calls	-
Pulse Search (standard)	$0.2 / 1k calls	$0.5 / 1k results

Each call is billed at the mode in meta.usage.billed_mode. A standard call is billed as lite when page details are not available for any result. The full content of the first result per search is free; only additional results are billed.

Octen Fast

Octen Fast includes Broad Search, Web Search, Image Search, and Video Search.

API	Search API Call	Full Content
Broad Search	$5 $1 / 1k calls (80% off)	$0.5 / 1k results
Web Search	$5 $1 / 1k calls (80% off)	$0.5 / 1k results
Image Search	$2 / 1k calls	-
Video Search	$5 / 1k calls	-

A single Broad Search call may include multiple Search API calls. For Broad Search and Web Search, the full content of the first 10 results per search is free; only additional results are billed.

Octen Premier

Octen Premier includes News Search, Business Search, and Place Search.

API	Search API Call	Full Content
News Search	$3 / 1k calls	$0.5 / 1k results
Business Search	$5 / 1k calls	$0.5 / 1k results
Place Search	$5 / 1k calls	$0.5 / 1k results

The full content of the first 10 results per search is free; only additional results are billed.

Extract

Resource	Price (USD)
Standard mode	$1 / 1k successful URLs
Advanced mode	$2.5 / 1k successful URLs

Each URL is billed at the mode it was processed in, including URLs handled by auto mode. Failed URLs are not billed.

Embedding

Model	Price (USD / 1M tokens)	Best For
octen-embedding-8b	$0.07	Best accuracy
octen-embedding-4b	$0.04	Balanced performance and cost
octen-embedding-0.6b	$0.01	High-volume and low-cost

VL Embedding

Billed by input tokens. Text and multimodal (image / video) inputs are priced differently:

Model	Text (USD / 1M tokens)	Image / Video (USD / 1M tokens)
octen-vl-embedding	$0.05	$0.12
octen-vl-embedding-large	$0.10	$0.25

Application Pricing

Answer

Charges include Search fees (based on the number of search queries) and model usage fees (based on token consumption).

Search Agent

Billed per task, based on the selected tier.

Tier	Price (USD / task)
low	$0.05
medium	$0.2
high	$0.5
auto	Based on actual usage

Deep Research

Billed per request, based on the selected tier.

Tier	Price (USD / request)
lite	$0.2
standard	$1
pro	$2.5
pro-visual	$3

Grounded Generation

Billed per generated output, based on the modality.

Modality	Price (USD)
Image	$0.25 / image
Video	$1 / video

Auto Search

Charges include Search fees (based on the number of search queries) and model usage fees (based on token consumption). With octen_multimodal_search, web, image, and video searches are billed separately, at the Web Search, Image Search, and Video Search rates. Token fees:

Model	Input (USD / 1M tokens)	Output (USD / 1M tokens)	Cache Read (USD / 1M tokens)	Cache Write (USD / 1M tokens)
openai/gpt-6.1-sol	$2 (≤272k) / $4 (>272k)	$10 (≤272k input) / $15 (>272k input)	$0.1 (≤272k) / $0.2 (>272k)	$2.5 (≤272k) / $5 (>272k)
openai/gpt-6.1-terra	$1 (≤272k) / $2 (>272k)	$5 (≤272k input) / $7.5 (>272k input)	$0.05 (≤272k) / $0.1 (>272k)	$1.25 (≤272k) / $2.5 (>272k)
openai/gpt-6-astra	$10 (≤272k) / $20 (>272k)	$50 (≤272k input) / $75 (>272k input)	$1 (≤272k) / $2 (>272k)	$12.5 (≤272k) / $25 (>272k)
openai/gpt-5.6-sol	$4 (≤272k) / $8 (>272k)	$20 (≤272k input) / $30 (>272k input)	$0.4 (≤272k) / $0.8 (>272k)	$5 (≤272k) / $10 (>272k)
openai/gpt-5.6-terra	$2 (≤272k) / $4 (>272k)	$12 (≤272k input) / $18 (>272k input)	$0.2 (≤272k) / $0.4 (>272k)	$2.5 (≤272k) / $5 (>272k)
openai/gpt-5.6-luna	$0.2 (≤272k) / $0.4 (>272k)	$1.2 (≤272k input) / $1.8 (>272k input)	$0.02 (≤272k) / $0.04 (>272k)	$0.25 (≤272k) / $0.5 (>272k)
openai/gpt-5.4	$2.5	$15	$0.25	-
anthropic/claude-fable-5.1	$10	$50	$0.25	$12.5 (5m) / $20 (1h)
anthropic/claude-fable-5	$10	$50	$1	$12.5 (5m) / $20 (1h)
anthropic/claude-opus-5.5	$4	$20	$0.2	$5 (5m) / $8 (1h)
anthropic/claude-opus-5	$5	$25	$0.5	$6.25 (5m) / $10 (1h)
anthropic/claude-opus-4.8	$5	$25	$0.5	$6.25 (5m) / $10 (1h)
anthropic/claude-opus-4.6	$5	$25	$0.5	$6.25 (5m) / $10 (1h)
anthropic/claude-sonnet-5.5	$2	$10	$0.1	$2.5 (5m) / $4 (1h)
anthropic/claude-sonnet-5	$2	$10	$0.2	$2.5 (5m) / $4 (1h)
anthropic/claude-sonnet-4.6	$3	$15	$0.3	$3.75 (5m) / $6 (1h)
anthropic/claude-haiku-5.5	$0.1 (≤100k) / $0.5 (>100k)	$0.5 (≤100k input) / $2.5 (>100k input)	$0.01 (≤100k) / $0.05 (>100k)	≤100k: $0.125 (5m) / $0.2 (1h); >100k: $0.625 (5m) / $1 (1h)
anthropic/claude-haiku-4.5	$1	$5	$0.1	$1.25 (5m) / $2 (1h)
google/gemini-4-argon	$4	$20	$0.2	-
google/gemini-3.8-flash	$0.75	$3.75	$0.075	-
google/gemini-3.5-flash	$1.5	$9	$0.15	-
google/gemini-3.5-flash-lite	$0.3	$2.5	$0.03	-
google/gemini-3.1-pro-preview	$2 (≤200k) / $4 (>200k)	$12 (≤200k input) / $18 (>200k input)	$0.2 (≤200k) / $0.4 (>200k)	-
google/gemini-3.1-flash-lite	$0.25	$1.5	$0.025	-
google/gemini-3-flash-preview	$0.5	$3	$0.05	-
moonshotai/kimi-k3.1-pro	$2	$10	$0.2	-
moonshotai/kimi-k3	$3	$15	$0.3	-
minimax/minimax-m3.1-flash	$0.15	$0.6	$0.015	-
minimax/minimax-m3	$0.3	$1.2	$0.06	-
qwen/qwen3.6-plus	$0.5 (≤256k) / $2 (>256k)	$3 (≤256k input) / $6 (>256k input)	$0.05	$0.625 (5m)
deepseek/deepseek-v4.1-flash-1017	$0.3	$1.2	$0.006	-
deepseek/deepseek-v4-pro-0813	$1.32	$3.96	$0.044	-
deepseek/deepseek-v4-pro	$1.74	$3.48	$0.145	-
deepseek/deepseek-v4-flash-0731	$0.14	$0.28	$0.028	-

Image generation token fees:

Model	Text Input (USD / 1M tokens)	Text Output (USD / 1M tokens)	Image Input (USD / 1M tokens)	Image Output (USD / 1M tokens)
openai/gpt-image-2.6-flare	$5	-	$8	$30
openai/gpt-image-2.6-sunburst	$5	-	$8	$30
openai/gpt-image-2.5-flare	$5	-	$8	$30
openai/gpt-image-2.5-sunburst	$5	-	$8	$30
openai/gpt-image-2	$5	-	$8	$30
google/gemini-3-pro-image	$2	$12	$2	$120
google/gemini-3.1-flash-image	$0.50	$3	$0.50	$60

Video generation fees:

Model	Per Second (USD)	Per 1M Tokens (USD)	Reference Image (USD)
minimax/minimax-h3	768p: $0.08 / 2K: $0.13	-	First 5 free, then $0.04 each
bytedance/seedance-2.5	-	480p, 720p: $10.7 / 1080p: $11.7	-
google/veo-3.1	With audio: $0.4 / Video only: $0.2	-	-
google/veo-3.1-fast	With audio: 720p $0.1, 1080p $0.12 / Video only: 720p $0.08, 1080p $0.1	-	-
google/veo-3.1-lite	With audio: 720p $0.05, 1080p $0.08 / Video only: 720p $0.03, 1080p $0.05	-	-

Example cost: A single anthropic/claude-sonnet-4.6 completion that runs 3 search calls, reads 40,000 cached input tokens, adds 10,000 fresh input tokens, and returns 2,000 output tokens:

Component	Usage	Rate	Cost
Input tokens	10,000	$3 / 1M	$0.030
Cache read	40,000	$0.3 / 1M	$0.012
Output tokens	2,000	$15 / 1M	$0.030
Search calls	3	$1 / 1k	$0.003
Total			$0.075

Invoices & Receipts

Each top-up generates an invoice and receipt.
Monthly usage statements are available in the Billing dashboard.

Contact Us

For custom QPS plans, higher rate limits, or billing inquiries:

Get in Touch

Reach out to us at support@octen.ai

Last modified on November 10, 2026

Overview

Capabilities

Integrations

Resources

Overview

Search Plans

QPS Plans

API Pricing

Octen Pulse

Octen Fast

Octen Premier

Extract

Embedding

VL Embedding

Application Pricing

Answer

Search Agent

Deep Research

Grounded Generation

Auto Search

Invoices & Receipts

Contact Us

Get in Touch

​Overview

​Search Plans

​QPS Plans

​API Pricing

​Octen Pulse

​Octen Fast

​Octen Premier

​Extract

​Embedding

​VL Embedding

​Application Pricing

​Answer

​Search Agent

​Deep Research

​Grounded Generation

​Auto Search

​Invoices & Receipts

​Contact Us

Get in Touch

Overview

Search Plans

QPS Plans

API Pricing

Octen Pulse

Octen Fast

Octen Premier

Extract

Embedding

VL Embedding

Application Pricing

Answer

Search Agent

Deep Research

Grounded Generation

Auto Search

Invoices & Receipts

Contact Us