$ Pricing

Honest pricing. Just under official.

Roughly 15% below each provider’s official rate, per model — and top-up bonuses bring the effective discount to about 21%. Pay-as-you-go, per-token for chat and per-call for image and video. No subscription, no minimum — and you’re billed on true token counts, so what you’re charged matches what you actually used.

cat ./pricing.txt

Pay only for what you actually use.

Pre-paid wallet, no subscription and no minimum. Add $10 to get going; your balance never expires, and every charge maps to real, audited usage.

Starter

Trying it out

$10
  • Access to every genuine model
  • True per-call usage logs
  • Community & email support
  • No minimum, no credit card
Get an API key
Most popular

Builder

Shipping a product

$100
  • Honest token billing on every call
  • 10 isolated API keys
  • Auto-recharge · IP allowlist
  • Priority email support
Top up $100

Scale

Running production traffic

$1000
  • Monitored, fail-fast routing
  • Unlimited API keys
  • Webhooks · monthly invoices
  • Dedicated Slack/Discord support
Top up $1000

Enterprise

High-volume scale

$5000
  • Everything in Scale
  • Dedicated routing capacity
  • Custom rate limits & SLA
  • Dedicated account manager
Top up $5000
$ Per-model pricing

Every model. Every rate. In the open.

Text · Text

7 models
ls ./models/text
ModelProviderInput priceOutput priceBilling unitvs Official
Claude Opus 4.7
Anthropic$4.25$21.25per 1M tokens15%
Claude Opus 4.6
Anthropic$4.25$21.25per 1M tokens15%
Claude Sonnet 4.6
Anthropic$2.55$12.75per 1M tokens15%
Claude Sonnet 4.5
Anthropic$2.55$12.75per 1M tokens15%
Claude Haiku 4.5
Anthropic$0.85$4.25per 1M tokens15%
Gemini 2.5 Pro
Google$1.0625$8.50per 1M tokens15%
Gemini 2.5 Flash
Google$0.255$2.125per 1M tokens15%

Image · Image

6 models
ls ./models/image
ModelProviderFlat priceBilling unitvs Official
Nano Banana
Google$0.024per image38%
Nano Banana 2
Google$0.042+per image37%
Resolution1K $0.04237%2K $0.06338%4K $0.09438%
Nano Banana Pro
Google$0.084+per image37%
Resolution1K / 2K $0.08437%4K $0.1538%
GPT-Image-2
OpenAI$0.079per image38%
Resolution1K $0.07938%2K $0.07938%4K $0.07938%
Nano Banana Edit
Google$0.0273per image30%
GPT-Image-2 Edit
OpenAI$0.0886per image30%
Resolution1K $0.088630%2K $0.088630%4K $0.088630%

Video · Video

3 models
ls ./models/video
ModelProviderFlat priceBilling unitvs Official
Veo 3 Fast
Google$0.25+per video38%
Resolution720p $0.2538%1080p $0.3138%4K $0.7538%
Veo 3 Quality
Google$1.20+per video38%
Resolution720p $1.238%1080p $1.238%4K $1.838%
Veo 3 Lite
Google$0.15+per video38%
Resolution720p $0.1538%1080p $0.2438%
$ Compare

Brievio vs cheap resellers vs going direct

If a gateway is 80% under list, ask where the capacity comes from. Here’s how the discounted-official tier compares.

diff resellers brievio
What mattersBrievioCheap / gray-market resellersGoing direct
Genuine first-party models
max_tokens, tools & caching honored
True token counts, never inflated
Monitored, fail-fast routing
Failed requests never billed
Stable, enterprise-grade supply$5
Text, image & video on one key
Priced just under official
$ Prompt caching

Cache reads at a fraction of the input rate.

Where the provider supports it, cache reads bill at 10% of input on Anthropic models and 20% on OpenAI and Gemini. Cache writes bill at the plain input rate — Brievio doesn’t pass through Anthropic’s upstream write surcharge. Add cache_control to your system prompt and these rates apply automatically.

cat ./cache-rates.txt
ModelInputCache readRatio
Claude Opus 4.7
Anthropic
$4.25$0.850.20×
Claude Opus 4.6
Anthropic
$4.25$0.850.20×
Claude Sonnet 4.6
Anthropic
$2.55$0.510.20×
Claude Sonnet 4.5
Anthropic
$2.55$0.510.20×
Claude Haiku 4.5
Anthropic
$0.85$0.170.20×
Gemini 2.5 Pro
Google
$1.06$0.21250.20×
Gemini 2.5 Flash
Google
$0.255$0.0510.20×

Full guide: how to enable it, dashboard metrics, affinity routing.Read the prompt-caching guide

$ brievio enterprise --contact

Need dedicated capacity, custom SLAs or invoiced billing?

Higher-volume teams can reserve dedicated routing capacity, agree custom SLAs and rate limits, and move to monthly invoiced billing. Tell us your traffic shape and we’ll size it with you.