Pricing

Transparent. Cheaper than direct.

Pay-as-you-go. No subscription, no minimum, no surprises. Each model’s price is published — compare against the upstream provider any time.

Top up & save

The more you pre-pay, the more you save.

Pre-paid wallet. $10 starts you up. No subscription, no minimum, balance never expires.

Starter

Just exploring

$10
  • Access to every model and endpoint
  • Per-call usage analytics
  • Email support
  • No subscription, no expiry — top up from $10
Sign up free
Most popular

Builder

Limited · +$10

Shipping a product

$100
  • $100 deposit = $110 credit
  • 10% bonus, limited time
  • Priority email support
  • Everything every account gets
Top up $100

Scale

Limited · +$250

Running production traffic

$1000
  • $1000 deposit = $1250 credit
  • 25% bonus, limited time
  • Priority email support
  • Everything every account gets
Top up $1000

Enterprise

Limited · +$2000

High-volume scale

$5000
  • $5000 deposit = $7000 credit
  • 40% bonus, limited time
  • Priority email support
  • Everything every account gets
Top up $5000

Included with every account

  • Unlimited API keys
  • Per-key monthly spend limits
  • Per-key IP allowlists
  • Auto-recharge from a saved card — any whole-dollar amount from $10, opt-in
  • Webhooks for image, video and music tasks
  • Usage API and CSV export
  • OpenAI-compatible and Anthropic Messages endpoints
Per-model pricing

Every model. Every price. Spelled out.

Text · Text

18 models
ModelProviderInput priceOutput priceBilling unitvs Official
Claude Fable 5Anthropic$7.00$35.00per 1M tokens30%+ OFF
Claude Opus 5Anthropic$2.00$10.00per 1M tokens60%+ OFF
Claude Opus 4.8Anthropic$2.50$12.50per 1M tokens50%+ OFF
Claude Opus 4.7Anthropic$2.00$10.00per 1M tokens60%+ OFF
Claude Opus 4.6Anthropic$2.00$10.00per 1M tokens60%+ OFF
Claude Sonnet 5Anthropic$2.00$10.00per 1M tokens
Claude Sonnet 4.6Anthropic$1.20$6.00per 1M tokens60%+ OFF
Claude Haiku 4.5Anthropic$0.40$2.00per 1M tokens60%+ OFF
Gemini 3.8 FlashGoogle$0.525$2.625per 1M tokens65%+ OFF
Gemini 3.7 FlashGoogle$0.525$2.625per 1M tokens65%+ OFF
Gemini 3.6 FlashGoogle$1.05$5.25per 1M tokens30%+ OFF
Gemini 3.1 ProGoogle$0.70$4.20per 1M tokens65%+ OFF
Gemini 2.5 FlashGoogle$0.09$0.75per 1M tokens70%+ OFF
GPT-6 AstraOpenAI$4.00$20.00per 1M tokens60%+ OFF
GPT-5.6 SolOpenAI$2.00$12.00per 1M tokens60%+ OFF
GPT-5.6 TerraOpenAI$0.70$4.20per 1M tokens65%+ OFF
GPT-5.6 LunaOpenAI$0.07$0.42per 1M tokens65%+ OFF
GPT-5.5OpenAI$2.00$12.00per 1M tokens60%+ OFF

Long prompts: past 272K input tokens, the whole request on GPT-6 Astra, GPT-5.6 Sol, GPT-5.6 Terra, GPT-5.6 Luna, GPT-5.5 bills at 2× input and 1.5× output — the vendors' own long-context tier.

Long prompts: past 200K input tokens, the whole request on Gemini 3.1 Pro bills at 2× input and 1.5× output — the vendors' own long-context tier.

Image · Image

9 models
ModelProviderSingle priceBilling unitvs Official
Nano BananaGoogle$0.0273per image30%+ OFF
Nano Banana 2Google$0.0469+per image30%+ OFF
Resolution1K $0.046930%2K $0.070730%4K $0.105730%
Nano Banana 2 LiteGoogle$0.0255per image25%+ OFF
Nano Banana ProGoogle$0.067+per image50%+ OFF
Resolution1K / 2K $0.06750%4K $0.1250%
GPT-Image-2OpenAI$0.0633per image50%+ OFF
Resolution1K $0.063350%2K $0.063350%4K $0.063350%
Ideogram v3Ideogram$0.0525+per image13%+ OFF
QualityTurbo $0.026213%Balanced $0.052513%Quality $0.07517%
Nano Banana EditGoogle$0.0273per image30%+ OFF
GPT-Image-2 EditOpenAI$0.0633per image50%+ OFF
Resolution1K $0.063350%2K $0.063350%4K $0.063350%
Ideogram v3 EditIdeogram$0.0525+per image13%+ OFF
QualityTurbo $0.026213%Balanced $0.052513%Quality $0.07517%

Video · Video

8 models
ModelProviderSingle priceBilling unitvs Official
Veo 3.1 FastGoogle$0.36+per video70%+ OFF
Resolution720p $0.3670%1080p $0.4265%4K $1.0855%
Veo 3.1 QualityGoogle$1.60+per video50%+ OFF
Resolution720p $1.650%1080p $1.650%4K $2.450%
Veo 3.1 LiteGoogle$0.18+per video60%+ OFF
Resolution720p $0.1860%1080p $0.22465%
Seedance 2ByteDance$0.246+per second of video
Resolution480p $0.114720p $0.2461080p $0.612
Seedance 2 FastByteDance$0.198+per second of video
Resolution480p $0.093720p $0.198
Seedance 2.5ByteDance$0.3784+per second of video
Resolution480p $0.1764720p $0.37841080p $0.7392
Seedance 2.0 MiniByteDance$0.0526+per second of video
Resolution480p $0.0245720p $0.0526
Wan 2.7Alibaba$0.096+per second of video4%+ OFF
Resolution720p $0.0964%1080p $0.1444%

Audio · Audio

2 models
ModelProviderSingle priceBilling unitvs Official
Suno V5Suno$0.09per song19%+ OFF
Suno V5.5Suno$0.09per song19%+ OFF
Compare

Kunavo vs going direct vs other aggregators

The honest version of why developers move to a unified gateway.

CapabilityKunavoOther aggregatorsGoing direct
OpenAI-compatible API
Stripe-native checkout
Text, image & video on one balance
Multi-provider failover
Failed requests never billed
Balance never expires
Global edge gateway
Fully self-serve, no sales call
Prompt caching

Cache reads at a fraction of input price.

Cache reads bill at 10% of input on Claude, GPT and Gemini. Cache writes bill at 1.25× input on Claude and GPT-5.6+, the plain input rate elsewhere. Both carry the same discount off the vendor's list as the model's input. Pass cache_control on your system prompt and these rates apply automatically.

ModelInputCache readCache writeRatio
Claude Fable 5
Anthropic
$7$0.7$8.750.10×
Claude Opus 5
Anthropic
$2$0.2$2.50.10×
Claude Opus 4.8
Anthropic
$2.5$0.25$3.130.10×
Claude Opus 4.7
Anthropic
$2$0.2$2.50.10×
Claude Opus 4.6
Anthropic
$2$0.2$2.50.10×
Claude Sonnet 5
Anthropic
$2$0.2$2.50.10×
Claude Sonnet 4.6
Anthropic
$1.2$0.12$1.50.10×
Claude Haiku 4.5
Anthropic
$0.4$0.04$0.50.10×
Gemini 3.8 Flash
Google
$0.525$0.0525$0.5250.10×
Gemini 3.7 Flash
Google
$0.525$0.0525$0.5250.10×
Gemini 3.6 Flash
Google
$1.05$0.105$1.050.10×
Gemini 3.1 Pro
Google
$0.7$0.07$0.70.10×
Gemini 2.5 Flash
Google
$0.09$0.009$0.090.10×
GPT-6 Astra
OpenAI
$4$0.4$50.10×
GPT-5.6 Sol
OpenAI
$2$0.2$2.50.10×
GPT-5.6 Terra
OpenAI
$0.7$0.07$0.8750.10×
GPT-5.6 Luna
OpenAI
$0.07$0.007$0.08750.10×
GPT-5.5
OpenAI
$2$0.2$20.10×

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

Need something the self-serve plan doesn’t cover?

High volume, procurement requirements, or a model we don’t list yet — write to us and we’ll tell you straight away whether we can do it.