Meter text, image, audio, and video generation with one credit balance. No subscriptions, no lock-in, and you see the per-model rates before you pay.
Credit value
1 credit = $0.01 USD
Included usage
100 free credits on signup
Volume savings
Up to 30% off past 1M credits
Pay only for the tokens you run across ccapi-route or ccapi-reasoner. Cache hits cost less automatically.
Cache hits trigger when we served the same prompt within 60 minutes.
SDXL, FLUX, ImaginePro, and Replicate models share a single per-image credit rate.
Streaming, dubbing, and Veo beta video rendering are priced by characters or seconds.
Video pricing moves to $0.08 / sec once Google exits beta.
Choose a simple free tier, predictable monthly allotments, or bespoke enterprise agreements.
Save ~2 months with annual billing.
Perfect for hobby projects and experiments.
$0/month
Ideal for startups and growing businesses.
$49/month
Tailored solutions for enterprise needs.
Custom
Forecast how credits translate into day-to-day workloads. Swap models freely without renegotiating pricing.
Weekend sprint with GPT-4o, SDXL visuals, and a narrated demo.
Estimated credits
210
Approx. cost
$2.10
Ship AI features to thousands of users with predictable costs.
Estimated credits
1420
Approx. cost
$14.20
Blend reasoning, audio responses, and Veo previews for internal copilots.
Estimated credits
4120
Approx. cost
$41.20
Predictable margins for teams that ship AI at scale.
Every provider inside CCAPI has published base pricing. Sort by the metric that matters to you.
| Model | Provider | Type | Input | Output | Image | Audio | Video |
|---|---|---|---|---|---|---|---|
Gemini 2.0 Flash (Experimental) google/gemini-2.0-flash-exp | Google AI | text | FREE | FREE | — | — | — |
Gemini 1.5 Flash google/gemini-1.5-flash | Google AI | text | $0.090 / 1M | $0.36 / 1M | — | — | — |
DeepSeek Chat deepseek/deepseek-chat | DeepSeek | text | $0.17 / 1M | $0.34 / 1M | — | — | — |
DeepSeek Coder deepseek/deepseek-coder | DeepSeek | text | $0.17 / 1M | $0.34 / 1M | — | — | — |
GPT-4o Mini openai/gpt-4o-mini | OpenAI | text | $0.18 / 1M | $0.72 / 1M | — | — | — |
Claude 3 Haiku anthropic/claude-3-haiku-20240307 | Anthropic | text | $0.30 / 1M | $1.50 / 1M | — | — | — |
DeepSeek V3 deepseek/deepseek-v3 | DeepSeek | text | $0.32 / 1M | $1.32 / 1M | — | — | — |
DeepSeek V3.2 (Experimental) deepseek/deepseek-v3.2-exp | DeepSeek | text | $0.32 / 1M | $1.32 / 1M | — | — | — |
GPT-3.5 Turbo openai/gpt-3.5-turbo | OpenAI | text | $0.60 / 1M | $1.80 / 1M | — | — | — |
Gemini 1.5 Pro google/gemini-1.5-pro | Google AI | text | $1.50 / 1M | $6.00 / 1M | — | — | — |
Claude 3.5 Sonnet anthropic/claude-3-5-sonnet-20241022 | Anthropic | text | $3.60 / 1M | $18.00 / 1M | — | — | — |
GPT-4o openai/gpt-4o | OpenAI | text | $6.00 / 1M | $18.00 / 1M | — | — | — |
GPT-4 Turbo openai/gpt-4-turbo | OpenAI | text | $12.00 / 1M | $36.00 / 1M | — | — | — |
Claude 3 Opus anthropic/claude-3-opus-20240229 | Anthropic | text | $18.00 / 1M | $90.00 / 1M | — | — | — |
Eleven Monolingual V1 elevenlabs/eleven_monolingual_v1 | ElevenLabs | audio | — | — | — | $0.36 / 1K chars | — |
Eleven Multilingual V2 elevenlabs/eleven_multilingual_v2 | ElevenLabs | audio | — | — | — | $0.72 / 1K chars | — |
Eleven Turbo V2 elevenlabs/eleven_turbo_v2 | ElevenLabs | audio | — | — | — | $0.18 / 1K chars | — |
ImaginePro Nova imaginepro/imagine-v1 | ImaginePro | image | — | — | $0.024 / image | — | — |
SDXL (Replicate) replicate/stability-ai/sdxl | Replicate | image | — | — | $0.012 / image | — | — |
SDXL 1.0 stabilityai/stable-diffusion-xl-1024-v1-0 | Stability AI | image | — | — | $0.048 / image | — | — |
Veo 1.0 veo/veo-1 | Google Veo | video | — | — | — | — | FREE |
1 credit always equals $0.01 USD. Every model charge is normalized to credits first so you can forecast usage across modalities.
If ccapi-route served an identical prompt within the past hour, we reuse the cached result and only charge the cache-hit input rate.
Yes. Add OpenAI, Anthropic, Google, or custom OpenRouter-compatible providers via the dashboard. We meter usage per key but consolidate billing.
Requests pause until you top up. Enterprise plans can enable auto-reload or invoiced billing so workloads never stop.
Need a bespoke pricing sheet or SOC 2 paperwork?
Our team will share detailed rate cards, migration guides, and help design routing strategies for your workload.