Pay for output, not for seats.
One balance covers every model. Credits are deducted per unit of output — a second of video, an image, a thousand characters of speech, a million tokens.
Pricing
Prepay credits. Spend them anywhere.
One credit is $0.005 of API usage on any model in the market. The rate is identical in every pack — no seats, no monthly minimum, no expiry.
Starter
Try any model.
$5one-off
1,000 credits
- All models, no gating
- Unlimited API keys
- Full request logs + CSV export
- Webhooks and async jobs
- Same rate limits and priority
- Credits never expire
Builder
Side projects.
$10one-off
2,000 credits
- All models, no gating
- Unlimited API keys
- Full request logs + CSV export
- Webhooks and async jobs
- Same rate limits and priority
- Credits never expire
Spending more than $2,000 a month? Talk to us about committed-use rates →
Per-model rates
Rates below are what we charge; credits convert at $0.005 each.
AI Text API
| Model | Provider | Credits / unit | Our price | Official price | Discount | Latency |
|---|---|---|---|---|---|---|
| GPT-5.2 | OpenAI | 678per 1M input tokens | $3.39 | $4.80 | −29% | ~3s |
| GPT-5.2 Mini | OpenAI | 91per 1M input tokens | $0.455 | $0.640 | −29% | ~1s |
| o5 Reasoning | OpenAI | 1,920per 1M input tokens | $9.60 | $13.60 | −29% | ~22s |
| Claude Opus 4.6 | Anthropic | 1,412per 1M input tokens | $7.06 | $10.00 | −29% | ~4s |
| Claude Sonnet 4.6 | Anthropic | 283per 1M input tokens | $1.42 | $2.00 | −29% | ~2s |
| Claude Haiku 4.5 | Anthropic | 74per 1M input tokens | $0.370 | $0.520 | −29% | ~1s |
| Gemini 3 Pro | 509per 1M input tokens | $2.54 | $3.60 | −29% | ~3s | |
| Gemini 3 Flash | 85per 1M input tokens | $0.425 | $0.600 | −29% | ~1s | |
| Gemini Omni Flash | 119per 1M input tokens | $0.595 | $0.840 | −29% | ~1s | |
| Grok 4.5 | xAI | 424per 1M input tokens | $2.12 | $3.00 | −29% | ~3s |
| DeepSeek V4 | DeepSeek | 51per 1M input tokens | $0.255 | $0.360 | −29% | ~2s |
| DeepSeek R2 | DeepSeek | 96per 1M input tokens | $0.480 | $0.680 | −29% | ~12s |
| Qwen3 Max | Alibaba | 170per 1M input tokens | $0.850 | $1.20 | −29% | ~3s |
| Qwen3 Coder | Alibaba | 119per 1M input tokens | $0.595 | $0.840 | −29% | ~3s |
| Kimi K3 | Moonshot AI | 108per 1M input tokens | $0.540 | $0.760 | −29% | ~4s |
| GLM-5 | Z.ai | 60per 1M input tokens | $0.300 | $0.420 | −29% | ~2s |
| Llama 5 405B | Meta | 153per 1M input tokens | $0.765 | $1.08 | −29% | ~5s |
| Llama 5 70B | Meta | 40per 1M input tokens | $0.200 | $0.280 | −29% | ~2s |
| Mistral Large 3 | Mistral | 198per 1M input tokens | $0.990 | $1.40 | −29% | ~2s |
| Codestral 3 | Mistral | 34per 1M input tokens | $0.170 | $0.240 | −29% | ~1s |
| Command A | Cohere | 128per 1M input tokens | $0.640 | $0.900 | −29% | ~2s |
| Embed 4 | Cohere | 6per 1M input tokens | $0.030 | $0.040 | −25% | ~1s |
AI Video API
| Model | Provider | Credits / unit | Our price | Official price | Discount | Latency |
|---|---|---|---|---|---|---|
| Veo 3.1 | 91per second of video | $0.455 | $0.640 | −29% | ~95s | |
| Veo 3 Fast | 34per second of video | $0.170 | $0.240 | −29% | ~38s | |
| Kling 3 Turbo | Kling | 26per second of video | $0.130 | $0.180 | −28% | ~42s |
| Kling 3.0 | Kling | 51per second of video | $0.255 | $0.360 | −29% | ~110s |
| Kling 2.6 Motion Control | Kling | 43per second of video | $0.215 | $0.300 | −28% | ~88s |
| Seedance 2.5 | ByteDance | 32per second of video | $0.160 | $0.220 | −27% | ~65s |
| Seedance 2.0 Mini | ByteDance | 13per second of video | $0.065 | $0.090 | −28% | ~24s |
| Wan 2.7 | Alibaba | 20per second of video | $0.100 | $0.140 | −29% | ~55s |
| Wan 2.6 VACE | Alibaba | 27per second of video | $0.135 | $0.190 | −29% | ~62s |
| Hailuo 2.3 | MiniMax | 29per second of video | $0.145 | $0.200 | −28% | ~70s |
| Hailuo Live 2 | MiniMax | 23per second of video | $0.115 | $0.160 | −28% | ~45s |
| Sora 2 | OpenAI | 80per second of video | $0.400 | $0.560 | −29% | ~120s |
| Runway Gen-5 | Runway | 57per second of video | $0.285 | $0.400 | −29% | ~80s |
| Luma Ray 3 | Luma | 37per second of video | $0.185 | $0.260 | −29% | ~58s |
| PixVerse V6 | PixVerse | 17per second of video | $0.085 | $0.120 | −29% | ~40s |
| Topaz Video Upscale | Topaz | 12per second of video | $0.060 | $0.080 | −25% | ~30s |
AI Image API
| Model | Provider | Credits / unit | Our price | Official price | Discount | Latency |
|---|---|---|---|---|---|---|
| Nano Banana 2 | 10per image | $0.050 | $0.064 | −22% | ~9s | |
| Flux 2 Pro | Black Forest Labs | 12per image | $0.060 | $0.080 | −25% | ~12s |
| Flux 2 Flex | Black Forest Labs | 4per image | $0.020 | $0.024 | −17% | ~4s |
| Flux 2 Kontext | Black Forest Labs | 10per image | $0.050 | $0.070 | −29% | ~10s |
| Midjourney v7 | Midjourney | 16per image | $0.080 | $0.110 | −27% | ~45s |
| GPT Image 2 | OpenAI | 14per image | $0.070 | $0.096 | −27% | ~18s |
| Seedream 5 | ByteDance | 8per image | $0.040 | $0.056 | −29% | ~8s |
| Grok Imagine | xAI | 8per image | $0.040 | $0.050 | −20% | ~7s |
| Ideogram v4 | Ideogram | 9per image | $0.045 | $0.060 | −25% | ~11s |
| Recraft V4 | Recraft | 11per image | $0.055 | $0.076 | −28% | ~14s |
| Stable Image Ultra | Stability AI | 7per image | $0.035 | $0.044 | −20% | ~9s |
| Topaz Image Upscale | Topaz | 5per image | $0.025 | $0.030 | −17% | ~6s |
AI Audio API
| Model | Provider | Credits / unit | Our price | Official price | Discount | Latency |
|---|---|---|---|---|---|---|
| Suno v5 | Suno | 170per track | $0.850 | $1.20 | −29% | ~60s |
| ElevenLabs v3 | ElevenLabs | 9per 1K characters | $0.045 | $0.060 | −25% | ~2s |
| ElevenLabs Scribe | ElevenLabs | 2per minute of audio | $0.010 | $0.0080 | −0% | ~3s |
| Gemini 3 Flash TTS | 4per 1K characters | $0.020 | $0.028 | −29% | ~2s | |
| MiniMax Speech 3 | MiniMax | 6per 1K characters | $0.030 | $0.036 | −17% | ~1s |
Questions developers actually ask.
Is this the same model, or a distilled copy?+
The same weights, served by the provider. We proxy the request, normalise the request and response shape, and bill you in credits. Output is identical to calling the provider directly.
How can the prices be lower?+
We commit to volume across every provider we resell and keep a thin margin on top — typically under 20%. You get bulk pricing without the bulk commitment.
Do credits expire?+
No. Prepaid credits stay on your balance until you spend them, and unused credits are refundable within 30 days of purchase.
What happens when a provider goes down?+
Requests fail over to a healthy region automatically. If a model is unavailable everywhere, the call returns a typed 503 and no credits are deducted.
Can I keep using the OpenAI or Anthropic SDK?+
For text models, yes — change the base URL and the key and everything else works, including streaming and tool use. Video, image and audio use our own REST resources.
Where is my data stored?+
Prompts and outputs are retained only as long as your log window (30 days to 1 year by plan), and are never used for training. Zero-retention mode is available on request.