Mira AI
Video and image generation models in Mira AI
16 models for short video and 10 for images. Prices are in credits per result — no subscription, you pay for volume.
Video models
| Model | Provider | Clip length | Credits |
|---|---|---|---|
| Seedance 2 | ByteDance Seed | 5, 10 s | 51 |
| Seedance 2.5 | ByteDance Seed | 5, 10, 15, 30 s | 241 |
| Runway Gen-4.5 | Runway | 5, 10 s | 49 |
| Kling 3 | Kling AI | 5, 10, 15 s | 90 |
| Kling 3 Turbo | Kling AI | 5, 10, 15 s | 60 |
| Kling Motion | Kling AI | 5, 10, 15, 30 s | 180 |
| Veo 3.1 | 8 s | 34 | |
| Veo 3.1 Lite | 8 s | 24 | |
| Gemini Omni Flash | 8 s | 30 | |
| Veo 3.1 Quality | 8 s | 113 | |
| MiniMax H3 | MiniMax | 5, 10, 15 s | 73 |
| Grok Imagine 1.5 | xAI | 5, 10, 15 s | 75 |
| HappyHorse 1.1 | Wan · HappyHorse | 5, 10, 15 s | 59 |
| Wan 3.0 | Wan · HappyHorse | 5, 10, 15, 30 s | 210 |
| Wan 3.0 Prime | Wan · HappyHorse | 5, 10, 15, 30 s | 299 |
| Wan 2.7 | Wan · HappyHorse | 5, 10, 15 s | 76 |
Image models
GPT Image 2OpenAI · 3 creditsGPT Image 2.5 FlareOpenAI · 3 creditsGPT Image 2.5 SunburstOpenAI · 8 creditsNano Banana ProGoogle · 8 creditsNano Banana 2.1Google · 4 creditsFLUX.2 ProBlack Forest Labs · 3 creditsSeedream 4ByteDance Seed · 3 creditsSeedream 5 ProByteDance Seed · 4 creditsMuse ImageMeta · 1 creditIdeogram 4.5Ideogram · 6 credits
3D models
A textured mesh from a text prompt or photos — GLB plus FBX, OBJ, USDZ or STL — with optional PBR maps and a humanoid rig. Priced per model and quality tier.
| Model | Provider | Inputs | Formats | Credits |
|---|---|---|---|---|
| Hunyuan3D 3.1 | Tencent Hunyuan | text prompt · up to 4 photos | GLB, FBX, OBJ, USDZ | 14 |
| Meshy 7 | Meshy | text prompt · up to 4 photos | GLB, FBX, OBJ, USDZ | 43 |
| Trellis 2 | Microsoft Research | up to 4 photos | GLB | 11 |
| Rodin Fast | Hyper3D (Deemos) | text prompt · up to 5 photos | GLB, FBX, OBJ, USDZ, STL | 4 |
Audio models
Voice, music, sound effects, dubbing and captions by ElevenLabs. Audio is priced per unit of text or sound, such as characters, seconds or minutes, not per clip.
| Model | Type | Rate |
|---|---|---|
| Eleven v4 | Speech | 2 credits per 1,000 characters |
| Eleven v3 | Speech | 2 credits per 1,000 characters |
| Eleven Flash v2.5 | Speech | 1 credit per 1,000 characters |
| Eleven Music v2.5 | Music | 10 credits per 30 s |
| Eleven SFX v2 | Sound effects | 3 credits per generation |
| Kling Audio SFX | Sound effects | 3 credits per generation |
| Kling Audio Foley | Sound effects | 3 credits per generation |
| Eleven Voice Changer | Voice | 2 credits per second |
| Eleven Voice Isolator | Voice | 4 credits per minute |
| Eleven Dubbing | Dubbing | 4 credits per second |
| Scribe v2 | Transcription | 2 credits per minute |
| Eleven Voice Design v3 | Voice | 2 credits per 1,000 characters |
LLM models
Assistants running on these models generate straight from their own chat — through the Mira MCP connector.