Are you a developer keen on integrating AI capabilities into your projects, but find the cost of GPT-4 prohibitive or are operating within budget constraints? Look no further!
ShuttleAI API offers FREE access to gpt-4
, dall-e-3
, and over 100+ other models directly within the API, providing a highly efficient and reliable service!
Check out shuttle-2-turbo
for chat completions and shuttle-diffusion
for images generations!
To obtain your complimentary ShuttleAI API key, simply follow these steps:
- Register on Our Platform.
- Proceed to the Dashboard to generate your unique key.
For comprehensive instructions on utilizing our API effectively, refer to the ShuttleAI API documentation available at https://docs.shuttleai.app/.
Free | ID | Name | Description | Owner | Cost/Req | Supports Tools | Max Input Tokens | Max Output Tokens | Supports Image Input | Supports Audio Input | Endpoint |
---|---|---|---|---|---|---|---|---|---|---|---|
βοΈ | shuttle-2-turbo | Shuttle Turbo (64k) | ShuttleAI's largest LLM, updated mid 2024. Shuttle-2-turbo is comparable to GPT-4-1106-preview, and significantly stronger than GPT-4-0314. It demonstrates highly competitive performance and consistently outperforms all the existing state-of-the-art opensource models. | shuttleai | 1 | Yes | 65536 | 4096 | Yes | No | /v1/chat/completions |
βοΈ | shuttle-turbo | Shuttle Turbo (32k) | ShuttleAI's first turbo chat completion model with built in support for image recognition & web access released on February 17th, 2024. | shuttleai | 1 | No | 32768 | 4096 | Yes | No | /v1/chat/completions |
π° | gpt-4o-2024-05-13 | GPT-4 Omni | OpenAI's latest flagship model. Cheaper, faster, and smarter than GPT-4 Turbo. | openai | 4 | No | 128000 | 4096 | Yes | Yes | /v1/chat/completions |
π° | gpt-4-turbo-2024-04-09 | GPT 4 Turbo | The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. | openai | 4 | Yes | 128000 | 4096 | Yes | No | /v1/chat/completions |
π° | gpt-4-0125-preview | GPT 4 Turbo Preview (0125) | GPT-4 Turbo preview model intended to reduce cases of "laziness" where the model doesn't complete a task. | openai | 4 | Yes | 128000 | 4096 | No | No | /v1/chat/completions |
π° | gpt-4-1106-preview | GPT 4 Turbo Preview (1106) | GPT-4 Turbo preview model featuring improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. | openai | 4 | Yes | 128000 | 4096 | No | No | /v1/chat/completions |
π° | gpt-4-1106-vision-preview | GPT 4 Vision Preview (1106) | GPT-4 model with the ability to understand images, in addition to all other GPT-4 Turbo capabilities. This is a preview model, we recommend developers to now use gpt-4-turbo which includes vision capabilities. | openai | 4 | No | 128000 | 4096 | Yes | No | /v1/chat/completions |
βοΈ | gpt-4-0613 | GPT 4 (0613) | Snapshot of gpt-4 from June 13th 2023 with improved function calling support. | openai | 2 | Yes | 8192 | 4096 | No | No | /v1/chat/completions |
βοΈ | gpt-4-bing | GPT 4 (Bing) | GPT-4 model with improved instruction following, and web search provided by Bing. | bing | 1 | No | 29000 | 4000 | Yes | No | /v1/chat/completions |
βοΈ | gpt-4-turbo-bing | GPT 4 Turbo (Bing) | Faster GPT-4-Turbo model with improved instruction following, and fast web search provided by Bing. | bing | 2 | No | 32000 | 4000 | Yes | No | /v1/chat/completions |
π° | gpt-4-32k-0613 | GPT 4 32k (0613) | Snapshot of gpt-4-32k from June 13th 2023 with improved function calling support. This model was never rolled out widely in favor of GPT-4 Turbo. | openai | 3 | No | 32768 | 4096 | No | No | /v1/chat/completions |
βοΈ | gpt-3.5-turbo-0125 | GPT 3.5 Turbo (0125) | The latest GPT-3.5 Turbo model with higher accuracy at responding in requested formats and a fix for a bug which caused a text encoding issue for non-English language function calls. | openai | 2 | Yes | 16385 | 4096 | No | No | /v1/chat/completions |
βοΈ | gpt-3.5-turbo-1106 | GPT 3.5 Turbo (1106) | GPT-3.5 Turbo model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. | openai | 2 | Yes | 16385 | 4096 | No | No | /v1/chat/completions |
π° | claude-3-opus-20240229 | Claude 3 Opus | Most powerful model for highly complex tasks. | anthropic | 9 | No | 200000 | 4096 | Yes | No | /v1/chat/completions |
π° | claude-3-sonnet-20240229 | Claude 3 Sonnet | Ideal balance of intelligence and speed for enterprise workloads. | anthropic | 7 | No | 200000 | 4096 | Yes | No | /v1/chat/completions |
π° | claude-3-haiku-20240307 | Claude 3 Haiku | Fastest and most compact model for near-instant responsiveness. | anthropic | 3 | No | 200000 | 4096 | Yes | No | /v1/chat/completions |
π° | claude-2.1 | Claude 2.1 | Updated version of Claude 2 with improved accuracy. | anthropic | 7 | No | 200000 | 4096 | No | No | /v1/chat/completions |
π° | claude-2.0 | Claude 2 | Predecessor to Claude 3, offering strong all-round performance. | anthropic | 6 | No | 100000 | 4096 | No | No | /v1/chat/completions |
π° | claude-instant-1.2 | Claude Instant v1.2 | Anthhropic's small and fast model, a predecessor of Claude Haiku. | anthropic | 3 | No | 100000 | 4096 | No | No | /v1/chat/completions |
π° | claude-instant-1.1 | Claude Instant v1.1 | Anthhropic's small and fast model, a predecessor of Claude Haiku. | anthropic | 2 | nan | nan | nan | nan | nan | /v1/chat/completions |
βοΈ | claude-instant-1.0 | Claude Instant v1.0 | Anthhropic's small and fast model, a predecessor of Claude Haiku. | anthropic | 2 | No | 100000 | 4096 | No | No | /v1/chat/completions |
π° | meta-llama-3-70b-instruct | Llama 3 70b Instruct | Meta's latest class of model (Llama 3) launched with a variety of sizes & flavors. This 70B instruct-tuned version was optimized for high quality dialogue usecases. | meta | 2 | No | 8192 | 4096 | No | No | /v1/chat/completions |
It has demonstrated strong performance compared to leading closed-source models in human evaluations. | |||||||||||
To read more about the model release, click here. Usage of this model is subject to Meta's Acceptable Use Policy. | |||||||||||
π° | meta-llama-3-8b-instruct | Llama 3 8b Instruct | Meta's latest class of model (Llama 3) launched with a variety of sizes & flavors. This 8B instruct-tuned version was optimized for high quality dialogue usecases. | meta | 1 | No | 8192 | 4096 | No | No | /v1/chat/completions |
It has demonstrated strong performance compared to leading closed-source models in human evaluations. | |||||||||||
To read more about the model release, click here. Usage of this model is subject to Meta's Acceptable Use Policy. | |||||||||||
π° | llama-3-sonar-large-32k-online | Llama 3 Sonar Large 32k Online | From perplexity labs, large llama 3 32k with live web search. | perplexitylabs | 2 | No | 32768 | 4096 | No | No | /v1/chat/completions |
π° | llama-3-sonar-small-32k-online | Llama 3 Sonar Small 32k Online | From perplexity labs, small llama 3 32k with live web search. | perplexitylabs | 2 | No | 32768 | 4096 | No | No | /v1/chat/completions |
π° | llama-3-sonar-large-32k-chat | Llama 3 Sonar Large 32k Chat | From perplexity labs, large llama 3 32k. | perplexitylabs | 2 | No | 32768 | 4096 | No | No | /v1/chat/completions |
π° | llama-3-sonar-small-32k-chat | Llama 3 Sonar Small 32k Chat | From perplexity labs, small llama 3 32k. | perplexitylabs | 2 | No | 32768 | 4096 | No | No | /v1/chat/completions |
π° | blackbox | Blackbox AI | The Blackbox AI model (amazing with coding and tasks in general), in API form. | blackbox | 1 | No | N/A | N/A | Yes | No | /v1/chat/completions |
π° | blackbox-code | BlackBox Code | The Blackbox AI model (amazing with coding), in API form. | blackbox | 1 | No | N/A | N/A | Yes | No | /v1/chat/completions |
βοΈ | wizardlm-2-8x22b | WizardLM 2 8x22B | WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model. It demonstrates highly competitive performance compared to those leading proprietary models. | microsoft | 3 | Yes | 65536 | 4096 | No | No | /v1/chat/completions |
βοΈ | wizardlm-2-70b | WizardLM 2 70b | WizardLM-2 7B is the smaller variant of Microsoft AI's latest Wizard model. It is the fastest and achieves comparable performance with existing 10x larger open-source leading models | microsoft | 2 | No | 32768 | 4096 | No | No | /v1/chat/completions |
βοΈ | dolphin-2.6-mixtral-8x7b | Dolphin 2.6 Mixtral 8x7B | The Dolphin 2.6 Mixtral 8x7b model is a finetuned version of the Mixtral-8x7b model, trained on a variety of data including coding data, for 3 days on 4 A100 GPUs. It is uncensored and requires trust_remote_code. The model is very obedient and good at coding, but not DPO tuned. The dataset has been filtered for alignment and bias. The model is compliant with user requests and can be used for various purposes such as generating code or engaging in general chat. | cognitivecomputations | 1 | No | 32768 | 32768 | No | No | /v1/chat/completions |
π° | codestral-latest | Codestral Latest | Mistral's latest code model. | mistral | 1 | No | 32768 | 4096 | No | No | /v1/chat/completions |
π° | mistral-large | Mistral Large | Mistral's Latest and Largest Model. | mistralai | 5 | No | 32768 | 8192 | No | No | /v1/chat/completions |
π° | mistral-next | Mistral Next | Mistral's prototype extra concision Model. | mistralai | 4 | No | 32768 | 4096 | No | No | /v1/chat/completions |
βοΈ | mistral-medium | Mistral Medium | Mistral's Medium Model. | mistralai | 4 | No | 32768 | 4096 | No | No | /v1/chat/completions |
π° | mistral-small | Mistral Small | Mistral's Small Model. | mistralai | 4 | No | 32768 | 4096 | No | No | /v1/chat/completions |
π° | mistral-tiny | Mistral Tiny | Mistral's Tiny Model. | mistralai | 3 | No | 32768 | 4096 | No | No | /v1/chat/completions |
βοΈ | mixtral-8x7b-instruct-v0.1 | Mixtral 8x7b Instruct | The Mixtral-8x7B Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts. The Mixtral-8x7B outperforms Llama 2 70B on most benchmarks tested. | mistralai | 1 | No | 32768 | 32768 | No | No | /v1/chat/completions |
βοΈ | mixtral-8x22b-instruct-v0.1 | Mixtral 8x22b Instruct | The Mixtral-8x22B Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts. The Mixtral-8x22B outperforms Llama 2 70B on most benchmarks tested. | mistralai | 3 | No | 32768 | 32768 | No | No | /v1/chat/completions |
βοΈ | mistral-7b-instruct-v0.2 | Mistral 7B Instruct 2 | A 7.3B parameter model that outperforms Llama 2 13B on all benchmarks, with optimizations for speed and context length. | mistralai | 1 | Yes | 32768 | 8192 | No | No | /v1/chat/completions |
This is v0.2 of Mistral 7B Instruct. | |||||||||||
βοΈ | mistral-7b-instruct-v0.1 | Mistral 7B Instruct | A 7.3B parameter model that outperforms Llama 2 13B on all benchmarks, with optimizations for speed and context length. | mistralai | 1 | No | 32768 | 32768 | No | No | /v1/chat/completions |
This is v0.1 of Mistral 7B Instruct. | |||||||||||
βοΈ | nous-hermes-2-mixtral-8x7b | Nous Hermes 2 Mixtral 8x7B | The Nous Hermes 2 Mixtral 8x7B model is a finetuned version of the Mixtral-8x7b model, trained on a variety of data including coding data, for 3 days on 4 A100 GPUs. It is uncensored and requires trust_remote_code. The model is very obedient and good at coding, but not DPO tuned. The dataset has been filtered for alignment and bias. The model is compliant with user requests and can be used for various purposes such as generating code or engaging in general chat. | nous-hermes | 3 | No | 32768 | 32768 | No | No | /v1/chat/completions |
π° | gemini-1.5-pro-latest | Gemini 1.5 Pro | Mid-size multimodal model that supports up to 1 million tokens. | 5 | Yes | 1048576 | 8192 | Yes | Yes | /v1/chat/completions | |
π° | gemini-1.0-pro-latest | Gemini 1.0 Pro Latest | The best model for scaling across a wide range of tasks. This is the latest model. | 1 | Yes | 30720 | 2048 | Yes | No | /v1/chat/completions | |
π° | gemini-1.0-pro-vision | Gemini 1.0 Pro Vision | The best image understanding model to handle a broad range of applications. | 1 | No | 12288 | 4096 | Yes | No | /v1/chat/completions | |
π° | lzlv-70b | lzlv 70B | A Mythomax/MLewd_13B-style merge of selected 70B models A multi-model merge of several LLaMA2 70B finetunes for roleplaying and creative work. The goal was to create a model that combines creativity with intelligence for an enhanced experience. | unknown | 1 | No | 4096 | 4096 | No | No | /v1/chat/completions |
π° | figgs-rp | Figgs RP | Figgs RP is from figgs.ai. Great AI, great RP. | figgsai | 1 | No | 4096 | 4096 | No | No | /v1/chat/completions |
π° | cinematika-7b | Cinematika 7B | Cinematika 7B is a large language model trained on a variety of data including coding data, for 3 days on 4 A100 GPUs. It is uncensored and requires trust_remote_code. The model is very obedient and good at coding, but not DPO tuned. The dataset has been filtered for alignment and bias. The model is compliant with user requests and can be used for various purposes such as generating code or engaging in general chat. | cinematika | 1 | No | 8000 | 8000 | No | No | /v1/chat/completions |
βοΈ | shuttle-diffusion | Shuttle Diffusion | Shuttle-Diffusion is our newest Shuttle hosted image model, surpassing SDXL, Playground v2, PixArt-a, DALL-E 3, and Midjourney 5.2. It generates images in ~4 seconds, hosted on our A100 (80GB) server, and is available for free. | shuttleai | 1 | nan | nan | nan | nan | nan | /v1/images/generations |
π° | dall-e-3 | DALL-E 3 | DALL-E 3 is a model that generates images from text. | openai | 5 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | sdxl | SDXL | The original SD-XL model from stabilityai. | stabilityai | 1 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | sdxl-emoji | SDXL Emoji | SDXL finetuned on Apple emojis. | stabilityai/fofr | 1 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | dreamshaper-xl | Dreamshaper XL | Dreamshaper XL is an excellent uncensored text to imagine model. | stabilityai | 3 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | juggernaut-xl | Juggernaut XL | Juggernaut SDXL model. | stabilityai | 2 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | dynavision-xl | Dynavision XL | Dynavision XL model from stabilityai. | stabilityai | 2 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | realism-engine-xl | Realism Engine XL | Realism Engine XL model for high fidelity image generation. | stabilityai | 2 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | sdxl-inpainting | SDXL Inpainting | Inpainting model based on the SDXL framework. | stabilityai | 4 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | turbovision-xl | Turbovision XL | Turbovision XL, an advanced image generation model. | stabilityai | 2 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | kandinsky-2.2 | Kandinsky 2.2 | Kandinsky 2.2 by Sberbank. | sberbank | 1 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | kandinsky-2 | Kandinsky 2 | Kandinsky 2 by Sberbank. | sberbank | 1 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | stable-diffusion-2.1 | Stable Diffusion 2.1 | Stable Diffusion version 2.1 from stabilityai. | stabilityai | 1 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | stable-diffusion-1.5 | Stable Diffusion 1.5 | Stable Diffusion version 1.5 from stabilityai. | stabilityai | 1 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | playground-v2.5 | Playground v2.5 | A ShuttleAI model. | playgroundai | 4 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | dreamshaper-v8 | Dreamshaper v8 | Dreamshaper v8 is an excellent uncensored text to imagine model. | stabilityai | 1 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | rev-animated | Rev Animated | Rev Animated model for dynamic animations. | stabilityai | 1 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | anything-v5 | Anything V5 | Versatile generation model for various images. | stabilityai | 1 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | absolutereality-v1.8.1 | Absolute Reality V1.8.1 | High fidelity reality simulation model. | stabilityai | 1 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | realisticvision-v5 | Realistic Vision V5 | Advanced realism in visual generation. | stabilityai | 1 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | timeless-v1 | Timeless V1 | Creates timeless artistic images. | stabilityai | 1 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | portrait-v1 | Portrait V1 | Specialized in generating detailed portraits. | stabilityai | 1 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | analog | Analog | Emulates analog photographic techniques. | stabilityai | 1 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | anything-v3 | Anything V3 | Flexible image generation for a variety of themes. | stabilityai | 1 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | anything-v4 | Anything V4 | Enhanced version for broader image generation capabilities. | stabilityai | 1 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | abyssorangemix | Abyss Orange Mix | Unique blend of deep learning models for vibrant artistic output. | stabilityai | 1 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | deliberate | Deliberate | Crafts images with a deliberate artistic touch. | stabilityai | 1 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | dreamlike-v1 | Dreamlike V1 | Generates ethereal and dream-like images. | stabilityai | 1 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | dreamlike-v2 | Dreamlike V2 | Second version with enhanced capabilities for dreamy visuals. | stabilityai | 1 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | dreamshaper-5 | Dreamshaper 5 | Fifth iteration of the model designed for creative image synthesis. | stabilityai | 1 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | dreamshaper-6 | Dreamshaper 6 | Improved Dreamshaper model for even more imaginative outputs. | stabilityai | 1 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | elldrethvividmix | Elldreth Vivid Mix | Combines multiple artistic styles into vivid creations. | stabilityai | 1 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | lyriel-v15 | Lyriel V15 | 15th version of the Lyriel model, specialized in high-detail image generation. | stabilityai | 1 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | lyriel-v16 | Lyriel V16 | Latest iteration of the Lyriel series with improved generative abilities. | stabilityai | 1 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | mechamix | Mechamix | Focuses on generating mechanical and robotic imagery. | stabilityai | 1 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | meinamix | Meina Mix | Meina Mix for a unique blend of modern and traditional art styles. | stabilityai | 1 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | realisticvs-v14 | RealisticVS V14 | 14th version of RealisticVS, focused on ultra-realistic visual synthesis. | stabilityai | 1 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | realisticvs-v20 | RealisticVS V20 | 20th version offering advanced realism and detail in image generation. | stabilityai | 1 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | riffusion | Riffusion | Specializes in generating images inspired by music and sound. | stabilityai | 1 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | sd-v14 | SD V14 | 14th version of the Stable Diffusion model with enhanced capabilities. | stabilityai | 1 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | sd-v15 | SD V15 | Latest version of Stable Diffusion, featuring improved performance and quality. | stabilityai | 1 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | sbp | SBP | SBP model tailored for specific business processes and imagery needs. | stabilityai | 1 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | theallysmix | The Allys Mix | Creative model that blends multiple artistic influences for unique outputs. | stabilityai | 1 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | openjourney | Open Journey | Designed for open-ended exploration of artistic and visual possibilities. | stabilityai | 1 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | icbinp | ICBINP | ICBINP aka I Can't Believe It's Not Photography, excels in photorealistic images. | seco | 1 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | latent-consistency-model | Latent Consistency Model | LCMs: The next generation of generative models after Latent Diffusion Models (LDMs), focusing on improved consistency and detail in generative outputs. | LCM | 1 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | deepfloyd-if | DeepFloyd IF | DeepFloyd's IF model, designed for intuitive and fluent image generation, emphasizing creativity and flexibility. | deepfloyd | 1 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | material-diffusion | Material Diffusion | Material Diffusion, tailored for generating complex material textures and realistic environmental details. | material | 1 | nan | nan | nan | nan | nan | /v1/images/generations |
βοΈ | eleven-labs | Eleven Labs (Chars: ~333) | Amazing natural sounding AI speech with a variety of voices to choose from, capped at 333 characters per request. | elevenlabs | 1 | nan | nan | nan | nan | nan | /v1/audio/speech |
π° | eleven-labs-2 | Eleven Labs v2 (Chars: ~100) | Newer version of Eleven Labs with improved multi lingual support, but capped at 100 characters per request. | elevenlabs | 2 | nan | nan | nan | nan | nan | /v1/audio/speech |
π° | eleven-labs-999 | Eleven Labs v2 (Chars: ~999) | Newer version of Eleven Labs with improved multi lingual support, but capped at 999 characters per request. | elevenlabs | 3 | nan | nan | nan | nan | nan | /v1/audio/speech |
βοΈ | speechify | Speechify | Fun Text-to-Speech model with a ton of voices to choose from, including cartoon, celebrity, and casual voices. | speechify | 3 | nan | nan | nan | nan | nan | /v1/audio/speech |
π° | tts-1 | TTS 1 | A ShuttleAI model. | openai | 4 | nan | nan | nan | nan | nan | /v1/audio/speech |
π° | tts-1-hd | TTS 1 | A ShuttleAI model. | openai | 4 | nan | nan | nan | nan | nan | /v1/audio/speech |
π° | whisper-1 | Whisper 1 | OpenAI's only Official API transcription/translation model; Based off Whisper Large v2. | openai | 3 | No | N/A | N/A | No | Yes | ['/v1/audio/transcriptions', '/v1/audio/translations'] |
βοΈ | whisper-large | Whisper Large | Whisper is a pre-trained model for automatic speech recognition (ASR) and speech translation. Trained on 680k hours of labelled data, Whisper models demonstrate a strong ability to generalise to many datasets and domains without the need for fine-tuning. | openai | 2 | No | N/A | N/A | No | Yes | ['/v1/audio/transcriptions', '/v1/audio/translations'] |
βοΈ | text-moderation-007 | Text Moderation (Latest) | Most capable moderation model across all categories. | openai | 1 | No | 32768 | 32768 | No | No | /v1/moderations |
βοΈ | joke-1 | Joke 1 | Some jokes. | shuttleai | 1 | nan | nan | nan | nan | nan | /v1/jokes |
βοΈ | insult-1 | Insult 1 | Some insults. | shuttleai | 1 | nan | nan | nan | nan | nan | /v1/insults |
π° | search-google | Search Google | Search Google for anything. Different from search-ddg in that it supports language filtering and image searching. | 2 | nan | nan | nan | nan | nan | /v1/web-search | |
βοΈ | search-ddg | Search DuckDuckGo | Search DuckDuckGo. Only english natively, no image search. Web results only. | duckduckgo | 1 | nan | nan | nan | nan | nan | /v1/web-search |