API

API keys

Generate up to 5 API keys to use NanoGPT in other applications. If you require more keys, please contact us at support@nano-gpt.com and we will help you out.

Authenticate by including your API key as a HTTP header: x-api-key: API_KEY

NameStatusCreatedAPI Key

API Reference

Documentation is not yet complete. The below example code can be used in Python, NanoGPTjs is a great starting point for JS users.

If you encounter issues or need further information please contact support@nano-gpt.com

Text models
POST https://nano-gpt.com/api/talk-to-gpt
NameModelDescription
ChatGPT 4ochatgpt-4o-latestOpenAI's current recommended model, the well-known ChatGPT.
OpenAI o1o1-previewOpenAI's new flagship series of reasoning models for solving hard problems. Useful when tackling complex problems in science, coding, math, and similar fields
OpenAI o1-minio1-miniA fast, cost-efficient version of OpenAI's o1 reasoning model tailored to coding, math, and science use cases.
Claude 3.5 Sonnetclaude-3-5-sonnet-20240620Anthropic's most intelligent model, offering even better results on many subjects than GPT-4o.
Gemini 1.5 Pro Oldgoogle/gemini-pro-1.5Older version of Google's next-generation model with a breakthrough 4 million context window. Comparable to GPT-4o.
Gemini 1.5 Progoogle/gemini-pro-1.5-expGoogle's next-generation model with a breakthrough 4 million context window. Comparable to GPT-4o.
Llama 3.1 LargeMeta-Llama-3-1-405B-Instruct-FP8Meta's largest Llama 3.1 405B model via an open permissionless network. Note: in testing phase, therefore temporarily 90% discounted.
Llama 3.2 Mediummeta-llama/llama-3.2-90b-vision-instructMedium-size (and capability) version of Meta's newest model (3.2 series).
Grok 2x-ai/grok-2Grok-2 is xAI's frontier language model, the one used on X. Claims state-of-the-art reasoning capabilities, best for complex and multi-step use cases.
Llama 3 Lumimaid 70Bneversleep/llama-3-lumimaid-70bA Llama 3 70B finetune trained on curated roleplay data. Extremely uncensored and suitable for NSFW.
WizardLM-2 8x22Bmicrosoft/wizardlm-2-8x22bMicrosoft's advanced Wizard model. The most popular role-playing model.
Llama 3.1 Largeaccounts/fireworks/models/llama-v3p1-405b-instructMeta's largest and most capable Llama model. Competitive with GPT-4o and Claude 3.5 Sonnet.
GPT 4ogpt-4o-2024-08-06OpenAI's precusor to ChatGPT-4o. Great on English text and code, with significant improvements on text in non-English languages.
Llama 3.1 Mediumaccounts/fireworks/models/llama-v3p1-70b-instructMeta's updated version of their medium Llama model. Slightly lesser performance than Llama Large, but cheaper.
Llama 3.1 Mediumllama-3.1-70b-instructMeta's GPT-4 level model. Cheaper than GPT-4 and Claude 3, with similar performance according to most.
GPT 4o minigpt-4o-miniOpenAI's most cost-efficient small model. Cheaper and smarter than GPT-3.5 (the original ChatGPT), but less performant than gpt-4o
Perplexity Onlinellama-3.1-sonar-huge-128k-onlineThe bigger version of the Perplexity model that is able to browse the web and access up-to-date information.
Llama 3.1 Largemeta-llama/llama-3.1-405b-instructMeta's largest and most capable Llama model. Competitive with GPT-4o and Claude 3.5 Sonnet.
Claude 3 Opusclaude-3-opus-20240229Anthropic's flagship model, outperforming GPT-4 on most benchmarks.
Gemini 1.5 Flashgoogle/gemini-flash-1.5-expGoogle's fastest multimodal model with great performance for diverse, repetitive tasks and a 4 million context window.
Gemini 1.5 Flashgoogle/gemini-flash-1.5Older version of Google's fastest multimodal model with great performance for diverse, repetitive tasks and a 4 million context window.
Perplexity Online Mediumllama-3.1-sonar-large-128k-onlineA Perplexity model that is able to browse the web and access up-to-date information.
Hermes 3 Largenousresearch/hermes-3-llama-3.1-405bLlama 3.1 405b with the brakes taken off. An uncensored model, aligned to the user.
Hermes 3 Largenousresearch/hermes-3-llama-3.1-405b:extendedLlama 3.1 405b with the brakes taken off. An uncensored model, aligned to the user.
MythoMax 13Bgryphe/mythomax-l2-13bOne of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay.
DeepSeek V2.5deepseek/deepseek-chatCombination of DeepSeek V2 Chat and Coder, integrating capabilities from both.
Qwen2.5 72Bqwen/qwen-2.5-72b-instructGreat multilingual support, strong at mathematics and coding, supports roleplay and chatbots.
EVA Qwen2.5 14Beva-unit-01/eva-qwen-2.5-14bBased on Qwen2.5-14b, specializing in RP and creative writing, fine-tuned with a mix of synthetic and natural data.
Dolphin 2.6 Mixtral 8x7bcognitivecomputations/dolphin-mixtral-8x7bDesigned for instruction following, conversational, and coding.
GPT 4 Turbogpt-4-turbo-previewCan take in the largest messages (up to 300 pages of context), and all round seen as one of the best in class models.
GPT 4ogpt-4oOpenAI's most advanced model. It matches GPT-4 Turbo performance on text in English and code, with significant improvement on text in non-English languages, while also being much faster and 50% cheaper.
GPT 3.5 Turbogpt-3.5-turboOlder model. Brought ChatGPT to the mainstream, seen as dated nowadays. 90% cheaper than GPT-4-Turbo, recommended for very simple tasks.
Gemini 1.5 Flashgemini-1.5-flash-001Google's fastest multimodal model with great performance for diverse, repetitive tasks and a 1 million context window.
Gemini 1.5 Progemini-1.5-pro-001Google's next-generation model with a breakthrough 1 million context window. Comparable to GPT-4o.
Playgroundfree-modelUse a randomly selected free model to test our service.
Magnum v2 72Banthracite-org/magnum-v2-72bFrom the creators of Goliath. Aimed at achieving prose quality similar to Claude Opus 3, trained on 55 million tokens of curated Roleplay data.
Rocinante 12Bthedrummer/rocinante-12bDesigned for engaging storytelling and rich prose. Expanded vocabulary with unique and expressive word choices, enhanced creativity and captivating stories.
Dolphin 2.9.2 Mixtral 8x22Bcognitivecomputations/dolphin-mixtral-8x22bSuccessor to Dolphin 2.6 Mixtral 8x7b. Great for instruction following, conversational, and coding.
Llama 3.1 70b Instructmeta-llama/llama-3.1-70b-instructOptimized for high quality dialogue usecases.
Llama 3.1 8b Instructmeta-llama/llama-3.1-8b-instructFast and efficient for simple purposes.
L3 Euryale 70Bsao10k/l3-euryale-70bA 70B parameter model from SAO10K, offering high-quality text generation.
Mistral Tinymistralai/mistral-tinyPowered by Mistral-7B-v0.2, best used for large batch processing tasks where cost is a significant factor but reasoning capabilities are not crucial.
Mistral 7B Instructmistralai/mistral-7b-instructOptimized for speed with decent context length
Llama 3 70b Instructmeta-llama/llama-3-70b-instructOptimized for high quality dialogue usecases.
WizardLM-2 7Bmicrosoft/wizardlm-2-7bFinetune of Mistral 7B Instruct, very fast.
Cohere: Command Rcohere/command-r35B parameter model that performs conversational language tasks at a higher quality, more reliably, and with a longer context than previous models. It can be used for complex workflows like code generation, retrieval augmented generation (RAG), tool use, and agents
Nous Hermes 3 70B Instructnousresearch/hermes-3-llama-3.1-70bGeneralist language model including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the board.
Mistral Nemomistralai/mistral-nemo12B parameter model with multilingual support.
Llama 3.2 3b Instructmeta-llama/llama-3.2-3b-instructSmall model optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization
Llama 3.1 8B (decentralized)Meta-Llama-3-1-8B-Instruct-FP8Meta's Llama 3.1 8B model via an open permissionless network

Note! The endpoint for the Gemini models is /api/talk-to-gemini

Image models
POST https://nano-gpt.com/api/generate-image
NameModelDescription
Flux Pro V1.1flux-pro/v1.1The current best scoring model across all image models tested.
Flux Schnellflux/schnellFast and high-quality image generation - the cheaper version of the Flux range of models.
DALL-E-3dall-e-3OpenAI's most well-known image model.
DALL-E-3 HDdall-e-3-hdOpenAI's most well-known image model, now in HD quality.
Flux Realismflux-realismIncredibly photorealistic image generation. Generate people, animals, landscapes that are hard to distinguish from reality.
Playground V2.5playground-v25Playground V2.5 outperforms SDXL in many user tests. Suitable for a broad range of images.
Proteusproteus-v0.2A versatile image generation model with high-quality outputs.
Realistic Vision V5.1realisticVisionV51_v51VAE_94301.safetensorsRealistic Vision generates realistic-looking humans. It can also generate realistic objects, animals and landscapes.
Uber RealisticuberRealisticPornMerge_urpmv12_4979.safetensorsGenerates realistic-looking NSFW images.
Stable Diffusion 3 Mediumsd3_base_medium.safetensorsExcels at photorealism, typography, and prompt following. Works best in 1024x1024.
Dreamshaper XLdreamshaper_8_93211.safetensorsDreamshaper generates realistic and anime/illustration-style images, and is best suited to sci-fi and fantasy scenes.
ReV AnimatedrevAnimated_v122.safetensorsReV Animated specialized in fantasy, anime and semi-realistic landscapes.
Stable Diffusion XLfast-sdxlCheap and powerful text-to-image model that generates pictures rapidly.
Flux Pro V1flux-proOlder version of Flux V1.1. Exceptional quality and prompt adherence.