JUMP TOIntroductionModelsLarge Language modelsLLM APIs01-ai / yi-largeCreates a model response for the given chat conversation.postabacusai / dracarys-llama-3.1-70b-instructCreates a model response for the given chat conversation.postai21labs / jamba-1.5-large-instructCreates a model response for the given chat conversation.postai21labs / jamba-1.5-mini-instructCreates a model response for the given chat conversation.postaisingapore / sea-lion-7b-instructCreate a chat completionpostbaichuan-inc / baichuan2-13b-chatCreates a model response for the given chat conversation.postbigcode / starcoder2-7bCreate Completionpostbigcode / starcoder2-15bCreate Completionpostdatabricks / dbrx-instructCreate a chat completionpostdeepseek-ai / deepseek-coder-6.7b-instructCreates a model response for the given chat conversation.postgoogle / gemma-2bCreate a chat completionpostgoogle / gemma-7bCreate a chat completionpostgoogle / gemma-2-2b-itCreates a model response for the given chat conversation.postgoogle / gemma-2-9b-itCreates a model response for the given chat conversation.postgoogle / gemma-2-27b-itCreates a model response for the given chat conversation.postgoogle / codegemma-1.1-7bCreates a model response for the given chat conversation.postgoogle / codegemma-7bCreate a chat completionpostgoogle / recurrentgemma-2bCreate a chat completionpostgoogle / shieldgemma-9bCreates a model response for the given chat conversation.postibm / granite-3.0-3b-a800m-instructCreates a model response for the given chat conversation.postibm / granite-3.0-8b-instructCreates a model response for the given chat conversation.postibm / granite-34b-code-instructCreates a model response for the given chat conversation.postibm / granite-8b-code-instructCreates a model response for the given chat conversation.postibm / granite-guardian-3.0-8bCreates a model response for the given chat conversation.postinstitute-of-science-tokyo / llama-3.1-swallow-70b-instruct-v01Creates a model response for the given chat conversation.postinstitute-of-science-tokyo / llama-3.1-swallow-8b-instruct-v0.1Creates a model response for the given chat conversation.postmediatek / breeze-7b-instructCreates a model response for the given chat conversation.postmeta / codellama-70bCreate a chat completionpostmeta / llama2-70bCreate a chat completionpostmeta / llama3-8bCreates a chat completionpostmeta / llama3-70bCreates a chat completionpostmeta / llama-3.1-8b-instructCreates a model response for the given chat conversation.postmeta / llama-3.1-70b-instructCreates a model response for the given chat conversation.postmeta / llama-3.1-405b-instructCreates a model response for the given chat conversation.postmeta/llama-3.2-1b-instructCreates a model response for the given chat conversation.postmeta/llama-3.2-3b-instructCreates a model response for the given chat conversation.postmicrosoft / phi-3-medium-128k-instructCreates a model response for the given chat conversation.postmicrosoft / phi-3-medium-4k-instructCreates a chat completionpostmicrosoft / phi-3-mini-128k-instructCreates a model response for the given chat conversation.postmicrosoft / phi-3-mini-4k-instructCreates a model response for the given chat conversation.postmicrosoft / phi-3-small-128k-instructCreates a chat completionpostmicrosoft / phi-3-small-8k-instructCreate a chat completionpostmicrosoft / phi-3.5-miniCreates a model response for the given chat conversation.postmicrosoft / phi-3.5-moe-instructCreates a model response for the given chat conversation.postmistralai / codestral-22b-instruct-v0.1Creates a model response for the given chat conversation.postmistralai / mamba-codestral-7b-v0.1Creates a model response for the given chat conversation.postmistralai / mistral-2-large-instructCreates a model response for the given chat conversation.postmistralai / mathstral-7b-v01Creates a model response for the given chat conversation.postmistralai / mistral-7b-instructCreate a chat completionpostmistralai / mistral-7b-instruct-v0.3Creates a model response for the given chat conversation.postmistralai / mixtral-8x7b-instructCreate a chat completionpostmistralai / mixtral-8x22b-instructCreate a chat completionpostmistralai / mistral-largeCreate a chat completionpostnvidia / llama-3.1-nemotron-51b-instructCreates a model response for the given chat conversation.postnvidia/llama-3.1-nemotron-70b-instructCreates a model response for the given chat conversation.postnvidia / llama-3.1-nemotron-70b-rewardCreates a model response for the given chat conversation.postnvidia / llama3-chatqa-1.5-70bCreates a model response for the given chat conversation.postnvidia / llama3-chatqa-1.5-8bCreates a model response for the given chat conversation.postnv-mistralai / mistral-nemo-12b-instructCreates a model response for the given chat conversation.postnvidia / mistral-nemo-minitron-8b-baseCreate Completionpostnvidia / mistral-nemo-minitron-8b-8k-instructCreates a model response for the given chat conversation.postnvidia / nemotron-4-340b-instructCreates a model response for the given chat conversation.postnvidia / nemotron-4-340b-rewardCreates a model response for the given chat conversation.postnvidia / nemotron-mini-4b-instructCreates a model response for the given chat conversation.postnvidia / usdcode-llama3-70b-instructCreates a model response for the given chat conversation.postnvidia / usdsearchSearch Postpostqwen / qwen2-7b-instructCreates a model response for the given chat conversation.postrakuten / rakutenai-7b-chatCreates a model response for the given chat conversation.postrakuten / rakutenai-7b-instructCreates a model response for the given chat conversation.postseallms / seallm-7b-v2.5Create a chat completionpostsnowflake / arcticCreate a chat completionposttokyotech-llm / llama-3-swallow-70b-instruct-v01Creates a model response for the given chat conversation.postthudm / chatglm3-6bCreates a model response for the given chat conversation.postupstage / solar-10.7b-instructCreates a model response for the given chat conversation.postwriter / palmyra-fin-70b-32kCreates a model response for the given chat conversation.postwriter / palmyra-med-70b-32kCreate a chat completionpostwriter / palmyra-med-70bCreate a chat completionpostyentinglin / llama-3-taiwan-70b-instructCreates a model response for the given chat conversation.postzyphra/zamba2-7b-instructCreates a model response for the given chat conversation.postRetrievalRetrieval APIsbaai / bge-m3Creates an embedding vector from the input text.postGets the result of an earlier function invocation request that returned a status of 202.getnvidia / embed-qa-4Create embedding vectorpostnvidia / nvclipCreates an embedding vector representing the input text or image.postnvidia / nv-embed-v1Creates an embedding vector from the input text.postnvidia / nv-embedqa-e5-v5Creates an embedding vector from the input text.postnvidia / nv-embedqa-mistral-7b-v2Creates an embedding vector from the input text.postnvidia / nv-rerankqa-mistral-4b-v3Rank passages by their relation to a query.postnvidia / rerank-qa-mistral-4bCreate rankingpostsnowflake / arctic-embed-lCreates an embedding vector from the input text.postGets the result of an earlier function invocation request that returned a status of 202.getVisual ModelsVisual Models APIsbriaai / bria-2.3Request generationposthive/ai-generated-image-detectionRequest response from the modelpostnvidia / consistoryRequest generationpostnvidia / nv-dinov2Run inference on the input image.postGets the result of an earlier function invocation request that returned a status of 202.getnvidia / nv-grounding-dinoRun inference on the input image/video for a given text promptpostGets the result of an earlier function invocation request that returned a status of 202.getnvidia / ocdrnetRequest response from the modelpostGets the result of an earlier function invocation request that returned a status of 202.getnvidia / retail-object-detectionRequest response from the modelpostGets the result of an earlier function invocation request that returned a status of 202.getnvidia / visual-changenetRequest response from the modelpostGets the result of an earlier function invocation request that returned a status of 202.getstabilityai/stable-diffusion-3-mediumRequest generationpoststabilityai / sdxl-turboRequest generationpoststabilityai / stable-diffusion-xlRequest generationpoststabilityai / stable-video-diffusionRequest generationpostmultimodAlMultimodal APIsadept / fuyu-8bRequest response from the modelpostStatus pollinggetgoogle / deplotRequest response from the modelpostStatus pollinggetgoogle / paligemmaRequest response from the modelpostGets the result of an earlier function invocation request that returned a status of 202.getmeta/llama-3.2-11b-vision-instructRequest response from the modelpostGets the result of an earlier function invocation request that returned a status of 202.getmeta/llama-3.2-90b-vision-instructRequest response from the modelpostGets the result of an earlier function invocation request that returned a status of 202.getmicrosoft / florence-2Request response from the modelpostGets the result of an earlier function invocation request that returned a status of 202.getmicrosoft / kosmos-2Request response from the modelpostGets the result of an earlier function invocation request that returned a status of 202.getmicrosoft / phi-3-vision-128k-instructRequest response from the modelpostGets the result of an earlier function invocation request that returned a status of 202.getmicrosoft / phi-3.5-vision-instructRequest response from the modelpostGets the result of an earlier function invocation request that returned a status of 202.getnvidia / neva-22bRequest response from the modelpostGets the result of an earlier function invocation request that returned a status of 202.getnvidia / vilaRequest response from the modelpostGets the result of an earlier function invocation request that returned a status of 202.getHealthcareHealthcare APIsdeepmind / alphafold2Predict Structure From Sequence Postpostdeepmind / alphafold2-multimerPredict Structure From Sequence Postpostipd / proteinmpnnPredict amino acid sequencespostipd / rfdiffusionRun RFdiffusion Protein Generationpostmeta / esmfoldPredict protein structure (alignment-free)postmeta / esm2-650mProtein Embeddingspostmit / diffdockPredict molecular dockingpostnvidia / deepvariantRun Parabricks Universal Variant Callingpostnvidia / fq2bamRun Parabricks fq2bam to align sequence readspostnvidia / maisiGenerate Imagepostnvidia / molmimPerform molecule generationpostnvidia / vista3dRun Inferencepostroute optimizationRoute Optimization APIsnvidia / cuOptSubmit to solverpostStatus pollinggetclimate simulationClimate Simulation APIsnvidia / ai-weather-forecastingSubmit an inference configurationpostGets the result of an earlier function invocation request that returned a status of 202.get https://ai.api.nvidia.com/v1/status/{requestId}
