Model directory

The default order considers task match first, places historical and older family generations later, then considers verified release dates, configurations, and channels. Unknown release dates receive no recency bonus. This is not a performance ranking. Price sorting compares only text token rates in the currency selected under More filters; other billing units follow. No currency conversion is applied.

Chinese model

Qwen Image

qwen/qwen-image

Developer:ALIBABA CLOUD
API provider:NVIDIA · Page三方Channel

API region unverifiedCatalog capability match

This model is indexed. Check documentation for API parameters, account access, and usage requirements.

Released:2025-08-07

Reference API pricingInput $0 · Output $0US dollar USD / million tokens· Catalog reference↗Original source note: 缓存、长上下文与其他附加计费以官方为准。A zero list price does not establish a free allowance for your account.Pricing checked:2026-09-18

Free trial unverified

Subscription / plansPlan information unverified

Complete integration configuration unverified
Source date:2026-09-18View model detailsSource ↗

International model

GPT OSS 20B

openai/gpt-oss-20b

Developer:OpenAI
API provider:NVIDIA · Page三方Channel

API region unverifiedCatalog capability match

This model is indexed. Check documentation for API parameters, account access, and usage requirements.

Released:2025-08-05

Reference API pricingInput $0 · Output $0US dollar USD / million tokens· Catalog reference↗Original source note: 缓存、长上下文与其他附加计费以官方为准。A zero list price does not establish a free allowance for your account.Pricing checked:2026-09-18

Free trial unverified

Subscription / plansPlan information unverified

Complete integration configuration unverified
Source date:2026-09-18View model detailsSource ↗

International model

GPT-OSS-120B

openai/gpt-oss-120b

Developer:OpenAI
API provider:NVIDIA · Page三方Channel

API region unverifiedCatalog capability match

This model is indexed. Check documentation for API parameters, account access, and usage requirements.

Released:2025-08-04

Reference API pricingInput $0 · Output $0US dollar USD / million tokens· Catalog reference↗Original source note: 缓存、长上下文与其他附加计费以官方为准。A zero list price does not establish a free allowance for your account.Pricing checked:2026-09-18

Free trial unverified

Subscription / plansPlan information unverified

Complete integration configuration unverified
Source date:2026-09-18View model detailsSource ↗

International model

Phi 4 Multimodal

microsoft/phi-4-multimodal-instruct

Developer:Microsoft Azure
API provider:NVIDIA · Page三方Channel

API region unverifiedCatalog capability match

This model is indexed. Check documentation for API parameters, account access, and usage requirements.

Released:2025-07-26

Reference API pricingInput $0 · Output $0US dollar USD / million tokens· Catalog reference↗Original source note: 缓存、长上下文与其他附加计费以官方为准。A zero list price does not establish a free allowance for your account.Pricing checked:2026-09-18

Free trial unverified

Subscription / plansPlan information unverified

Complete integration configuration unverified
Source date:2026-09-18View model detailsSource ↗

International model

Llama 3.3 Nemotron Super 49B v1.5

nvidia/llama-3.3-nemotron-super-49b-v1.5

Developer:NVIDIA
API provider:NVIDIA · Original provider

API region unverifiedCatalog capability match

This model is indexed. Check documentation for API parameters, account access, and usage requirements.

Released:2025-07-25

Reference API pricingInput $0 · Output $0US dollar USD / million tokens· Catalog reference↗Original source note: 缓存、长上下文与其他附加计费以官方为准。A zero list price does not establish a free allowance for your account.Pricing checked:2026-09-18

Free trial unverified

Subscription / plansPlan information unverified

Complete integration configuration unverified
Source date:2026-09-18View model detailsSource ↗

Origin unverified

sarvam-m

sarvamai/sarvam-m

Developer:Developer unverified
API provider:NVIDIA · Page三方Channel

API region unverifiedCatalog capability match

This model is indexed. Check documentation for API parameters, account access, and usage requirements.

Released:2025-07-25

Reference API pricingInput $0 · Output $0US dollar USD / million tokens· Catalog reference↗Original source note: 缓存、长上下文与其他附加计费以官方为准。A zero list price does not establish a free allowance for your account.Pricing checked:2026-09-18

Free trial unverified

Subscription / plansPlan information unverified

Complete integration configuration unverified
Source date:2026-09-18View model detailsSource ↗

International model

llama-3_2-nemoretriever-300m-embed-v1

nvidia/llama-3_2-nemoretriever-300m-embed-v1

Developer:NVIDIA
API provider:NVIDIA · Original provider

API region unverifiedCatalog capability match

This model is indexed. Check documentation for API parameters, account access, and usage requirements.

Released:2025-07-24

Reference API pricingInput $0 · Output $0US dollar USD / million tokens· Catalog reference↗Original source note: 缓存、长上下文与其他附加计费以官方为准。A zero list price does not establish a free allowance for your account.Pricing checked:2026-09-18

Free trial unverified

Subscription / plansPlan information unverified

Complete integration configuration unverified
Source date:2026-09-18View model detailsSource ↗

Chinese model

Qwen3 Coder 480B A35B Instruct

qwen/qwen3-coder-480b-a35b-instruct

Developer:ALIBABA CLOUD
API provider:NVIDIA · Page三方Channel

API region unverifiedCatalog capability match

This model is indexed. Check documentation for API parameters, account access, and usage requirements.

Released:2025-07-23

Reference API pricingInput $0 · Output $0US dollar USD / million tokens· Catalog reference↗Original source note: 缓存、长上下文与其他附加计费以官方为准。A zero list price does not establish a free allowance for your account.Pricing checked:2026-09-18

Free trial unverified

Subscription / plansPlan information unverified

Complete integration configuration unverified
Source date:2026-09-18View model detailsSource ↗

International model

cosmos-transfer1-7b

nvidia/cosmos-transfer1-7b

Developer:NVIDIA
API provider:NVIDIA · Original provider

API region unverifiedCatalog capability match

This model is indexed. Check documentation for API parameters, account access, and usage requirements.

Released:2025-06-13

Reference API pricingInput $0 · Output $0US dollar USD / million tokens· Catalog reference↗Original source note: 缓存、长上下文与其他附加计费以官方为准。A zero list price does not establish a free allowance for your account.Pricing checked:2026-09-18

Free trial unverified

Subscription / plansPlan information unverified

Complete integration configuration unverified
Source date:2026-09-18View model detailsSource ↗

International model

Gemma 3n E2b It

google/gemma-3n-e2b-it

Developer:Google Gemini
API provider:NVIDIA · Page三方Channel

API region unverifiedCatalog capability match

This model is indexed. Check documentation for API parameters, account access, and usage requirements.

Released:2025-06-12

Reference API pricingInput $0 · Output $0US dollar USD / million tokens· Catalog reference↗Original source note: 缓存、长上下文与其他附加计费以官方为准。A zero list price does not establish a free allowance for your account.Pricing checked:2026-09-18

Free trial unverified

Subscription / plansPlan information unverified

Complete integration configuration unverified
Source date:2026-09-18View model detailsSource ↗

International model

mistral-nemotron

mistralai/mistral-nemotron

Developer:Mistral AI
API provider:NVIDIA · Page三方Channel

API region unverifiedCatalog capability match

This model is indexed. Check documentation for API parameters, account access, and usage requirements.

Released:2025-06-11

Reference API pricingInput $0 · Output $0US dollar USD / million tokens· Catalog reference↗Original source note: 缓存、长上下文与其他附加计费以官方为准。A zero list price does not establish a free allowance for your account.Pricing checked:2026-09-18

Free trial unverified

Subscription / plansPlan information unverified

Complete integration configuration unverified
Source date:2026-09-18View model detailsSource ↗

International model

Gemma 3n E4b It

google/gemma-3n-e4b-it

Developer:Google Gemini
API provider:NVIDIA · Page三方Channel

API region unverifiedCatalog capability match

This model is indexed. Check documentation for API parameters, account access, and usage requirements.

Released:2025-06-03

Reference API pricingInput $0 · Output $0US dollar USD / million tokens· Catalog reference↗Original source note: 缓存、长上下文与其他附加计费以官方为准。A zero list price does not establish a free allowance for your account.Pricing checked:2026-09-18

Free trial unverified

Subscription / plansPlan information unverified

Complete integration configuration unverified
Source date:2026-09-18View model detailsSource ↗

International model

magpie-tts-zeroshot

nvidia/magpie-tts-zeroshot

Developer:NVIDIA
API provider:NVIDIA · Original provider

API region unverifiedCatalog capability match

This model is indexed. Check documentation for API parameters, account access, and usage requirements.

Released:2025-05-22

Reference API pricingInput $0 · Output $0US dollar USD / million tokens· Catalog reference↗Original source note: 缓存、长上下文与其他附加计费以官方为准。A zero list price does not establish a free allowance for your account.Pricing checked:2026-09-18

Free trial unverified

Subscription / plansPlan information unverified

Complete integration configuration unverified
Source date:2026-09-18View model detailsSource ↗

International model

Llama 3.1 Nemotron 70B Instruct

nvidia/llama-3.1-nemotron-70b-instruct

Developer:NVIDIA
API provider:NVIDIA · Original provider

API region unverifiedCatalog capability match

This model is indexed. Check documentation for API parameters, account access, and usage requirements.

Released:2025-04-15

Reference API pricingInput $0 · Output $0US dollar USD / million tokens· Catalog reference↗Original source note: 缓存、长上下文与其他附加计费以官方为准。A zero list price does not establish a free allowance for your account.Pricing checked:2026-09-18

Free trial unverified

Subscription / plansPlan information unverified

Complete integration configuration unverified
Source date:2026-09-18View model detailsSource ↗

International model

Llama 3.1 Nemotron Nano VL 8B v1

nvidia/llama-3.1-nemotron-nano-vl-8b-v1

Developer:NVIDIA
API provider:NVIDIA · Original provider

API region unverifiedCatalog capability match

This model is indexed. Check documentation for API parameters, account access, and usage requirements.

Released:2025-04-10

Reference API pricingInput $0 · Output $0US dollar USD / million tokens· Catalog reference↗Original source note: 缓存、长上下文与其他附加计费以官方为准。A zero list price does not establish a free allowance for your account.Pricing checked:2026-09-18

Free trial unverified

Subscription / plansPlan information unverified

Complete integration configuration unverified
Source date:2026-09-18View model detailsSource ↗

International model

Llama 3.1 Nemotron Ultra 253B

nvidia/llama-3.1-nemotron-ultra-253b-v1

Developer:NVIDIA
API provider:NVIDIA · Original provider

API region unverifiedCatalog capability match

This model is indexed. Check documentation for API parameters, account access, and usage requirements.

Released:2025-04-07

Reference API pricingInput $0 · Output $0US dollar USD / million tokens· Catalog reference↗Original source note: 缓存、长上下文与其他附加计费以官方为准。A zero list price does not establish a free allowance for your account.Pricing checked:2026-09-18

Free trial unverified

Subscription / plansPlan information unverified

Complete integration configuration unverified
Source date:2026-09-18View model detailsSource ↗

International model

Llama 3.3 Nemotron Super 49B v1

nvidia/llama-3.3-nemotron-super-49b-v1

Developer:NVIDIA
API provider:NVIDIA · Original provider

API region unverifiedCatalog capability match

This model is indexed. Check documentation for API parameters, account access, and usage requirements.

Released:2025-04-07

Reference API pricingInput $0 · Output $0US dollar USD / million tokens· Catalog reference↗Original source note: 缓存、长上下文与其他附加计费以官方为准。A zero list price does not establish a free allowance for your account.Pricing checked:2026-09-18

Free trial unverified

Subscription / plansPlan information unverified

Complete integration configuration unverified
Source date:2026-09-18View model detailsSource ↗

International model

Llama Guard 4 12B

meta/llama-guard-4-12b

Developer:Meta
API provider:NVIDIA · Page三方Channel

API region unverifiedCatalog capability match

This model is indexed. Check documentation for API parameters, account access, and usage requirements.

Released:2025-04-05

Reference API pricingInput $0 · Output $0US dollar USD / million tokens· Catalog reference↗Original source note: 缓存、长上下文与其他附加计费以官方为准。A zero list price does not establish a free allowance for your account.Pricing checked:2026-09-18

Free trial unverified

Subscription / plansPlan information unverified

Complete integration configuration unverified
Source date:2026-09-18View model detailsSource ↗

International model

Llama 4 Maverick 17b 128e Instruct

meta/llama-4-maverick-17b-128e-instruct

Developer:Meta
API provider:NVIDIA · Page三方Channel

API region unverifiedCatalog capability match

This model is indexed. Check documentation for API parameters, account access, and usage requirements.

Released:2025-04-01

Reference API pricingInput $0 · Output $0US dollar USD / million tokens· Catalog reference↗Original source note: 缓存、长上下文与其他附加计费以官方为准。A zero list price does not establish a free allowance for your account.Pricing checked:2026-09-18

Free trial unverified

Subscription / plansPlan information unverified

Complete integration configuration unverified
Source date:2026-09-18View model detailsSource ↗

International model

Mistral-7B-Instruct-v0.3

mistralai/mistral-7b-instruct-v0.3

Developer:Mistral AI
API provider:NVIDIA · Page三方Channel

API region unverifiedCatalog capability match

This model is indexed. Check documentation for API parameters, account access, and usage requirements.

Released:2025-04-01

Reference API pricingInput $0 · Output $0US dollar USD / million tokens· Catalog reference↗Original source note: 缓存、长上下文与其他附加计费以官方为准。A zero list price does not establish a free allowance for your account.Pricing checked:2026-09-18

Free trial unverified

Subscription / plansPlan information unverified

Complete integration configuration unverified
Source date:2026-09-18View model detailsSource ↗

International model

bevformer

nvidia/bevformer

Developer:NVIDIA
API provider:NVIDIA · Original provider

API region unverifiedCatalog capability match

This model is indexed. Check documentation for API parameters, account access, and usage requirements.

Released:2025-03-18

Reference API pricingInput $0 · Output $0US dollar USD / million tokens· Catalog reference↗Original source note: 缓存、长上下文与其他附加计费以官方为准。A zero list price does not establish a free allowance for your account.Pricing checked:2026-09-18

Free trial unverified

Subscription / plansPlan information unverified

Complete integration configuration unverified
Source date:2026-09-18View model detailsSource ↗

International model

cosmos-predict1-5b

nvidia/cosmos-predict1-5b

Developer:NVIDIA
API provider:NVIDIA · Original provider

API region unverifiedCatalog capability match

This model is indexed. Check documentation for API parameters, account access, and usage requirements.

Released:2025-03-18

Reference API pricingInput $0 · Output $0US dollar USD / million tokens· Catalog reference↗Original source note: 缓存、长上下文与其他附加计费以官方为准。A zero list price does not establish a free allowance for your account.Pricing checked:2026-09-18

Free trial unverified

Subscription / plansPlan information unverified

Complete integration configuration unverified
Source date:2026-09-18View model detailsSource ↗

International model

Llama 3.1 Nemotron Nano 8B v1

nvidia/llama-3.1-nemotron-nano-8b-v1

Developer:NVIDIA
API provider:NVIDIA · Original provider

API region unverifiedCatalog capability match

This model is indexed. Check documentation for API parameters, account access, and usage requirements.

Released:2025-03-18

Reference API pricingInput $0 · Output $0US dollar USD / million tokens· Catalog reference↗Original source note: 缓存、长上下文与其他附加计费以官方为准。A zero list price does not establish a free allowance for your account.Pricing checked:2026-09-18

Free trial unverified

Subscription / plansPlan information unverified

Complete integration configuration unverified
Source date:2026-09-18View model detailsSource ↗

International model

sparsedrive

nvidia/sparsedrive

Developer:NVIDIA
API provider:NVIDIA · Original provider

API region unverifiedCatalog capability match

This model is indexed. Check documentation for API parameters, account access, and usage requirements.

Released:2025-03-18

Reference API pricingInput $0 · Output $0US dollar USD / million tokens· Catalog reference↗Original source note: 缓存、长上下文与其他附加计费以官方为准。A zero list price does not establish a free allowance for your account.Pricing checked:2026-09-18

Free trial unverified

Subscription / plansPlan information unverified

Complete integration configuration unverified
Source date:2026-09-18View model detailsSource ↗