Novita AI offers an AI and agent cloud platform for developers, enabling rapid deployment of models and agents. Key capabilities include:

Model APIs: Access to over 200 AI models (LLMs, image, video, TTS, embeddings) via a simple API, with plug-and-play functionality and scalable infrastructure.
Custom Models: Enterprise-grade deployment with guaranteed performance SLAs, scalability, and monitoring, requiring no DevOps.
GPU Cloud: Globally distributed GPU instances for training, finetuning, and inference, with on-demand or spot pricing at up to 50% off.
Agent Sandbox: Isolated containers for running autonomous agents with ~200 ms startup times, safe tool use (browser/API/code), and per-second billing for CPU/RAM. Strengths include developer-first design, high performance, global reliability, cost-efficiency, and secure sandboxing. Typical use cases involve prototyping to production AI workloads, custom model hosting, and agent development.

Model

Input ($/M)

Output ($/M)

Audit

Speed

Latency

deepseek/deepseek-r1

—

66.2 t/s

6.29 s

deepseek/deepseek-r1-0528

—

48.5 t/s

11.41 s

Time

Model

Speed

Latency

Dec 27, 05:39 PM

deepseek/deepseek-r1-0528

45.47 tok/s

12.79s

Dec 27, 05:15 PM

deepseek/deepseek-r1-0528

48.99 tok/s

11.30s

Dec 18, 10:30 AM

deepseek/deepseek-r1-0528

56.81 tok/s

10.29s

Oct 24, 01:50 AM

deepseek/deepseek-r1-0528

40.65 tok/s

8.69s

Oct 17, 08:24 AM

deepseek/deepseek-r1-0528

70.30 tok/s

9.83s

Oct 10, 02:55 PM

deepseek/deepseek-r1-0528

52.23 tok/s

10.00s

Oct 10, 10:25 AM

deepseek/deepseek-r1-0528

75.36 tok/s

6.29s

Sep 21, 07:28 AM

deepseek/deepseek-r1-0528

62.65 tok/s

5.10s

Sep 3, 09:24 AM

deepseek/deepseek-r1-0528

36.90 tok/s

8.17s

Sep 3, 06:12 AM

deepseek/deepseek-r1-0528

42.45 tok/s

13.95s

Provider

Why compare

Models

Free

Avg price

Speed

30d uptime

Novita AI

novita-ai

Provides a unified API for accessing 200+ AI models, custom model deployment, GPU cloud services, and secure agent sandboxes.

Current provider baseline

N/A

56 tok/s

65.5%

OpenRouter

openrouter

A unified API interface providing access to over 300 models from 60+ providers, including OpenAI, Anthropic, and Google.

Faster measured speed
Higher 30-day availability
Broader model coverage
Same provider category

221

N/A

86 tok/s

99.7%

nvidia-nim

NVIDIA NIM provides optimized AI model inference APIs for LLMs, vision, and embedding models through NVIDIA cloud infrastructure.

Faster measured speed
Higher 30-day availability
Broader model coverage
Same provider category

N/A

66 tok/s

99.5%

api-kriora-com

Provides OpenAI-compatible APIs and managed GPU instances for deploying and scaling open-source AI models.

Faster measured speed
Higher 30-day availability
Broader model coverage
Same provider category

N/A

565 tok/s

99.7%

api-suanli-cn

Gongji Compute (共绩算力) provides pay-as-you-go, standard API access to mainstream LLMs and elastic GPU computing for AI applications.

Higher 30-day availability
More free-model options
Broader model coverage
Same provider category

N/A

36 tok/s

77.9%

api-fireworks-ai

Fireworks AI provides a cloud platform for running and fine-tuning open-source AI models with optimized inference for production applications.

Faster measured speed
Higher 30-day availability
Broader model coverage
Same provider category

N/A

139 tok/s

99.8%

550c-cloud

共绩算力 (550c.cloud) is a shared computing platform providing Ollama-hosted open-source AI model inference via OpenAI-compatible API.

Faster measured speed
Higher 30-day availability
Broader model coverage
Same provider category

N/A

112 tok/s

82.6%

Notes

Health checks: Scope: the 72-hour chart and recent availability measure API connectivity only. Each bar summarizes one hour of checks. Targets: LMSpeed tries the configured health check URL and provider status URL first, then API endpoints derived from known API hosts and recent speed-test base URLs. A website host is considered only when it looks like an API endpoint. Probe steps: each candidate goes through DNS lookup, TCP connection, TLS handshake for HTTPS, and an HTTP HEAD request with redirects followed. Probing stops after the first reachable candidate. Reachable criteria: every required network step must succeed. An HTTP response below 500 is treated as reachable, including 401 because it confirms that an authenticated API endpoint responded, except for statuses classified as blocked. Blocked results: HTTP 403, 429, 521, 525, and 530, plus detected WAF or Cloudflare challenges, are shown as blocked and excluded from availability calculations because LMSpeed cannot determine whether the API itself is down. Model availability: when a dedicated test key is configured, LMSpeed sends an authenticated GET request to a derived /models endpoint and compares returned model IDs with this provider's listed models. These per-model results appear in Models & Pricing and are not included in the provider connectivity percentage. Timeouts: TCP connection, TLS handshake, HTTP connectivity, and model requests each use a 20-second timeout. A full run can take longer when several candidates are tried. Frequency: a background worker checks all providers every 5 minutes by default. The 72-hour chart combines those samples into hourly bars, and the schedule may be changed by the service operator. Limit: automated samples are not an SLA and do not guarantee account quota, every model, every region, or successful completion requests. Check the provider's own status page before making operational decisions.

Domain Rating data is sourced from Ahrefs. It is a 0–100 backlink-based domain strength signal and does not measure API speed or reliability.

Announcements and FAQ are read from this provider's NewAPI status snapshot when available. LMSpeed stores the original content and optional English translations from the provider status source, then shows the localized fields on this page.

Novita AI

Novita AI

API Endpoints

Health Check

API Benchmarks & Pricing

Recent Test Records

Similar API Provider Alternatives to Compare

Notes

Similar API Provider Alternatives to Compare

Provider	Why compare	Models	Free	Avg price	Speed	30d uptime
Novita AI novita-ai Provides a unified API for accessing 200+ AI models, custom model deployment, GPU cloud services, and secure agent sandboxes.	Current provider baseline	2	0	N/A	56 tok/s	65.5%
OpenRouter openrouter A unified API interface providing access to over 300 models from 60+ providers, including OpenAI, Anthropic, and Google.	Faster measured speed Higher 30-day availability Broader model coverage Same provider category	221	0	N/A	86 tok/s	99.7%
nvidia-nim NVIDIA NIM provides optimized AI model inference APIs for LLMs, vision, and embedding models through NVIDIA cloud infrastructure.	Faster measured speed Higher 30-day availability Broader model coverage Same provider category	53	0	N/A	66 tok/s	99.5%
api-kriora-com Provides OpenAI-compatible APIs and managed GPU instances for deploying and scaling open-source AI models.	Faster measured speed Higher 30-day availability Broader model coverage Same provider category	9	0	N/A	565 tok/s	99.7%
api-suanli-cn Gongji Compute (共绩算力) provides pay-as-you-go, standard API access to mainstream LLMs and elastic GPU computing for AI applications.	Higher 30-day availability More free-model options Broader model coverage Same provider category	6	5	N/A	36 tok/s	77.9%
api-fireworks-ai Fireworks AI provides a cloud platform for running and fine-tuning open-source AI models with optimized inference for production applications.	Faster measured speed Higher 30-day availability Broader model coverage Same provider category	5	0	N/A	139 tok/s	99.8%
550c-cloud 共绩算力 (550c.cloud) is a shared computing platform providing Ollama-hosted open-source AI model inference via OpenAI-compatible API.	Faster measured speed Higher 30-day availability Broader model coverage Same provider category	4	0	N/A	112 tok/s	82.6%

Novita AI

Novita AI

API Endpoints

About Novita AI

Health Check

API Benchmarks & Pricing

Recent Test Records

Similar API Provider Alternatives to Compare

Notes

Similar API Provider Alternatives to Compare