Model library
15
serverless models
1M
max context window
B200 · B300
Blackwell GPUs on demand
$1
free credits, no card
z.ai · LLM
Frontier agentic model. Top-tier coding, tool use, and long-context reasoning.
moonshotai · Vision
Frontier open-weights model for coding, reasoning, and long context.
z.ai · Vision
Ultra-fast multimodal workhorse for chat, extraction, and routing.
Pick a model, tune the knobs, copy the code or simulate a streaming reply.
Simulated streaming reply
Hit “Run demo stream” to preview token-by-token output…
from openai import OpenAI
client = OpenAI(
api_key="$RUNAII_API_KEY",
base_url="https://api.runaii.cloud/v1",
)
resp = client.chat.completions.create(
model="runaii/glm-5.3",
temperature=0.7,
top_p=0.9,
max_tokens=1024,
messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)~320ms
TTFT (typical)
211 tok/s
Peak throughput
1M
Context
z.ai
Frontier agentic model. Top-tier coding, tool use, and long-context reasoning.
z.ai
Ultra-fast multimodal workhorse for chat, extraction, and routing.
moonshotai
Frontier open-weights model for coding, reasoning, and long context.
deepseek
SWE-bench leader. Strong math, code, and agentic tool use.
deepseek
Speed-tuned V4 for high-volume pipelines.
qwen
Qwen flagship. Multilingual strength and dense world knowledge.
qwen
Balanced multimodal model for production chat.
openai
OpenAI's open-weights 120B MoE. Efficient reasoning per dollar.
openai
Small open-weights model for classification and routing.
minimax
Long-context generalist with aggressive pricing.
meta
The dependable classic. Broad ecosystem support.
qwen
State-of-the-art multilingual embeddings.
qwen
Cross-encoder reranking for RAG pipelines.
openai
Speech-to-text across 99 languages.
blackforest
Context-aware image generation and editing.
The advisor picks 3 open models sized to your use case, cost, and context needs — every price on this page.
Step 1 / 2
Open the playground with any model preloaded — $1 credit covers thousands of calls.