SERVE MODELS FAST.
SCALE WORKLOADS.
Ultra-fast inference for open-source and third-party models, global high availability, and an automatic 30% discount on every token. Served live from api.matterai.so/v1/models.
Live Model Catalog
GLM 5.3 Flash
GLM 5.3 Flash is a fast, low cost open model for everyday coding tasks.
zai/glm-5.3-flash
DeepSeek V4.1 Flash
DeepSeek V4.1 Flash is DeepSeek's latest fast, cost-efficient model with a 1M context window, native multimodal (vision) support, thinking and non-thinking modes, and strong coding, tool-use, and agentic performance.
deepseek/deepseek-v4.1-flash
Gemini 3.8 Flash
Gemini 3.8 Flash is a fast, low cost model by Google for everyday coding tasks.
gemini-3.8-flashGLM 5.3
GLM 5.3 is Z.ai's frontier open model for complex coding tasks and long running agents.
zai/glm-5.3System Models
Free models that answer typed questions about a piece of text in a single call, with structured output. Call POST api.matterai.so/v1/system with your MatterAI API key.
GLiNER2.5-DecideFreeFastino's 340M-parameter open-weight encoder decision model. Evaluates a set of typed questions (choice, score, yes/no) over a piece of text and jointly decodes structured answers in a single pass, with no prompt templates or token generation. Built for fast, deterministic classification: intent, routing, sentiment, priority, policy and moderation decisions. It does not reason, explain or answer open questions.
- Parameters
- 340M
- License
- Apache-2.0
- Architecture
- DeBERTa-v3-large encoder
- Question types
- choice, score, noul
ClefFreeCloudflare's 27B multimodal decision model that turns a state and a schema of typed questions into decisions. It reads the state as text, JSON, images, or video, and returns a probability for every allowed option of every question.
- Parameters
- 27B
- License
- Terms and License
- Architecture
- Multimodal decision model
- Question types
- choice, score, noul
Clef FlashFreeCloudflare's fast 9B multimodal decision model that turns a state and a schema of typed questions into decisions. It reads the state as text, JSON, images, or video, and returns a probability for every allowed option of every question.
- Parameters
- 9B
- License
- Terms and License
- Architecture
- Multimodal decision model
- Question types
- choice, score, noul
curl -X POST https://api.matterai.so/v1/system \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $MATTERAI_API_KEY" \
-d '{
"model": "fastino/gliner2.5-decide",
"state": "The customer said the delivery was late but the product quality was excellent.",
"questions": {
"sentiment": {
"type": "choice",
"instructions": "What is the overall sentiment of this feedback?",
"criteria": {
"positive": "Customer is happy overall",
"negative": "Customer is unhappy overall",
"mixed": "Customer has both good and bad things to say"
}
},
"satisfaction": {
"type": "score",
"instructions": "Rate overall customer satisfaction from low to high.",
"criteria": ["low", "medium", "high"]
},
"needs_followup": {
"type": "noul",
"instructions": "Does this feedback require a follow-up from the support team?"
}
}
}'CACHE READS
AUTOMATICALLY.
Tokens read from cache receive up to a 90% discount automatically across supported models. In addition, all models feature an automatic 30% discount below upstream list pricing.
USE WITH
ANY OPENAI SDK.
Fully OpenAI-compatible completions and chat endpoints. Drop into existing LangChain, LlamaIndex, Vercel AI SDK, or raw client code.
from openai import OpenAI
client = OpenAI(
api_key="YOUR_MATTERAI_KEY",
base_url="https://api2.matterai.so/v1",
)
response = client.chat.completions.create(
model="zai/glm-5.3",
messages=[{"role": "user", "content": "Refactor auth middleware to async/await"}],
)