Models & PricingModel Cards
May 12, 2026
GAPREMIERv26.04
SAGE 2.4 Actus
Our frontier-class multimodal model optimized for agentic and coding use cases. Released as open weights under a Modified MIT license.
Speed
Performance
Context
128k
Price
$0.40 / $1.20 /M Tokens
Features
Features
Try it
import sagea
client = sagea.Client(api_key="your-api-key")
response = client.chat.completions.create(
model="sage-2-4-actus",
messages=[
{"role": "user", "content": "Explain quantum computing in simple terms"}
]
)
print(response.choices[0].message.content)Base URL: https://api.sagea.space/v1 — Auth: Authorization: Bearer $SAGEA_API_KEY
Specifications
| Parameters | 72B |
| Context Length | 128,000 tokens |
| Max Output | 8,192 tokens |
| Training Data | Up to April 2026 |
| License | Modified MIT |
Other Models
Capabilities
SAGE 2.4 Actus is SAGEA's frontier-class multimodal model for agentic and coding workloads. It combines deep reasoning with real-time tool use across text, vision, and code.
- Agentic workflows: autonomous function calling, multi-step planning, and tool chaining via
POST https://api.sagea.space/v1/chat/completionsandPOST https://api.sagea.space/v1/agents. - Advanced coding: state-of-the-art generation across 50+ languages with 128k context for full codebases.
- Multimodal understanding: text + images + code in a unified context window.
- Structured outputs: JSON mode and schema-constrained generation for production pipelines.
Benchmarks
| Benchmark | Score | Notes |
|---|---|---|
| Agentic tool use (internal) | 87.4 | Multi-step function calling |
| Code generation (multi-lang) | 82.1 | 50+ languages |
| Reasoning (chain-of-thought) | 84.6 | 128k context |
Use cases
- Coding agents and software engineering copilots
- Research assistants over large documents and repos
- Enterprise workflows with custom tools and APIs
Limitations
- 128k context is powerful but costs more per request — use SAGE 2.5 Celer for simple Q&A.
- Always evaluate on your data before production rollout. See Choosing a Model.