Ornith 1.0 9B

DeepreinforceMCP Tool CallReasoning

deepreinforce/ornith-1.0-9bOpen Weights

Open coding-reasoning model for repository tasks and self-improving agents

Benchmark Pricing$0.00 / 1M in$0.00 / 1M out

Context: 262,144 tokens•Max Output: 4,096 tokens•Released: 2026-06-25

TECHNICAL SPECIFICATIONS

Context Window262,144262.1K tokens

Max Output4,0964.1K tokens

LicenseMITSelf-hostable

Input Modalities

TextVision

Function / Tool CallingSupported (MCP Ready)

Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ Ornith 1.0 9B natively supports OpenAI / Anthropic format tool calling and is fully compatible with MCP servers and agent loops.

MCP Context Window Recommendations

With a context capacity of 262,144 tokens, this model can handle moderately large MCP tool definitions and multi-turn conversation logs comfortably.

STANDARDIZED BENCHMARKS & EVALS

SWE-Bench Verifiedpercent resolved

69.4

SWE-Bench Propercent resolved

42.9

SWE-Bench Multilingualpercent resolved

Terminal-Bench 2.1percent

43.1

Terminal-Bench 2.1percent

40.6

NL2Repopercent

27.2

Claw-evalpercent

63.1

API CALL INVOCATION EXAMPLE

// Example: Calling Ornith 1.0 9B via OpenAI SDK
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.DEEPREINFORCE_API_KEY,
});

const response = await client.chat.completions.create({
  model: "deepreinforce/ornith-1.0-9b",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

console.log(response.choices[0].message.content);