InferX

Ornith-1.0-35B-FP8

Name: Ornith-1.0-35B-FP8
Brand: InferX

Canonical ID: inferx/Ornith-1.0-35B-FP8

More InferX models More ornith family models

Large coding-reasoning model for agentic software tasks and RL search

Reasoning: Yes Tool use: Yes Open weights

Overview

text image

Provider: InferX
Family: ornith
Release date: 2026-06-25
Last updated: 2026-06-25
Input modalities: text, image
Output modalities: text

Pricing and Limits

Token pricing

Input: $0/1M
Output: $0/1M
Cached input: N/A

Context and output

Context window: 262,000
Max output tokens: 100,000
Qualified ID: inferx/Ornith-1.0-35B-FP8

Model Summary

Ornith-1.0-35B-FP8 is a model listing in the InferX provider catalog. It is categorized under the ornith family.

The model supports text, image modalities across input/output paths. Reported context capacity is 262,000. Pricing is listed at $0/1M input and $0/1M output.

Same Family: ornith

Comparable models in the same family across providers.

Browse family

Model	Provider	Context	Input	Output	Flags
Ornith 1.5 35B nano-gpt/ornith-ai/ornith-1.5-35b-a3b	NanoGPT	262,144	$0.1/1M	$0.4/1M	Reasoning Tools
Ornith 1.5 35B A3B iteracompute/ornith-ai/ornith-1.5-35b-a3b	IteraCompute	327,680	$0.3/1M	$3/1M	Reasoning Tools
Ornith 1.5 35B A3B runinfra/ornith-ai/Ornith-1.5-35B-A3B	RunInfra	262,144	$0.1/1M	$0.4/1M	Reasoning Tools
Ornith 1.5 35B Thinking nano-gpt/ornith-ai/ornith-1.5-35b-a3b:thinking	NanoGPT	262,144	$0.1/1M	$0.4/1M	Reasoning Tools

Ornith-1.0-35B-FP8

Overview

Pricing and Limits

Token pricing

Context and output

Model Summary

More From InferX

Agents-A1

deepseek-v4-flash

Devstral-2-123B-Instruct-2512-int4-AutoRound

Gemma 4 31B IT FP8

mimo-v25

Qwen3.6 27B FP8

Qwen3.6 35B A3B FP8

Qwen3.6-35B-A3B-fp8-no-thinking

Same Family: ornith