Together AI

Qwen3 235B A22B Instruct 2507 FP8

Name: Qwen3 235B A22B Instruct 2507 FP8
Brand: Together AI

Canonical ID: togetherai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput

More Together AI models More qwen3-235b-a22b-instruct-2507-tput family models

Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use

Reasoning: Yes Tool use: Yes Open weights

Overview

text

Provider: Together AI
Family: qwen3-235b-a22b-instruct-2507-tput
Release date: 2025-07-25
Last updated: 2025-07-25
Input modalities: text
Output modalities: text

Pricing and Limits

Token pricing

Input: $0.2/1M
Output: $0.6/1M
Cached input: N/A

Context and output

Context window: 262,144
Max output tokens: 262,144
Qualified ID: togetherai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput

Model Summary

Qwen3 235B A22B Instruct 2507 FP8 is a model listing in the Together AI provider catalog. It is categorized under the qwen3-235b-a22b-instruct-2507-tput family.

The model supports text modalities across input/output paths. Reported context capacity is 262,144. Pricing is listed at $0.2/1M input and $0.6/1M output.

Qwen3 235B A22B Instruct 2507 FP8

Overview

Pricing and Limits

Token pricing

Context and output

Model Summary

More From Together AI

Beam 1.0 501B A23B

DeepSeek R1

DeepSeek V3

DeepSeek V3.1

DeepSeek V4.1 Flash

DeepSeek V4 Flash 0731

DeepSeek V4 Pro 0813

GLM 4.6