Qwen3-235B A22B Instruct (tput)
Pricing & Specs

Qwen (Alibaba) · $0.2 input / $0.6 output per 1M tokens · 262.144K context window

No longer offered on OpenMark

$0.2
per 1M input tokens
$0.6
per 1M output tokens
262.144K
context window (tokens)

Qwen3-235B A22B Instruct (tput) is no longer offered on OpenMark (deprecated or superseded upstream). Its specs are kept here for reference. If you're still running it in production, it's worth benchmarking current alternatives: newer models are often cheaper AND better on the same task.

Qwen3-235B A22B Instruct (tput) API Pricing

TokensPrice
Input$0.2 / 1M tokens
Output$0.6 / 1M tokens

What that means in practice

1x One typical task (1K input + 500 output tokens): $0.0005
1K 1,000 runs of that task: $0.50
💡 Real cost depends on how verbose the model is on YOUR prompts. Benchmark to measure actual tokens, not estimates.

Qwen3-235B A22B Instruct (tput) Specs

SpecValue
Context window262.144K tokens
Input modalitiestext
Output modalitiestext
Latency (measured by OpenMark)~434ms median response
Reasoning modelNo
Tool / function callingYes
JSON modeYes
StreamingYes
Prompt cachingNo

Capabilities

text generation reasoning function calling structured outputs streaming

Notes

Deprecated/removed from Together AI.

FAQ

How much does Qwen3-235B A22B Instruct (tput) cost?

Qwen3-235B A22B Instruct (tput) costs $0.2 per 1M input tokens and $0.6 per 1M output tokens.

What is Qwen3-235B A22B Instruct (tput)'s context window?

Qwen3-235B A22B Instruct (tput) has a 262.144K-token context window.

Can I test Qwen3-235B A22B Instruct (tput) on my own task?

Qwen3-235B A22B Instruct (tput) is no longer offered on OpenMark, but you can benchmark its current alternatives from Qwen (Alibaba) and other providers on your own task, free tier available.

Still using Qwen3-235B A22B Instruct (tput)?

It's been superseded. Benchmark its current alternatives on your actual
workload. You'll likely find something cheaper AND better. Free tier available.

Test Current Alternatives Free →

Get the monthly model change report

New models, API price changes, and retirements, straight from the registry that powers OpenMark. One email a month.