GPT OSS 120BQwen3 235B A22B Instruct 2507v = reported by the model’s maker. — = no public score yet. Arena bars span the range across every model we grade.
What it costs you
Drag to match your monthly usage.
GPT OSS 120B$14.20 /month
Qwen3 235B A22B Instruct 2507$40.00 /month
GPT OSS 120B saves you $25.80 a month at this usage, $310 a year.
At a glance
Attribute
GPT OSS 120B
Qwen3 235B A22B Instruct 2507
Made by
OpenAI
Qwen
Availability
Coming soon
Coming soon
Overall grade
Good · 46.1
Excellent · 71.0
Overall rank
#53 of 67
#28 of 67
Input price
$0.037 per 1M
$0.090 per 1M
Output price
$0.17 per 1M
$0.55 per 1M
Context window
131,072 tokens
262,144 tokens
Reasoning levels
Yes
Yes
Reads images
No
No
Model ID
gpt-oss-120b
qwen3-235b-a22b-instruct-2507
Try both with one key
Same endpoint, same key, both hosted in the USA. Change one word to switch models, in Claude Code, Cursor, Cline or your own code.
# Ask either model the same thingcurlhttps://fullsendai.com/v1/chat/completions \-H"Authorization: Bearer $FULLSEND_API_KEY" \-d'{"model": "gpt-oss-120b", "messages": [...]}'# …then swap one word-d'{"model": "qwen3-235b-a22b-instruct-2507", "messages": [...]}'
Questions
Is GPT OSS 120B or Qwen3 235B A22B Instruct 2507 better?
Qwen3 235B A22B Instruct 2507 grades 71.0 against 46.1 for GPT OSS 120B, from public benchmarks.
Which is cheaper, GPT OSS 120B or Qwen3 235B A22B Instruct 2507?
GPT OSS 120B: $0.037 in and $0.17 out per million tokens, against $0.090 and $0.55 through FullsendAI.
Which has the larger context window?
Qwen3 235B A22B Instruct 2507, with 262,144 tokens.
Can I use both with one API key?
Yes, once they launch: both are coming soon, at the prices shown, and both will use the same FullsendAI key.
Scores: LMArena (CC BY 4.0), Aider (aider.chat), SWE-bench, LiveCodeBench, and model makers’ published results where marked v. Prices are FullsendAI’s, per million tokens. Data as of Oct 28, 2026.
