NewPoint any agent at UberLLM — one key, every model, list price or less.
UberLLM

Devstral 2 123B vs Qwen3 Next 80B A3B

mistralai/devstral-2-123b · qwen/qwen3-next-80b-a3b-instruct

As of November 4, 2026, Qwen3 Next 80B A3B is the cheaper API on UberLLM: $0.0009 per million input tokens and $0.0095 per million output, versus $0.0077 / $0.0384 for Devstral 2 123B, about 76% less when output is 3 tokens for every input token. These are the best prices on the market right now. Both work with one OpenAI-compatible key and UberLLM adds no fee. Choose Qwen3 Next 80B A3B to cut cost; choose Devstral 2 123B when its capabilities fit your task better.

Devstral 2 123B vs Qwen3 Next 80B A3B, side by side

SpecDevstral 2 123BQwen3 Next 80B A3B
Price · input / 1M$0.0077$0.0009
Price · output / 1M$0.0384$0.0095
Context length256,000256,000
Max output tokens32,00016,384
Input modalitiestexttext
Output modalitiestexttext
Tools / functionsYesYes
% off list98.1% off99.1% off

Best prices on UberLLM right now. No UberLLM fee on requests; adding credit by card costs 5.5% + $0.50. Updated November 4, 2026. A price more than 70% below list is what buyers were billed, not an error. Why so cheap?

Devstral 2 123B vs Qwen3 Next 80B A3B — FAQ

Is Devstral 2 123B or Qwen3 Next 80B A3B cheaper?

Qwen3 Next 80B A3B is cheaper on a blended token mix, by about 76%. A request costs what its provider charged, UberLLM adds no fee, and every request is listed with its cost in Activity.

What's the price difference between Devstral 2 123B and Qwen3 Next 80B A3B?

Devstral 2 123B: $0.0077 in / $0.0384 out per 1M tokens. Qwen3 Next 80B A3B: $0.0009 in / $0.0095 out per 1M tokens. That's roughly a 76% blended difference. Prices are live; UberLLM adds no fee.

Can I use both Devstral 2 123B and Qwen3 Next 80B A3B with one API?

Yes. Both are served through a single OpenAI-compatible endpoint — set the base URL to https://api.uberllm.dev/v1 and your UberLLM key, then switch between them by changing the model id. Anthropic SDKs work via https://api.uberllm.dev/v1/messages.

More comparisons