Skip to content
Metered.

Compare model prices

Input, output, cached and batch prices, every route and a month of tokens, side by side.

Qwen3 235B A22B Instruct 2507Qwen3.8 Max Prime

A month of tokens

  • Qwen3 235B A22B Instruct 2507$26.91
  • Qwen3.8 Max Prime$640.00

100M input and 20M output tokens, list price. Use your own numbers.

Side by side

Qwen3 235B A22B Instruct 2507Qwen3.8 Max Prime
Input per 1M$0.15$4
Output per 1M$0.598$12
Cached inputn/a$0.5
Batch in / outn/an/a
Blended (3:1)$0.262$6
Context262K1M
Routes91
ReleasedJul 21, 2025Sep 23, 2026
Leadersboard scoren/an/a

On the price map

$0.03$0.1$0.3$1$3$10$30$100$0.03$0.1$0.3$1$3$10$30$100$300Input $ per 1M tokensOutput $ per 1M tokensxxZZDMOOOOOOOOOOOOOOOOZDGMMDMGDQMGGMMZGGDDGGGGGGGGMOOOZQAQQAQQQAAAQAQxQQAQQAQAAAAQQQQxxxOOOOOOOOOOOOOOOOOAAOMMQQQMGGMQQQQQQQMMMMQQQQQQQMQQQQxMMCZZZZZZZAAAOAOOOOOOOACDDDDDMDDMGGZMOQQQMOOZZQMMQQQQQGGGMMMMMMOOOMQCAOCCOOOOOOMQGGGZMDMMGMMQQQ
Size: context window, 8K to 2MEqual blended cost (3:1) 243 models, lower left is cheaper

Every route

Qwen3 235B A22B Instruct 2507

  • GMICloudfp8, fp8-41%$0.087 / $0.35cached $0.018
  • DeepInfrafp8, fp8-22%$0.09 / $0.55$0.205 blended
  • Novita AIfp8, fp8-19%$0.09 / $0.58$0.213 blended
  • Qwen (Alibaba) (list)the lab's own API$0.15 / $0.598$0.262 blended
  • Venicefp8, fp8+15%$0.15 / $0.75$0.3 blended
  • Nebiusfp8, fp8+15%$0.2 / $0.6$0.3 blended
  • Parasailfp8, fp8+17%$0.14 / $0.8cached $0.05
  • StreamLakedefault region+40%$0.21 / $0.84$0.368 blended
  • Google Vertex AIus-south1+47%$0.22 / $0.88$0.385 blended

Qwen3.8 Max Prime

  • Qwen (Alibaba) (list)the lab's own API$4 / $12cached $0.5

List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.

Weekly: LLM API list prices that changed, Thursday mornings.