Zerogpu API pricing

Language models (13)

Prices per million tokens.

• DeepSeek V4.1 Flash

  zerogpu/deepseek-v4.1-flash

  Input

  $0.30

  Output

  $1.20

  Context

  1.05M

• GLM 5.3 Flash

  zerogpu/glm-5.3-flash

  Input

  $0.10

  Output

  $0.35

  Context

  1.05M

• GPT-4.1 mini

  zerogpu/gpt-4.1-mini

  Input

  $0.40

  Output

  $1.60

  Context

  1.05M

• GPT-5.4 nano

  zerogpu/gpt-5.4-nano

  Input

  $0.20

  Output

  $1.25

  Context

  272K

• GPT-5.6 luna

  zerogpu/gpt-5.6-luna

  Input

  $0.20

  Output

  $1.20

  Context

  272K

• GPT-6 luna

  zerogpu/gpt-6-luna

  Input

  $0.10

  Output

  $0.50

  Context

  272K

• gpt-oss-120b

  zerogpu/gpt-oss-120b

  Input

  $0.15

  Output

  $0.60

  Context

  128K

• Qwen3 30B A3B Fp8

  zerogpu/qwen3-30b-a3b-fp8

  Input

  $0.10

  Output

  $0.45

  Context

  33K

• Qwen3.6 35B A3B

  zerogpu/qwen3.6-35b-a3b

  Input

  $0.20

  Output

  $1.50

  Context

  262K

• Lfm2.5 1.2B Instruct

  zerogpu/LFM2.5-1.2B-Instruct

  Input

  $0.02

  Output

  $0.05

  Context

  33K

• Lfm2.5 1.2B Thinking

  zerogpu/LFM2.5-1.2B-Thinking

  Input

  $0.02

  Output

  $0.05

  Context

  33K

• Llama 3.1 8B Instruct Fast

  zerogpu/llama-3.1-8b-instruct-fast

  Input

  $0.15

  Output

  $0.28

  Context

  131K

• Llama 3.2 3B Instruct Fast

  zerogpu/llama-3.2-3b-instruct-fast

  Input

  $0.05

  Output

  $0.30

  Context

  131K