Inferenceapis API pricing

Language models (24)

Prices per million tokens.

• DeepSeek Flash

  inferenceapis/deepseek-flash

  Input

  $0.40

  Output

  $1.60

  Context

  1.05M

• DeepSeek V3

  inferenceapis/deepseek-ai/DeepSeek-V3

  Input

  $0.19

  Output

  $0.38

  Context

  1.05M

• DeepSeek V4 Flash

  inferenceapis/deepseek-ai/DeepSeek-V4-Flash

  Input

  $0.19

  Output

  $0.38

  Context

  1.05M

• DeepSeek V4 Flash 0731

  inferenceapis/deepseek-ai/DeepSeek-V4-Flash-0731

  Input

  $0.19

  Output

  $0.38

  Context

  1.05M

• DeepSeek V4 Pro

  inferenceapis/deepseek-ai/DeepSeek-V4-Pro

  Input

  $1.72

  Output

  $5.15

  Context

  1.05M

• DeepSeek V4 Pro 0813

  inferenceapis/deepseek-ai/DeepSeek-V4-Pro-0813

  Input

  $1.72

  Output

  $5.15

  Context

  1.05M

• DeepSeek V4.1 Flash

  inferenceapis/deepseek-ai/DeepSeek-V4.1-Flash

  Input

  $0.40

  Output

  $1.60

  Context

  1.05M

• GLM 5.3

  inferenceapis/glm-5.3

  Input

  $1.82

  Output

  $5.72

  Context

  1.05M

• GLM 5.3 Flash

  inferenceapis/glm-5.3-flash

  Input

  $0.20

  Output

  $0.66

  Context

  1.05M

• gpt-oss-20b

  inferenceapis/gpt-oss-20b

  Input

  $0.04

  Output

  $0.19

  Context

  131K

• gpt-oss-120b

  inferenceapis/gpt-oss-120b

  Input

  $0.20

  Output

  $0.80

  Context

  131K

• Kimi K2.7 Code

  inferenceapis/kimi-k2.7-code

  Input

  $0.89

  Output

  $4.42

  Context

  262K

• Llama 3.3 70B Instruct

  inferenceapis/llama-3.3-70b

  Input

  $0.20

  Output

  $0.50

  Context

  131K

• Llama 3.3 70B Instruct

  inferenceapis/llama-3.3-70b-instruct

  Input

  $0.20

  Output

  $0.50

  Context

  131K

• Llama 3.3 70B Instruct Turbo

  inferenceapis/meta-llama/Llama-3.3-70B-Instruct-Turbo

  Input

  $0.20

  Output

  $0.50

  Context

  131K

• MiniMax M3

  inferenceapis/minimax-m3

  Input

  $0.39

  Output

  $1.56

  Context

  524K

• Qwen3 VL 235B A22B Instruct

  inferenceapis/Qwen/Qwen3-VL-235B-A22B-Instruct

  Input

  $0.26

  Output

  $1.15

  Context

  262K

• Qwen3.8 Flash

  inferenceapis/Qwen/Qwen3.8-Flash

  Input

  $0.15

  Output

  $0.50

  Context

  1M

• DeepSeek Chat

  inferenceapis/deepseek-chat

  Input

  $0.19

  Output

  $0.38

  Context

  1.05M

• DeepSeek Reasoner

  inferenceapis/deepseek-reasoner

  Input

  $0.19

  Output

  $0.38

  Context

  1.05M

• Llama 3.1 8B Instant

  inferenceapis/llama-3.1-8b-instant

  Input

  $0.20

  Output

  $0.50

  Context

  131K

• Llama 3.3 70B Versatile

  inferenceapis/llama-3.3-70b-versatile

  Input

  $0.20

  Output

  $0.50

  Context

  131K

• Qwen3 VL

  inferenceapis/qwen3-vl

  Input

  $0.26

  Output

  $1.15

  Context

  262K

• Qwen3 VL 235B

  inferenceapis/qwen3-vl-235b

  Input

  $0.26

  Output

  $1.15

  Context

  262K