Llamagate API pricing

Language models (14)

Prices per million tokens.

• Llama 3.2 3B Instruct

  llamagate/llama-3.2-3b

  Input

  $0.04

  Output

  $0.08

  Context

  131K

• Llama3.1 8B

  llamagate/llama-3.1-8b

  Input

  $0.03

  Output

  $0.05

  Context

  131K

• Qwen2.5 Coder 7B Instruct

  llamagate/qwen2.5-coder-7b

  Input

  $0.06

  Output

  $0.12

  Context

  33K

• Qwen3 8B

  llamagate/qwen3-8b

  Input

  $0.04

  Output

  $0.14

  Context

  33K

• Qwen3 VL 8B Instruct

  llamagate/qwen3-vl-8b

  Input

  $0.15

  Output

  $0.55

  Context

  33K

• Codellama 7B

  llamagate/codellama-7b

  Input

  $0.06

  Output

  $0.12

  Context

  16K

• DeepSeek Coder 6.7B

  llamagate/deepseek-coder-6.7b

  Input

  $0.06

  Output

  $0.12

  Context

  16K

• DeepSeek R1 7B Qwen

  llamagate/deepseek-r1-7b-qwen

  Input

  $0.08

  Output

  $0.15

  Context

  131K

• DeepSeek R1 8B

  llamagate/deepseek-r1-8b

  Input

  $0.10

  Output

  $0.20

  Context

  66K

• Dolphin3 8B

  llamagate/dolphin3-8b

  Input

  $0.08

  Output

  $0.15

  Context

  128K

• Gemma3 4B

  llamagate/gemma3-4b

  Input

  $0.03

  Output

  $0.08

  Context

  128K

• Llava 7B

  llamagate/llava-7b

  Input

  $0.10

  Output

  $0.20

  Context

  4K

• Mistral 7B V0.3

  llamagate/mistral-7b-v0.3

  Input

  $0.10

  Output

  $0.15

  Context

  33K

• Openthinker 7B

  llamagate/openthinker-7b

  Input

  $0.08

  Output

  $0.15

  Context

  33K