InfraRabbit

Inference host prices: together

Open-weight models served by inference hosts, with each host's price per 1M tokens (input, output). One row per model, host and quantization.

Sources for this list

SKUNameInput / 1MOutput / 1MCached inputContext windowLast verifiedSource
deepseek/deepseek-v4-pro-0813/together/unknowndeepseek/deepseek-v4-pro-0813 via Together USD 1.32USD 3.96– 2026-10-24 01:11 UTCsource
deepseek/deepseek-v4.1-flash/together/unknowndeepseek/deepseek-v4.1-flash via Together USD 0.30USD 1.20– 2026-10-24 01:11 UTCsource
minimax/minimax-m3/together/unknownminimax/minimax-m3 via Together USD 0.30USD 1.20– 2026-10-24 01:11 UTCsource
moonshotai/kimi-k3/together/unknownmoonshotai/kimi-k3 via Together USD 3.00USD 15.00– 2026-10-24 01:11 UTCsource
openai/gpt-oss-120b/together/unknownopenai/gpt-oss-120b via Together USD 0.15USD 0.60– 2026-10-24 01:11 UTCsource
qwen/qwen3.5-397b-a17b/together/unknownqwen/qwen3.5-397b-a17b via Together USD 0.60USD 3.60– 2026-10-24 01:11 UTCsource
qwen/qwen3.8-max/together/unknownqwen/qwen3.8-max via Together USD 2.00USD 6.00– 2026-10-24 01:11 UTCsource
z-ai/glm-5.3/together/unknownz-ai/glm-5.3 via Together USD 1.40USD 4.40– 2026-10-24 01:11 UTCsource