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
- Last verified 2026-10-24T01:11:22+00:00 · https://www.together.ai/pricing (first-party,
together-pricing)
| SKU | Name | Input / 1M | Output / 1M | Cached input | Context window | Last verified | Source |
|---|---|---|---|---|---|---|---|
| deepseek/deepseek-v4-pro-0813/together/unknown | deepseek/deepseek-v4-pro-0813 via Together | USD 1.32 | USD 3.96 | – | 2026-10-24 01:11 UTC | source | |
| deepseek/deepseek-v4.1-flash/together/unknown | deepseek/deepseek-v4.1-flash via Together | USD 0.30 | USD 1.20 | – | 2026-10-24 01:11 UTC | source | |
| minimax/minimax-m3/together/unknown | minimax/minimax-m3 via Together | USD 0.30 | USD 1.20 | – | 2026-10-24 01:11 UTC | source | |
| moonshotai/kimi-k3/together/unknown | moonshotai/kimi-k3 via Together | USD 3.00 | USD 15.00 | – | 2026-10-24 01:11 UTC | source | |
| openai/gpt-oss-120b/together/unknown | openai/gpt-oss-120b via Together | USD 0.15 | USD 0.60 | – | 2026-10-24 01:11 UTC | source | |
| qwen/qwen3.5-397b-a17b/together/unknown | qwen/qwen3.5-397b-a17b via Together | USD 0.60 | USD 3.60 | – | 2026-10-24 01:11 UTC | source | |
| qwen/qwen3.8-max/together/unknown | qwen/qwen3.8-max via Together | USD 2.00 | USD 6.00 | – | 2026-10-24 01:11 UTC | source | |
| z-ai/glm-5.3/together/unknown | z-ai/glm-5.3 via Together | USD 1.40 | USD 4.40 | – | 2026-10-24 01:11 UTC | source |