Inference host prices: baseten
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 2026-10-25T17:41:49+00:00 · https://www.baseten.co/pricing/ (first-party,
baseten-pricing)
| SKU | Name | Input / 1M | Output / 1M | Cached input | Context window | Last verified | Source |
|---|---|---|---|---|---|---|---|
| deepseek/deepseek-v4-flash-0731/baseten/unknown | deepseek/deepseek-v4-flash-0731 via BaseTen | USD 0.13 | USD 0.26 | – | 2026-10-25 17:41 UTC | source | |
| deepseek/deepseek-v4-pro-0813/baseten/unknown | deepseek/deepseek-v4-pro-0813 via BaseTen | USD 1.32 | USD 3.96 | – | 2026-10-25 17:41 UTC | source | |
| deepseek/deepseek-v4.1-flash-1017/baseten/unknown | deepseek/deepseek-v4.1-flash-1017 via BaseTen | USD 0.30 | USD 1.20 | – | 2026-10-25 17:41 UTC | source | |
| deepseek/deepseek-v4.1-flash-fast/baseten/unknown | deepseek/deepseek-v4.1-flash-fast via BaseTen | USD 0.60 | USD 2.40 | – | 2026-10-25 17:41 UTC | source | |
| deepseek/deepseek-v4.1-flash/baseten/unknown | deepseek/deepseek-v4.1-flash via BaseTen | USD 0.30 | USD 1.20 | – | 2026-10-25 17:41 UTC | source | |
| meta-models/muse-spark-open/baseten/unknown | meta-models/muse-spark-open via BaseTen | USD 1.25 | USD 4.25 | – | 2026-10-25 17:41 UTC | source | |
| moonshotai/kimi-k3/baseten/unknown | moonshotai/kimi-k3 via BaseTen | USD 3.00 | USD 15.00 | – | 2026-10-25 17:41 UTC | source | |
| nemotron-35-super-vl/baseten/unknown | nemotron-35-super-vl via BaseTen | USD 0.20 | USD 0.50 | – | 2026-10-25 17:41 UTC | source | |
| nvidia-nemotron-ultra/baseten/unknown | nvidia-nemotron-ultra via BaseTen | USD 0.60 | USD 2.40 | – | 2026-10-25 17:41 UTC | source | |
| openai/gpt-oss-120b/baseten/unknown | openai/gpt-oss-120b via BaseTen | USD 0.10 | USD 0.50 | – | 2026-10-25 17:41 UTC | source | |
| z-ai/glm-5.2-fast/baseten/unknown | z-ai/glm-5.2-fast via BaseTen | USD 2.10 | USD 6.60 | – | 2026-10-25 17:41 UTC | source | |
| z-ai/glm-5.2/baseten/unknown | z-ai/glm-5.2 via BaseTen | USD 1.40 | USD 4.40 | – | 2026-10-25 17:41 UTC | source | |
| z-ai/glm-5.3-fast/baseten/unknown | z-ai/glm-5.3-fast via BaseTen | USD 2.10 | USD 6.60 | – | 2026-10-25 17:41 UTC | source | |
| z-ai/glm-5.3-flash/baseten/unknown | z-ai/glm-5.3-flash via BaseTen | USD 0.15 | USD 0.50 | – | 2026-10-25 17:41 UTC | source | |
| z-ai/glm-5.3/baseten/unknown | z-ai/glm-5.3 via BaseTen | USD 1.40 | USD 4.40 | – | 2026-10-25 17:41 UTC | source |