Baseten
22 modelsProvider docs
As of Oct 4, 2026, Baseten lists 22 supported models in the Sovyron catalog, including DeepSeek V4.1 Flash, deepseek-ai/DeepSeek-V4.1-Flash-Fast, GLM-5.3-Flash, GLM 5.3 Fast and GLM-5.3 — deepseek-flash, glm-flash, glm, deepseek-thinking, ling and kimi-k3 families. Its metered rates span $0.1625–$6 per 1M tokens on a 3:1 input:output blend, and every price in the table is Baseten's own, normalized to USD — open a model to compare it with the cheapest offer across all providers.
Supported models and pricing
22 of 22 models
| Model | 1M input | 1M output | 1M cache read | Context | Released |
|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | $0.3 | $1.2 | $0.03 | 1.0M | Sep 10, 2026 |
| deepseek-ai/DeepSeek-V4.1-Flash-Fast | $0.6 | $2.4 | — | 1.0M | Sep 10, 2026 |
| GLM-5.3-Flash | $0.15 | $0.5 | — | 1.0M | Aug 26, 2026 |
| GLM 5.3 Fast | $2.1 | $6.6 | — | 1.0M | Aug 14, 2026 |
| GLM-5.3 | $1.4 | $4.4 | $0.14 | 1.0M | Aug 14, 2026 |
| DeepSeek V4 Pro 0813 | $1.32 | $3.96 | — | 1.0M | Aug 12, 2026 |
| DeepSeek V4 Flash 0731 | $0.13 | $0.26 | $0.028 | 1.0M | Jul 31, 2026 |
| Inkling Small | $0.5 | $1.2 | $0.1 | 1.0M | Jul 30, 2026 |
| Kimi K3 | $3 | $15 | — | 1.0M | Jul 16, 2026 |
| Inkling | $1 | $4.05 | — | 1.0M | Jul 15, 2026 |
| GLM 5.2 Fast | $2.1 | $6.6 | $0.21 | 1.0M | Jun 13, 2026 |
| GLM-5.2 | $1.4 | $4.4 | $0.3 | 1.0M | Jun 13, 2026 |
| Kimi K2.7 Code | $0.95 | $4 | $0.16 | 262k | Jun 12, 2026 |
| Nemotron Ultra | $0.6 | $2.4 | $0.12 | 203k | Jun 4, 2026 |
| DeepSeek V4 Pro | $1.74 | $3.48 | $0.145 | 1.0M | Apr 24, 2026 |
| Kimi K2.6 | $0.95 | $4 | $0.16 | 262k | Apr 21, 2026 |
| GLM-5.1 | $1.3 | $4.3 | $0.26 | 203k | Apr 7, 2026 |
| Nemotron Super | $0.3 | $0.75 | $0.06 | 203k | Mar 11, 2026 |
| GLM-5 | $0.95 | $3.15 | $0.2 | 203k | Feb 12, 2026 |
| Kimi K2.5 | $0.6 | $3 | $0.12 | 262k | Jan 30, 2026 |
| GLM-4.7 | $0.6 | $2.2 | $0.12 | 200k | Dec 22, 2025 |
| OpenAI GPT 120B | $0.1 | $0.5 | — | 128k | Aug 5, 2025 |