Baseten
Dedicated inference for open-weight models.
Baseten runs open-weight models on dedicated infrastructure with an OpenAI-compatible endpoint. Its catalog is deliberately small — a curated set of frontier open models served fast, rather than a resale of other providers' models.
Open-weight focus Dedicated deployments Small curated catalog
- Status
- Live
- Models in catalog
- 20
- Text / multimodal
- 20
- Publishes pricing for
- 20 models
- Largest context window
- 1M tokens
- Model id style
- Canonical `provider/model` for open-weight models.
- Billing
- Usage-based, billed by Baseten.
- Catalog last checked
- Website
- baseten.co
- Documentation
- Developer docs
Catalog
20 models on Baseten
The 20 most widely available are shown; the rest are searchable in the full model list. "Id on this gateway" is what Baseten calls the model — where it differs from the canonical id, that difference is what a router has to translate.
Search all 20 models on Baseten| Model | Vendor | Type | Id on this gateway | Available on | Context | Input / Mtok |
|---|---|---|---|---|---|---|
DeepSeek V4.1 Flash 1017
deepseek/deepseek-v4.1-flash-1017
|
DeepSeek | Multimodal | deepseek-ai/DeepSeek-V4.1-Flash-1017 |
BasetenCloudflareFireworksMorphNanoGPTOpenRouterOrcaRouterRampRequestySailTogetherVercel | 1M | $0.050–$0.300 |
GLM 5.3
z-ai/glm-5.3
|
Z.ai | Multimodal | zai-org/GLM-5.3 |
BasetenCloudflareFireworksMorphNanoGPTOpenRouterOrcaRouterRampRequestySailTogetherVercel | 1M | $0.078–$1.40 |
GLM 5.3 Flash
z-ai/glm-5.3-flash
|
Z.ai | Multimodal | zai-org/GLM-5.3-Flash |
BasetenCloudflareFireworksMorphNanoGPTOpenRouterOrcaRouterRampRequestySailTogetherVercel | 1M | $0.029–$0.150 |
DeepSeek V4.1 Flash
deepseek/deepseek-v4.1-flash
|
DeepSeek | Multimodal | deepseek-ai/DeepSeek-V4.1-Flash |
BasetenCloudflareFireworksMorphNanoGPTOpenRouterOrcaRouterRampRequestyTogetherVercel | 1M | $0.045–$0.300 |
Muse Spark Open
meta-llama/muse-spark-open
|
Meta | Multimodal | meta-models/muse-spark-open |
BasetenCheaper InferenceCloudflareConcentrateExperiential LabsFireworksNanoGPTOpenRouterRampRequestyVercel | 1M | $1.06–$1.25 |
Kimi K3
moonshotai/kimi-k3
|
Moonshot AI | Multimodal | moonshotai/Kimi-K3 |
BasetenCloudflareFireworksMorphNanoGPTOpenRouterOrcaRouterRequestySailTogetherVercel | 1M | $0.149–$3.00 |
DeepSeek V4 Flash 0731
deepseek/deepseek-v4-flash-0731
|
DeepSeek | Text | deepseek-ai/DeepSeek-V4-Flash-0731 |
BasetenCloudflareMorphNanoGPTOpenRouterOrcaRouterRequestySailVercel | 1M | $0.050–$0.220 |
DeepSeek V4 Pro 0813
deepseek/deepseek-v4-pro-0813
|
DeepSeek | Text | deepseek-ai/DeepSeek-V4-Pro-0813 |
BasetenCloudflareNanoGPTOpenRouterOrcaRouterRequestySailTogetherVercel | 1M | $0.115–$1.32 |
GLM 5.2
z-ai/glm-5.2
|
Z.ai | Multimodal | zai-org/GLM-5.2 |
BasetenCloudflareNanoGPTOpenRouterOrcaRouterRampRequestyTogetherVercel | 1M | $0.0060–$1.40 |
OpenAI GPT 120B
openai/gpt-oss-120b
|
OpenAI | Text | openai/gpt-oss-120b |
BasetenCloudflareFireworksNanoGPTOpenRouterRequestyTogetherVercel | 131.1K | $0.030–$0.150 |
GLM 5.2 Fast
z-ai/glm-5.2-fast
|
Z.ai | Multimodal | zai-org/GLM-5.2-Fast |
BasetenRampRequestyVercel | 1M | $2.10–$2.80 |
GLM 5.3 Fast
z-ai/glm-5.3-fast
|
Z.ai | Multimodal | zai-org/GLM-5.3-Fast |
BasetenFireworksVercel | 1M | $2.10 |
DeepSeek V4.1 Flash 1017 Fast
deepseek/deepseek-v4.1-flash-1017-fast
|
DeepSeek | Multimodal | deepseek-ai/DeepSeek-V4.1-Flash-1017-Fast |
BasetenVercel | 1M | $0.600 |
DeepSeek V4.1 Flash Fast
deepseek/deepseek-v4.1-flash-fast
|
DeepSeek | Multimodal | deepseek-ai/DeepSeek-V4.1-Flash-Fast |
BasetenVercel | 1M | $0.600 |
Beam
reflection/beam-1.0
|
Reflection | Text | reflection/Beam-1.0 |
BasetenNanoGPT | 1M | $0.400–$0.500 |
elephant-1
decision-models/baseten-elephant-9b-latest
|
Decision Models | Multimodal | decision-models/baseten-elephant-9b-latest |
Baseten | 16.4K | $0.035 |
joey-1
decision-models/baseten-joey-2b-latest
|
Decision Models | Multimodal | decision-models/baseten-joey-2b-latest |
Baseten | 16.4K | $0.010 |
mammoth-1
decision-models/baseten-mammoth-27b-latest
|
Decision Models | Multimodal | decision-models/baseten-mammoth-27b-latest |
Baseten | 16.4K | $0.100 |
Nemotron Ultra
nvidia/nvidia-nemotron-3-ultra-550b-a55b
|
NVIDIA | Text | nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B |
Baseten | 202.8K | $0.600 |
Nemotron Super 3.5
nvidia/nvidia-nemotron-3.5-super-vl-120b-a12b
|
NVIDIA | Multimodal | nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B |
Baseten | 1M | $0.200 |
Cheapest here
Lowest input prices on Baseten
Ranked by what this gateway charges, not by the cheapest price anywhere.
By model type
What Baseten carries
A gateway with 2,000 models is not necessarily a gateway with 2,000 chat models.
Not exclusive
15 of these models are on other gateways too
Anything in this list can be served from somewhere other than Baseten without changing the model id your application sends.