Baseten

Inference host · 12 models · 24 priced routes · baseten.co

Models on Baseten

About Baseten

Across GlyphCompany profile awards Funding rounds 96 releases salaries socials

Model	In / out per 1M	Vs headline
DeepSeek V4 Flash 0731 fp8 · DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.	$0.13 / $0.26+82% vs headline	+82%	fp8 · DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.
DeepSeek V4 Flash 0731 fp32 · DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.	$0.13 / $0.26+82% vs headline	+82%	fp32 · DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.
gpt-oss-120b fp4 · gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases.	$0.1 / $0.5+1094% vs headline	+1094%	fp4 · gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases.
gpt-oss-120b fp4-us, fp4 · gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases.	$0.1 / $0.5+1094% vs headline	+1094%	fp4-us, fp4 · gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases.
GLM 5.3 Flash fp8 · GLM-5.3-Flash is a native multimodal model from Z.ai.	$0.15 / $0.5+389% vs headline	+389%	fp8 · GLM-5.3-Flash is a native multimodal model from Z.ai.
GLM 5.3 Flash fp8-us, fp8 · GLM-5.3-Flash is a native multimodal model from Z.ai.	$0.15 / $0.5+389% vs headline	+389%	fp8-us, fp8 · GLM-5.3-Flash is a native multimodal model from Z.ai.
Nemotron 3.5 Super VL fp4 · NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total.	$0.2 / $0.5+108% vs headline	+108%	fp4 · NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total.
DeepSeek V4.1 Flash us · DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture.	$0.3 / $1.2+383% vs headline	+383%	us · DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture.
DeepSeek V4.1 Flash DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture.	$0.3 / $1.2+383% vs headline	+383%	DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture.
DeepSeek V4.1 Flash 1017 DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name.	$0.3 / $1.2+100% vs headline	+100%	DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name.
Nemotron 3 Ultra fp4 · NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE).	$0.6 / $2.4+42% vs headline	+42%	fp4 · NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE).
Nemotron 3 Ultra fp4-us, fp4 · NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE).	$0.6 / $2.4+42% vs headline	+42%	fp4-us, fp4 · NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE).
DeepSeek V4.1 Flash 1017 fast · DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name.	$0.6 / $2.4+300% vs headline	+300%	fast · DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name.
DeepSeek V4 Pro 0813 fp4 · DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek.	$1.32 / $3.96+100% vs headline	+100%	fp4 · DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek.
Muse Spark Open fp4 · Muse Spark Open is a coding-optimized open-weight model.	$1.25 / $4.25Same vs headline	Same	fp4 · Muse Spark Open is a coding-optimized open-weight model.
GLM 5.3 fp4 · GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.	$1.4 / $4.4+344% vs headline	+344%	fp4 · GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.
GLM 5.2 fp8 · GLM 5.2 is a large-scale reasoning model from Z.ai.	$1.4 / $4.4+131% vs headline	+131%	fp8 · GLM 5.2 is a large-scale reasoning model from Z.ai.
GLM 5.3 fp4-us, fp4 · GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.	$1.4 / $4.4+344% vs headline	+344%	fp4-us, fp4 · GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.
GLM 5.2 fp8-us, fp8 · GLM 5.2 is a large-scale reasoning model from Z.ai.	$1.4 / $4.4+131% vs headline	+131%	fp8-us, fp8 · GLM 5.2 is a large-scale reasoning model from Z.ai.
GLM 5.3 fast, fp8 · GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.	$2.1 / $6.6+566% vs headline	+566%	fast, fp8 · GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.