What is the latest version of SambaNova SN40L?

The current shipped version of SambaNova SN40L is SN40L, as of November 8, 2026.

How much does SambaNova SN40L cost?

SambaNova SN40L has no published flat entry price. Free tier available; pay-as-you-go developer and subscription-based enterprise plans offered.

What AI model does SambaNova SN40L use?

SambaNova SN40L runs primarily on DeepSeek-V3.1.

← Chips & Compute

SambaNova SN40L

Name: SambaNova SN40L
Author: SambaNova

SambaNova · #10 most active of 18 in Chips & Compute

Compare →

Reconfigurable dataflow units with three-tier memory for serving many models per node.

100

Trust score · Verified

2 data points checked · 2026-11-03

Model stack: VerifiedEntry price: UnverifiableVersion: VerifiedHow this works →

Current version

SN40L

Entry cost

Free tier available; pay-as-you-go developer and subscription-based enterprise plans offered.

Changes / 30d

The short answers · verified November 8, 2026

What is the latest version of SambaNova SN40L?: The current shipped version of SambaNova SN40L is SN40L, as of November 8, 2026.
How much does SambaNova SN40L cost?: SambaNova SN40L has no published flat entry price. Free tier available; pay-as-you-go developer and subscription-based enterprise plans offered.
What AI model does SambaNova SN40L use?: SambaNova SN40L runs primarily on DeepSeek-V3.1.

Source: SambaNova — cloud.sambanova.ai · Reusable under CC BY 4.0 — cite Tomorrow

Capabilities

three-tier memory
many models per node
fast open-model serving
Reconfigurable Dataflow Unit (RDU)
Three-tier memory architecture
Dataflow processing
Low power inference
Multi-model concurrency
OpenAI-compatible APIs
OpenAI Compatible APIs
Fast Inference
OpenAI Compatibility
Anthropic Compatibility
Function calling
JSON mode
Vision
Video
Audio
Embeddings
Prompt caching
Text generation
Inference
OpenAI compatibility
RDU
Fast inference
Three-tier memory
JSON Mode
Function Calling
API Access
Dataflow Architecture
Vision support
Inference Platform
OpenAI compatible API
API keys
OpenAI-compatible API
OpenAI-Compatible APIs
SambaOrchestrator
RDU Acceleration
Text Generation
Reasoning
API
API access
Custom Checkpoints
RAG
Anthropic compatibility
APIs
AI Inference
On-Demand Pricing
Inference API
Text to speech
SambaRack integration
RDU (Reconfigurable Dataflow Unit)
OpenAI API Compatibility
RAG support
Multi-model execution
Low-latency inference
Agentic AI workloads
Dataflow architecture
RDU hardware
Multi-model deployment
SambaCloud models
Sovereign AI
BYOC (Bring Your Own Checkpoints)
Agentic workflows
Bring Your Own Checkpoints
BYOC
Multi-model serving
Dataflow Processing
Three-Tier Memory
AI Inference Hardware
RDU Chip
OpenAI compatible APIs
Agentic inference
Low Power Inference
AI Inference Platform
RDU Architecture
Agentic Inference
RDU chip
SambaCloud API
Serverless Inference

Pricing

Free
Start exploring SambaNova Cloud, includes pay-as-you-go credits
Free
Developer Pay as you go
Pay as you go for fast inference, standard rate limits
Free

Entry price over time

8 of 67 points reconstructed from Internet Archive captures (hollow dots) — dated by capture, not by when we first saw the page. View a capture

9/10/2025 · $011/8/2026 · $0

Geek mode

Models under the hood

DeepSeek-V3.1
DeepSeek
disclosed
gpt-oss-120b
OpenAI
disclosed
Llama / DeepSeek open weights
open weights
disclosed
Llama 3
Meta
disclosed
Llama 3.1
Meta
disclosed
Llama 3.1 (8B, 70B, 405B)
Meta
disclosed
Llama 3.1 405B
Meta
disclosed
Llama 3.1 70B
Meta
disclosed
Llama 3.1 8B
Meta
disclosed
MiniMax M2.7
MiniMax
disclosed
MiniMax M3.1 Flash
MiniMax
inferred
Production & Preview models
SambaNova
unknown
RDU
SambaNova
inferred
RDU dataflow
SambaNova
disclosed
SambaNova RDU
SambaNova
inferred
SambaNova SN40L RDUs
SambaNova
inferred
SambaRack SN40-16
SambaNova
inferred
SN40L RDU
SambaNova
disclosed

Context window

—

Public API

yes

Multi-model routing

yes

Stack signals

rdu
hardware

Shared model stack

Other tracked products running on the same foundation models — a quick read on how much of the catalog moves when one of these models changes.

Llama 3Meta · 3 products
MiniMax M2.7MiniMax · 3 products
MiniMax M3.1 FlashMiniMax · 3 products
DeepSeek-V3.1DeepSeek · 2 products
- ERNIE Bot
- SambaNova SN40L
Llama 3.1Meta · 2 products
- AWS Trainium2
- SambaNova SN40L
Llama 3.1 405BMeta · 2 products
- AWS Trainium2
- SambaNova SN40L
openai/gpt-oss-120b+1 aliasOpenAI · 2 products
- Groq LPU
- SambaNova SN40L
Llama / DeepSeek open weightsopen weights · 1 product
- SambaNova SN40L

green disclosed · amber inferred · grey unattributed. Aliases are folded into one model; provider concentration counts only models with an established vendor.

Reported scale

Reference data. Each figure is whatever the source actually said — weekly users, downloads, revenue run-rate — with its own definition and date. These are not comparable between tools and are never used to rank anything.

No public usage figure on record for this product.

Also in Chips & Compute

All Chips & Compute

Google TPU Ironwood

Google

Inference-first TPU pods

Version: 7th-generation (Ironwood)
Cost: from $5.4/unit
Model: Gemini

Cerebras WSE-3

Cerebras

Wafer-scale inference and training

Version: CS-4
Cost: Free trial credits available; developer tier has free promotional credits.
Model: Codex-Spark

Tenstorrent Blackhole

Tenstorrent

Open RISC-V AI hardware

Version: Blackhole
Cost: from $999/unit
Model: Blackhole Tensix

AWS Trainium2

AWS

Cloud-native training silicon

Version: Trainium2
Cost: Pricing is not published on the page. Available via EC2 instances/UltraServers.
Model: Neuron compiler

NVIDIA Blackwell

NVIDIA

GB200/B200 rack-scale AI systems

Version: GB200 NVL72
Cost: Pricing is not published (enterprise/quote-only)
Model: Blackwell

AMD Instinct MI355X

AMD

High-memory GPU alternative

Version: MI355X
Cost: Enterprise hardware, pricing not published
Model: CDNA

Elsewhere on the same models

Products in other segments that name one of SambaNova SN40L's models in their stack.

ERNIE Bot

BaiduChina

Baidu's flagship assistant, now on open-weight ERNIE models.

Version: 5.0
Cost: Pay-as-you-go API pricing with select free trial skills/components. Ernie 5.0 at 0.006-0.01 RMB per 1k input tokens.
Model: DeepSeek-V3.1

Change history

Nov 8, 2026first seencapability
New capabilities: Serverless Inference
79 tracked80 tracked · +Serverless Inference
source
Nov 2, 2026first seencapability
New capabilities: SambaCloud API
78 tracked79 tracked · +SambaCloud API
source
Oct 27, 2026first seenmodel
SambaNova SN40L added MiniMax M3.1 Flash to its model stack
DeepSeek-V3.1, Llama / DeepSeek open weights, Llama 3, Llama 3.1, Llama 3.1 (8B, 70B, 405B), Llama 3.1 405B, Llama 3.1 70B, Llama 3.1 8B, MiniMax M2.7, Production & Preview models, RDU, RDU dataflow, SN40L RDU, SambaNova RDU, SambaNova SN40L RDUs, SambaRack SN40-16, gpt-oss-120bDeepSeek-V3.1, Llama / DeepSeek open weights, Llama 3, Llama 3.1, Llama 3.1 (8B, 70B, 405B), Llama 3.1 405B, Llama 3.1 70B, Llama 3.1 8B, MiniMax M2.7, MiniMax M3.1 Flash, Production & Preview models, RDU, RDU dataflow, SN40L RDU, SambaNova RDU, SambaNova SN40L RDUs, SambaRack SN40-16, gpt-oss-120b
source
Oct 25, 2026first seencapability
New capabilities: RDU chip
77 tracked78 tracked · +RDU chip
source
Oct 24, 2026first seenmodel
SambaNova SN40L added SambaNova RDU to its model stack
DeepSeek-V3.1, Llama / DeepSeek open weights, Llama 3, Llama 3.1, Llama 3.1 (8B, 70B, 405B), Llama 3.1 405B, Llama 3.1 70B, Llama 3.1 8B, MiniMax M2.7, Production & Preview models, RDU, RDU dataflow, SN40L RDU, SambaNova SN40L RDUs, SambaRack SN40-16, gpt-oss-120bDeepSeek-V3.1, Llama / DeepSeek open weights, Llama 3, Llama 3.1, Llama 3.1 (8B, 70B, 405B), Llama 3.1 405B, Llama 3.1 70B, Llama 3.1 8B, MiniMax M2.7, Production & Preview models, RDU, RDU dataflow, SN40L RDU, SambaNova RDU, SambaNova SN40L RDUs, SambaRack SN40-16, gpt-oss-120b
source
Oct 23, 2026first seenmodel
SambaNova SN40L added Production & Preview models to its model stack
DeepSeek-V3.1, Llama / DeepSeek open weights, Llama 3, Llama 3.1, Llama 3.1 (8B, 70B, 405B), Llama 3.1 405B, Llama 3.1 70B, Llama 3.1 8B, MiniMax M2.7, RDU, RDU dataflow, SN40L RDU, SambaNova SN40L RDUs, SambaRack SN40-16, gpt-oss-120bDeepSeek-V3.1, Llama / DeepSeek open weights, Llama 3, Llama 3.1, Llama 3.1 (8B, 70B, 405B), Llama 3.1 405B, Llama 3.1 70B, Llama 3.1 8B, MiniMax M2.7, Production & Preview models, RDU, RDU dataflow, SN40L RDU, SambaNova SN40L RDUs, SambaRack SN40-16, gpt-oss-120b
source
Oct 21, 2026first seencapability
New capabilities: RDU Architecture, Agentic Inference
75 tracked77 tracked · +RDU Architecture, Agentic Inference
source
Oct 20, 2026first seencapability
New capabilities: AI Inference Platform
74 tracked75 tracked · +AI Inference Platform
source
Oct 19, 2026first seenmodel
SambaNova SN40L added RDU to its model stack
DeepSeek-V3.1, Llama / DeepSeek open weights, Llama 3, Llama 3.1, Llama 3.1 (8B, 70B, 405B), Llama 3.1 405B, Llama 3.1 70B, Llama 3.1 8B, MiniMax M2.7, RDU dataflow, SN40L RDU, SambaNova SN40L RDUs, SambaRack SN40-16, gpt-oss-120bDeepSeek-V3.1, Llama / DeepSeek open weights, Llama 3, Llama 3.1, Llama 3.1 (8B, 70B, 405B), Llama 3.1 405B, Llama 3.1 70B, Llama 3.1 8B, MiniMax M2.7, RDU, RDU dataflow, SN40L RDU, SambaNova SN40L RDUs, SambaRack SN40-16, gpt-oss-120b
source
Oct 17, 2026first seencapability
New capabilities: Low Power Inference
73 tracked74 tracked · +Low Power Inference
source
Oct 16, 2026first seencapability
New capabilities: OpenAI compatible APIs, Agentic inference
71 tracked73 tracked · +OpenAI compatible APIs, Agentic inference
source
Oct 15, 2026first seencapability
New capabilities: RDU Chip
70 tracked71 tracked · +RDU Chip
source
Oct 14, 2026first seencapability
New capabilities: Dataflow Processing, Three-Tier Memory, AI Inference Hardware
67 tracked70 tracked · +Dataflow Processing, Three-Tier Memory, AI Inference Hardware
source
Oct 13, 2026first seencapability
New capabilities: Multi-model serving
66 tracked67 tracked · +Multi-model serving
source
Oct 11, 2026first seencapability
New capabilities: BYOC
65 tracked66 tracked · +BYOC
source
Oct 9, 2026first seencapability
New capabilities: Agentic workflows, Bring Your Own Checkpoints
63 tracked65 tracked · +Agentic workflows, Bring Your Own Checkpoints
source
Oct 6, 2026first seencapability
New capabilities: Sovereign AI, BYOC (Bring Your Own Checkpoints)
61 tracked63 tracked · +Sovereign AI, BYOC (Bring Your Own Checkpoints)
source
Oct 5, 2026first seenmodel
SambaNova SN40L added SambaNova SN40L RDUs to its model stack
DeepSeek-V3.1, Llama / DeepSeek open weights, Llama 3, Llama 3.1, Llama 3.1 (8B, 70B, 405B), Llama 3.1 405B, Llama 3.1 70B, Llama 3.1 8B, MiniMax M2.7, RDU dataflow, SN40L RDU, SambaRack SN40-16, gpt-oss-120bDeepSeek-V3.1, Llama / DeepSeek open weights, Llama 3, Llama 3.1, Llama 3.1 (8B, 70B, 405B), Llama 3.1 405B, Llama 3.1 70B, Llama 3.1 8B, MiniMax M2.7, RDU dataflow, SN40L RDU, SambaNova SN40L RDUs, SambaRack SN40-16, gpt-oss-120b
source
Oct 3, 2026first seencapability
New capabilities: SambaCloud models
60 tracked61 tracked · +SambaCloud models
source
Oct 1, 2026first seenmodel
SambaNova SN40L added to its model stack
DeepSeek-V3.1, Llama / DeepSeek open weights, Llama 3, Llama 3.1, Llama 3.1 (8B, 70B, 405B), Llama 3.1 405B, Llama 3.1 70B, Llama 3.1 8B, MiniMax M2.7, RDU dataflow, SN40L RDU, SambaRack SN40-16, gpt-oss-120bDeepSeek-V3.1, Llama / DeepSeek open weights, Llama 3, Llama 3.1, Llama 3.1 (8B, 70B, 405B), Llama 3.1 405B, Llama 3.1 70B, Llama 3.1 8B, MiniMax M2.7, RDU dataflow, SN40L RDU, SambaRack SN40-16, gpt-oss-120b
source
Sep 29, 2026first seencapability
New capabilities: Multi-model deployment
59 tracked60 tracked · +Multi-model deployment
source
Sep 28, 2026first seencapability
New capabilities: RDU hardware
58 tracked59 tracked · +RDU hardware
source
Sep 27, 2026first seencapability
New capabilities: Low-latency inference, Agentic AI workloads, Dataflow architecture
55 tracked58 tracked · +Low-latency inference, Agentic AI workloads, Dataflow architecture
source
Sep 23, 2026first seencapability
New capabilities: Multi-model execution
54 tracked55 tracked · +Multi-model execution
source
Sep 22, 2026first seencapability
New capabilities: OpenAI API Compatibility, RAG support
52 tracked54 tracked · +OpenAI API Compatibility, RAG support
source
Sep 21, 2026first seencapability
New capabilities: SambaRack integration, RDU (Reconfigurable Dataflow Unit)
50 tracked52 tracked · +SambaRack integration, RDU (Reconfigurable Dataflow Unit)
source
Sep 19, 2026first seenmodel
SambaNova SN40L added Llama 3 to its model stack
DeepSeek-V3.1, Llama / DeepSeek open weights, Llama 3.1, Llama 3.1 (8B, 70B, 405B), Llama 3.1 405B, Llama 3.1 70B, Llama 3.1 8B, MiniMax M2.7, RDU dataflow, SN40L RDU, SambaRack SN40-16, gpt-oss-120bDeepSeek-V3.1, Llama / DeepSeek open weights, Llama 3, Llama 3.1, Llama 3.1 (8B, 70B, 405B), Llama 3.1 405B, Llama 3.1 70B, Llama 3.1 8B, MiniMax M2.7, RDU dataflow, SN40L RDU, SambaRack SN40-16, gpt-oss-120b
source
Sep 15, 2026first seenmodel
SambaNova SN40L added to its model stack
DeepSeek-V3.1, Llama / DeepSeek open weights, Llama 3.1, Llama 3.1 (8B, 70B, 405B), Llama 3.1 405B, Llama 3.1 70B, Llama 3.1 8B, MiniMax M2.7, RDU dataflow, SN40L RDU, SambaRack SN40-16, gpt-oss-120bDeepSeek-V3.1, Llama / DeepSeek open weights, Llama 3.1, Llama 3.1 (8B, 70B, 405B), Llama 3.1 405B, Llama 3.1 70B, Llama 3.1 8B, MiniMax M2.7, RDU dataflow, SN40L RDU, SambaRack SN40-16, gpt-oss-120b
source
Sep 13, 2026first seenmodel
SambaNova SN40L added to its model stack
DeepSeek-V3.1, Llama / DeepSeek open weights, Llama 3.1, Llama 3.1 (8B, 70B, 405B), Llama 3.1 405B, Llama 3.1 70B, Llama 3.1 8B, MiniMax M2.7, RDU dataflow, SN40L RDU, SambaRack SN40-16, gpt-oss-120bDeepSeek-V3.1, Llama / DeepSeek open weights, Llama 3.1, Llama 3.1 (8B, 70B, 405B), Llama 3.1 405B, Llama 3.1 70B, Llama 3.1 8B, MiniMax M2.7, RDU dataflow, SN40L RDU, SambaRack SN40-16, gpt-oss-120b
source
Sep 11, 2026first seencapability
New capabilities: Text to speech
49 tracked50 tracked · +Text to speech
source
Sep 10, 2026first seencapability
New capabilities: Inference API
48 tracked49 tracked · +Inference API
source
Sep 7, 2026first seencapability
New capabilities: AI Inference, On-Demand Pricing
46 tracked48 tracked · +AI Inference, On-Demand Pricing
source
Sep 5, 2026first seenmodel
SambaNova SN40L added to its model stack
DeepSeek-V3.1, Llama / DeepSeek open weights, Llama 3.1, Llama 3.1 (8B, 70B, 405B), Llama 3.1 405B, Llama 3.1 70B, Llama 3.1 8B, MiniMax M2.7, RDU dataflow, SN40L RDU, SambaRack SN40-16, gpt-oss-120bDeepSeek-V3.1, Llama / DeepSeek open weights, Llama 3.1, Llama 3.1 (8B, 70B, 405B), Llama 3.1 405B, Llama 3.1 70B, Llama 3.1 8B, MiniMax M2.7, RDU dataflow, SN40L RDU, SambaRack SN40-16, gpt-oss-120b
source
Sep 5, 2026first seencapability
New capabilities: APIs
45 tracked46 tracked · +APIs
source
Sep 4, 2026first seenmodel
SambaNova SN40L added SambaRack SN40-16 to its model stack
DeepSeek-V3.1, Llama / DeepSeek open weights, Llama 3.1, Llama 3.1 (8B, 70B, 405B), Llama 3.1 405B, Llama 3.1 70B, Llama 3.1 8B, MiniMax M2.7, RDU dataflow, SN40L RDU, gpt-oss-120bDeepSeek-V3.1, Llama / DeepSeek open weights, Llama 3.1, Llama 3.1 (8B, 70B, 405B), Llama 3.1 405B, Llama 3.1 70B, Llama 3.1 8B, MiniMax M2.7, RDU dataflow, SN40L RDU, SambaRack SN40-16, gpt-oss-120b
source
Sep 2, 2026first seencapability
New capabilities: Anthropic compatibility
44 tracked45 tracked · +Anthropic compatibility
source
Aug 31, 2026first seenmodel
SambaNova SN40L added to its model stack
DeepSeek-V3.1, Llama / DeepSeek open weights, Llama 3.1, Llama 3.1 (8B, 70B, 405B), Llama 3.1 405B, Llama 3.1 70B, Llama 3.1 8B, MiniMax M2.7, RDU dataflow, SN40L RDU, gpt-oss-120bDeepSeek-V3.1, Llama / DeepSeek open weights, Llama 3.1, Llama 3.1 (8B, 70B, 405B), Llama 3.1 405B, Llama 3.1 70B, Llama 3.1 8B, MiniMax M2.7, RDU dataflow, SN40L RDU, gpt-oss-120b
source
Aug 30, 2026first seencapability
New capabilities: Custom Checkpoints, RAG
42 tracked44 tracked · +Custom Checkpoints, RAG
source
Aug 29, 2026first seencapability
New capabilities: API access
41 tracked42 tracked · +API access
source
Aug 28, 2026first seenmodel
SambaNova SN40L added SN40L RDU to its model stack
DeepSeek-V3.1, Llama / DeepSeek open weights, Llama 3.1, Llama 3.1 (8B, 70B, 405B), Llama 3.1 405B, Llama 3.1 70B, Llama 3.1 8B, MiniMax M2.7, RDU dataflow, gpt-oss-120bDeepSeek-V3.1, Llama / DeepSeek open weights, Llama 3.1, Llama 3.1 (8B, 70B, 405B), Llama 3.1 405B, Llama 3.1 70B, Llama 3.1 8B, MiniMax M2.7, RDU dataflow, SN40L RDU, gpt-oss-120b
source

Subscribe to SambaNova SN40L changes

SambaNova SN40L compared

Straight head-to-head pages against the busiest products in Chips & Compute.

SambaNova SN40L vs Google TPU Ironwood SambaNova SN40L vs Cerebras WSE-3 SambaNova SN40L vs Tenstorrent Blackhole SambaNova SN40L vs AWS Trainium2 SambaNova SN40L vs NVIDIA Blackwell SambaNova SN40L vs AMD Instinct MI355X

How to cite this page

Free to cite and reuse under CC BY 4.0. Permalink: https://tomorrow.aliensquad.ai/tools/sambanova

APA

Tomorrow. (2026). SambaNova SN40L — version, pricing and model stack [Data set entry]. AlienSquad. Retrieved 2026-11-08, from https://tomorrow.aliensquad.ai/tools/sambanova

BibTeX

@misc{tomorrow-tools-sambanova,
  author       = {{Tomorrow}},
  title        = {SambaNova SN40L — version, pricing and model stack},
  year         = {2026},
  publisher    = {AlienSquad},
  howpublished = {\url{https://tomorrow.aliensquad.ai/tools/sambanova}},
  note         = {Accessed: 2026-11-08}
}