SambaNova Cloud - Free API Access
Source: https://cloud.sambanova.ai/
Description
Create account to comment on specific lines or Sign in
+ 1 SambaNova Cloud offers free API access to top open-source models including DeepSeek R1, DeepSeek V3, Llama 4 Maverick, Qwen 3, and more — powered by SambaNova's custom RDU chips that deliver inference speeds up to 10x faster than GPUs. No credit card is required to start. New accounts receive $5 in free credits (valid for 3 months), which translates to over 30 million tokens on Llama 8B. After credits are exhausted, a rate-limited Free Tier remains available (10-40 RPM depending on model, 40 RPD). The API is OpenAI-compatible, so you can swap in SambaNova as a drop-in replacement in most codebases.
No comments on this line yet.
+ 2
No comments on this line yet.
+
3
No comments on this line yet.
+ 4
No comments on this line yet.
+ 6
No comments on this line yet.
+ 7 1. Go to cloud.sambanova.ai
No comments on this line yet.
+ 8 2. Click "Get Started" or "Sign Up"
No comments on this line yet.
+ 9 3. Create an account (email signup or SSO)
No comments on this line yet.
+ 10 4. Once logged in, navigate to the API Keys page at cloud.sambanova.ai/apis
No comments on this line yet.
+ 11 5. Click "Create New Key" — save it immediately, as keys cannot be viewed again after creation
No comments on this line yet.
+
12
6. Set the environment variable SAMBANOVA_API_KEY or pass it directly in your API calls
No comments on this line yet.
+
13
7. Use the base URL https://api.sambanova.ai/v1 — compatible with OpenAI client libraries
No comments on this line yet.
+ 14
No comments on this line yet.
+ 15 Important:
No comments on this line yet.
+ 16 • No credit card or payment method required for the Free Tier
No comments on this line yet.
+ 17 • You can create up to 25 API keys per account
No comments on this line yet.
+ 18 • The $5 free credit is automatically applied to your account and expires after 3 months
No comments on this line yet.
+ 19 • After credits expire, you remain on the Free Tier with rate-limited access (no payment needed)
No comments on this line yet.
+ 20 • Linking a payment method upgrades you to the Developer Tier with higher rate limits
No comments on this line yet.
+ 21
No comments on this line yet.
+
22
No comments on this line yet.
+ 23
No comments on this line yet.
+ 25
No comments on this line yet.
+ 27
No comments on this line yet.
+ 28 ModelTypeNotes
No comments on this line yet.
+ 29 DeepSeek-R1-0528Reasoning671B MoE, advanced reasoning/math/code
No comments on this line yet.
+ 30 DeepSeek-R1-Distill-Llama-70BReasoningDistilled reasoning model
No comments on this line yet.
+ 31 DeepSeek-V3-0324Chat671B MoE, general-purpose
No comments on this line yet.
+ 32 DeepSeek-V3.1ChatLatest DeepSeek generation
No comments on this line yet.
+ 33 DeepSeek-V3.1-TerminusChatEnhanced V3.1 variant
No comments on this line yet.
+ 34 DeepSeek-V3.2ChatNewest DeepSeek model
No comments on this line yet.
+ 35 Meta-Llama-3.1-8B-InstructChatFast, lightweight
No comments on this line yet.
+ 36 Meta-Llama-3.3-70B-InstructChatStrong general-purpose
No comments on this line yet.
+ 37
No comments on this line yet.
+ 39
No comments on this line yet.
+ 40 ModelTypeNotes
No comments on this line yet.
+ 41 Llama-4-Maverick-17B-128E-InstructChat/Vision17B active params, 128 experts MoE
No comments on this line yet.
+ 42 openai/gpt-oss-120bChatOpen-source 120B MoE from OpenAI
No comments on this line yet.
+ 43 Qwen3-32BChatAlibaba's Qwen 3 series
No comments on this line yet.
+ 44 Qwen3-235BChatLarge Qwen 3 model
No comments on this line yet.
+ 45 E5-Mistral-7B-InstructEmbeddingsText embeddings model
No comments on this line yet.
+ 46 Whisper-Large-v3AudioSpeech-to-text transcription
No comments on this line yet.
+ 47 Llama-3.3-Swallow-70B-InstructChatJapanese-focused Llama variant
No comments on this line yet.
+ 48 ALLaM-7B-InstructChatArabic language model
No comments on this line yet.
+ 49
No comments on this line yet.
+ 50 Note: Preview models have limited capacity and may be removed at short notice. Do not rely on them for production workloads.
No comments on this line yet.
+ 51
No comments on this line yet.
+
52
No comments on this line yet.
+ 53
No comments on this line yet.
+ 55
No comments on this line yet.
+ 57
No comments on this line yet.
+ 58 ModelRPMRPDTPD
No comments on this line yet.
+ 59 Meta-Llama-3.1-8B-Instruct4040200,000
No comments on this line yet.
+ 60 Meta-Llama-3.3-70B-Instruct4040200,000
No comments on this line yet.
+ 61 DeepSeek-R12040200,000
No comments on this line yet.
+ 62 DeepSeek-R1-Distill-Llama-70B4040200,000
No comments on this line yet.
+ 63 DeepSeek-V3-03242040200,000
No comments on this line yet.
+ 64 DeepSeek-V3.12040200,000
No comments on this line yet.
+ 65 Llama-4-Maverick-17B-128E2040200,000
No comments on this line yet.
+ 66 gpt-oss-120b2040200,000
No comments on this line yet.
+ 67 Qwen3-32B1040200,000
No comments on this line yet.
+ 68 Whisper-Large-v34040200,000
No comments on this line yet.
+ 69 E5-Mistral-7B-Instruct2040200,000
No comments on this line yet.
+ 70
No comments on this line yet.
+ 71 RPM = Requests per Minute, RPD = Requests per Day, TPD = Tokens per Day
No comments on this line yet.
+ 72
No comments on this line yet.
+ 74
No comments on this line yet.
+ 75 ModelRPMRPD
No comments on this line yet.
+ 76 Meta-Llama-3.1-8B-Instruct1,440288,000
No comments on this line yet.
+ 77 Meta-Llama-3.3-70B-Instruct24048,000
No comments on this line yet.
+ 78 DeepSeek-R16012,000
No comments on this line yet.
+ 79 DeepSeek-R1-Distill-Llama-70B24048,000
No comments on this line yet.
+ 80 DeepSeek-V3-03246012,000
No comments on this line yet.
+ 81 DeepSeek-V3.16012,000
No comments on this line yet.
+ 82 Llama-4-Maverick-17B-128E6012,000
No comments on this line yet.
+ 83 gpt-oss-120b6012,000
No comments on this line yet.
+ 84 Qwen3-32B306,000
No comments on this line yet.
+ 85 Whisper-Large-v345090,000
No comments on this line yet.
+ 86 E5-Mistral-7B-Instruct6012,000
No comments on this line yet.
+ 87
No comments on this line yet.
+ 88 The Developer Tier provides dramatically higher limits — for example, Llama 8B goes from 40 to 1,440 RPM (36x increase). The key difference: the Free Tier caps you at 40 requests per day and 200,000 tokens per day across all models.
No comments on this line yet.
+ 89
No comments on this line yet.
+
90
No comments on this line yet.
+ 91
No comments on this line yet.
+ 93
No comments on this line yet.
+ 94 ModelInputOutput
No comments on this line yet.
+ 95 Meta-Llama-3.1-8B-Instruct$0.01$0.02
No comments on this line yet.
+ 96 Meta-Llama-3.3-70B-Instruct$0.06$0.12
No comments on this line yet.
+ 97 DeepSeek-V3.1 (cb)$0.015$0.075
No comments on this line yet.
+ 98 DeepSeek-V3.1-Terminus$0.30$0.45
No comments on this line yet.
+ 99 DeepSeek-V3.2$0.30$0.45
No comments on this line yet.
+ 100 DeepSeek-R1-0528$0.50$0.70
No comments on this line yet.
+ 101 DeepSeek-R1-Distill-Llama-70B$0.07$0.14
No comments on this line yet.
+ 102 Llama-4-Maverick-17B-128E$0.063$0.18
No comments on this line yet.
+ 103 openai/gpt-oss-120b$0.022$0.059
No comments on this line yet.
+ 104 Qwen3-32B$0.04$0.08
No comments on this line yet.
+ 105 Qwen3-235B$0.04$0.08
No comments on this line yet.
+ 106 E5-Mistral-7B-Instruct$0.013Free
No comments on this line yet.
+ 107 Whisper-Large-v3$10/hourN/A
No comments on this line yet.
+ 108
No comments on this line yet.
+ 109 With the $5 free credit, you can run roughly 30 million tokens on Llama 8B, or about 70,000 tokens on DeepSeek-R1-0528.
No comments on this line yet.
+ 110
No comments on this line yet.
+
111
No comments on this line yet.
+ 112
No comments on this line yet.
+ 114
No comments on this line yet.
+ 115 FeatureFree TierDeveloper Tier
No comments on this line yet.
+ 116 Payment methodNot requiredRequired (credit card)
No comments on this line yet.
+ 117 Free credit$5 (expires in 3 months)$5 (expires in 3 months)
No comments on this line yet.
+ 118 RPM10-40 depending on model30-1,440 depending on model
No comments on this line yet.
+ 119 RPD40 across all models6,000-288,000 depending on model
No comments on this line yet.
+ 120 TPD200,000 across all modelsNo stated cap
No comments on this line yet.
+ 121 After credits expireRate-limited access continuesPay-as-you-go
No comments on this line yet.
+ 122 Production useNot practical (40 RPD cap)Yes
No comments on this line yet.
+ 123
No comments on this line yet.
+
124
No comments on this line yet.
+ 125
No comments on this line yet.
+ 127
No comments on this line yet.
+ 128 The Free Tier's biggest constraint is the 40 requests per day limit across all models, combined with a 200,000 tokens per day cap. This means:
No comments on this line yet.
+ 129
No comments on this line yet.
+ 130 • You can do about 40 short conversations per day for testing and prototyping
No comments on this line yet.
+ 131 • The RPM limits (10-40) are less of an issue than the daily caps
No comments on this line yet.
+ 132 • This is enough for experimentation and evaluation, but not for building anything real
No comments on this line yet.
+ 133 • SambaNova has stated they have no plans to maintain the free tier long-term — it may be fully replaced by the credit-based Developer Tier
No comments on this line yet.
+ 134
No comments on this line yet.
+ 135 If you want meaningful free usage, the $5 credit on the Developer Tier (no charge until credits run out) is the better path. Just be aware that linking a payment method means you can be billed once credits are exhausted.
No comments on this line yet.
+ 136
No comments on this line yet.
+
137
No comments on this line yet.
+ 138
No comments on this line yet.
+ 140
No comments on this line yet.
+ 141 SambaNova's API is fully OpenAI-compatible, which means you can use standard OpenAI client libraries:
No comments on this line yet.
+ 142
No comments on this line yet.
+
143
No comments on this line yet.
+ 144 from openai import OpenAI
No comments on this line yet.
+ 145
No comments on this line yet.
+ 146 client = OpenAI(
No comments on this line yet.
+
147
api_key="YOUR_SAMBANOVA_API_KEY",
api_key="YOUR_SAMBANOVA_API_KEY", No comments on this line yet.
+
148
base_url="https://api.sambanova.ai/v1"
base_url="https://api.sambanova.ai/v1" No comments on this line yet.
+ 149 )
No comments on this line yet.
+ 150
No comments on this line yet.
+ 151 response = client.chat.completions.create(
No comments on this line yet.
+
152
model="DeepSeek-R1",
model="DeepSeek-R1", No comments on this line yet.
+
153
messages=[{"role": "user", "content": "Hello!"}]
messages=[{"role": "user", "content": "Hello!"}] No comments on this line yet.
+ 154 )
No comments on this line yet.
+
155
No comments on this line yet.
+ 156
No comments on this line yet.
+ 157 This makes it trivial to switch between SambaNova, OpenAI, Together AI, and other compatible providers.
No comments on this line yet.
+ 158
No comments on this line yet.
+
159
No comments on this line yet.
+ 160
No comments on this line yet.
+ 162
No comments on this line yet.
+ 163 • Community participation — the top 10 most engaged members on the SambaNova Developer Community each month receive $10 in additional credits
No comments on this line yet.
+ 164 • Community membership bonus — existing community members received an extra $5 credit when the Developer Tier launched
No comments on this line yet.
+ 165 • Engagement is tracked via a community leaderboard (answering questions, sharing projects, providing feedback)
No comments on this line yet.
+ 166
No comments on this line yet.
+
167
No comments on this line yet.
+ 168
No comments on this line yet.
+ 170
No comments on this line yet.
+ 171 • Speed advantage — SambaNova's RDU hardware delivers extremely fast inference. DeepSeek-R1 671B runs at ~200 tokens/sec vs. ~19 tokens/sec average on GPU providers. If speed matters to you, this is a strong differentiator
No comments on this line yet.
+ 172 • No auto-billing on Free Tier — without a payment method linked, you will never be charged. The Free Tier simply rate-limits you after credits expire
No comments on this line yet.
+ 173 • Developer Tier auto-billing — once you link a payment method, you will be billed for usage beyond the $5 free credit. Set spending alerts if available
No comments on this line yet.
+ 174 • Preview models are unstable — models marked "Preview" (including Llama 4 Maverick, gpt-oss-120b, Qwen3) may be removed without notice. Don't build production features on them
No comments on this line yet.
+ 175 • AWS Marketplace — SambaCloud is also available through AWS Marketplace if you prefer consolidated billing
No comments on this line yet.
+
176
• Rate limit headers — every API response includes X-RateLimit-Remaining and related headers so you can programmatically track your usage
No comments on this line yet.
+ 177 • Free tier future uncertain — SambaNova has indicated they may fully deprecate the Free Tier in favor of the credit-based Developer Tier. Sign up while it is still available
No comments on this line yet.
+ 178
No comments on this line yet.
+
179
No comments on this line yet.
+ 180
No comments on this line yet.
+ 181 Sources:
No comments on this line yet.
+ 182 • SambaNova Cloud Plans
No comments on this line yet.
+ 183 • SambaNova Cloud Pricing
No comments on this line yet.
+ 184 • SambaNova Rate Limits Documentation
No comments on this line yet.
+ 185 • SambaNova Developer Tier Blog Post
No comments on this line yet.
+ 186 • SambaNova API Keys & URLs
No comments on this line yet.
+ 187 • SambaNova Developer Community - Free Tier Discussion
No comments on this line yet.
+ 188 • SambaNova Supported Models
No comments on this line yet.
+ 189 • Free LLM API Resources (GitHub)
No comments on this line yet.