vs
DeepInfra vs SambaNova
Compare pricing across 12 shared models. DeepInfra offers 60 models, SambaNova offers 18.
8 Ways to Use Fewer Tokens
Get the free PDF guide — practical tips to cut your token usage and API costs. Subscribe to the Price Per Token newsletter and download instantly.
12
Shared Models
11
DeepInfra Cheaper
1
SambaNova Cheaper
0
Same Price
Price Comparison — Shared Models
| Model ↑ | DeepInfra Input | SambaNova Input | DeepInfra Output | SambaNova Output | Cheaper |
|---|---|---|---|---|---|
| DeepSeek V3 0324 | $0.200 | $3.00 | $0.770 | $4.50 | DeepInfra |
| DeepSeek V3.1 | $0.210 | $0.150 | $0.790 | $0.750 | SambaNova |
| DeepSeek V3.1 Terminus | $0.210 | $3.00 | $0.790 | $4.50 | DeepInfra |
| DeepSeek V3.2 | $0.260 | $3.00 | $0.380 | $4.50 | DeepInfra |
| GPT-OSS-120b | $0.150 | $0.140 | $0.600 | $0.950 | DeepInfra |
| Llama 3.1 8B Instruct | $0.020 | $0.100 | $0.050 | $0.200 | DeepInfra |
| Llama 3.3 70B Instruct | $0.100 | $0.600 | $0.320 | $1.20 | DeepInfra |
| Llama 4 Maverick | $0.150 | $0.630 | $0.600 | $1.80 | DeepInfra |
| MiniMax M2.5 | $0.270 | $0.300 | $0.950 | $1.20 | DeepInfra |
| Qwen3 32B | $0.080 | $0.400 | $0.280 | $0.800 | DeepInfra |
| R1 0528 | $0.500 | $5.00 | $2.15 | $7.00 | DeepInfra |
| R1 Distill Llama 70B | $0.700 | $0.700 | $0.800 | $1.40 | DeepInfra |
Model Coverage
Only on DeepInfra(48)DeepSeek V3$0.320/M
Gemma 3 12B$0.040/M
Gemma 3 27B$0.080/M
Gemma 3 4B$0.040/M
GLM 4.6$0.430/M
GLM 4.6V$0.300/M
GLM 4.7$0.400/M
GLM 5$0.800/M
GLM-4.7-Flash$0.060/M
GPT-OSS-20b$0.030/M
Hermes 3 405B Instruct$1.00/M
Hermes 3 70B Instruct$0.300/M
Kimi K2 0711$0.550/M
Kimi K2 0905 (exacto)$0.400/M
Kimi K2 Thinking$0.470/M
Kimi K2.5$0.450/M
Llama 3 8B Instruct$0.030/M
Llama 3 8B Lunaris$0.040/M
Llama 3.1 70B Instruct$0.400/M
Llama 3.1 Euryale 70B v2.2$0.850/M
Llama 3.2 11B Vision Instruct$0.049/M
Llama 3.3 Euryale 70B$0.850/M
Llama 4 Scout$0.080/M
meta-llama-llama-guard-4-12b$0.180/M
MiniMax M2$0.254/M
MiniMax M2.1$0.270/M
Mistral Nemo$0.020/M
Mistral Small 24B Instruct 2501$0.050/M
Mistral Small 3.2 24B$0.075/M
Mixtral 8x7B Instruct$0.540/M
MythoMax 13B$0.400/M
Nemotron 3 Nano 30B A3B$0.050/M
Nemotron Nano 12B 2 VL$0.200/M
Nemotron Nano 9B V2$0.040/M
Olmo 3.1 32B Instruct$0.200/M
Phi 4$0.070/M
Qwen2.5 72B Instruct$0.120/M
Qwen2.5 VL 32B Instruct$0.200/M
Qwen3 14B$0.120/M
Qwen3 235B A22B Instruct 2507$0.071/M
Qwen3 235B A22B Thinking 2507$0.230/M
Qwen3 30B A3B$0.080/M
Qwen3 Coder 480B A35B (exacto)$0.400/M
Qwen3 Next 80B A3B Instruct$0.090/M
Qwen3 VL 235B A22B Instruct$0.200/M
Qwen3 VL 30B A3B Instruct$0.150/M
Shared(12)
12
models available on both
DeepInfraSambaNova
60 total17 total
Only on SambaNova(5)ALLaM 7B Instruct Preview$0.220/M
microsoft-e5-mistral-7b$0.130/M
Qwen3 235B A22B$0.400/M
whisper-large-v3$—/M
Full Provider Pricing
Frequently Asked Questions
Built by @aellman
Tools
Directories
Models & Pricing
Endpoints
Rankings
- All Rankings
- All Benchmarks
- Best LLM for Coding
- Best LLM for Math
- Best LLM for Writing
- Best LLM for RAG
- Best LLM for OpenClaw
- Best LLM for Cursor
- Best LLM for Windsurf
- Best LLM for Cline
- Best LLM for Aider
- Best LLM for GitHub Copilot
- Best LLM for Bolt
- Best LLM for Continue.dev
- MMLU-Pro
- GPQA
- LiveCodeBench
- Aider
- AIME
- MATH (Hard)
- Big-Bench Hard
2026 68 Ventures, LLC. All rights reserved.