vs
DeepInfra vs Groq
Compare pricing across 6 shared models. DeepInfra offers 68 models, Groq offers 14.
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.
6
Shared Models
5
DeepInfra Cheaper
1
Groq Cheaper
0
Same Price
Price Comparison — Shared Models
| Model ↑ | DeepInfra Input | Groq Input | DeepInfra Output | Groq Output | Cheaper |
|---|---|---|---|---|---|
| GPT-OSS-120b | $0.037 | $0.150 | $0.170 | $0.600 | DeepInfra |
| GPT-OSS-20b | $0.030 | $0.075 | $0.140 | $0.300 | DeepInfra |
| Llama 3.1 8B Instruct | $0.020 | $0.050 | $0.040 | $0.080 | DeepInfra |
| Llama 3.3 70B Instruct | $0.100 | $0.590 | $0.320 | $0.790 | DeepInfra |
| meta-llama-llama-guard-4-12b | $0.270 | $0.200 | $0.270 | $0.200 | Groq |
| Qwen3 32B | $0.064 | $0.290 | $0.224 | $0.590 | DeepInfra |
Model Coverage
Only on DeepInfra(62)DeepSeek V3$0.320/M
DeepSeek V3.1$0.250/M
DeepSeek V3.2$0.260/M
DeepSeek V4 Pro$1.30/M
DeepSeek V4.1 Flash$0.200/M
deepseek-deepseek-v4-flash-0731$0.060/M
Gemma 3 12B$0.075/M
Gemma 3 27B$0.080/M
Gemma 3 4B$0.050/M
Gemma 4 26B A4B Instruct$0.070/M
Gemma 4 31B Instruct$0.300/M
GLM 4.6$0.500/M
GLM 4.7$0.320/M
GLM-5.2$0.750/M
GLM-5.3$0.563/M
GLM-5.3 Flash$0.101/M
Granite 4.2 8B$0.060/M
HY4 Preview$0.834/M
Inkling 2 Small$0.285/M
Inkling Small$0.450/M
Kimi K2.6$0.750/M
Kimi K3$2.85/M
Kimi K3.1 Pro$2.00/M
Ling 3.0 Flash$0.060/M
Ling 3.0 Flash VL$0.060/M
Llama 3 8B Lunaris$0.040/M
Llama 3.1 Euryale 70B v2.2$0.850/M
Llama 4 Scout$0.150/M
MiMo v2.6 Flash$0.140/M
MiMo v2.6 Pro$0.430/M
MiniMax M3$0.280/M
Mistral Nemo$0.029/M
Mistral Small 24B Instruct 2501$0.040/M
Mistral Small 3.2 24B$0.075/M
Muse Glimmer 30B$0.300/M
Nemotron 3 Super 120B A12B$0.075/M
Nemotron 3 Ultra 550B A55B$0.400/M
Nemotron 3.5 Lightning$0.060/M
Nemotron 3.5 Super VL$0.150/M
Nemotron-3 Super 120B A12B$0.075/M
Phi 4$0.070/M
Qwen2.5 72B Instruct$0.288/M
Qwen3 14B$0.180/M
Qwen3 235B A22B Instruct 2507$0.135/M
Qwen3 30B A3B$0.180/M
Qwen3 Coder 480B A35B (exacto)$0.300/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
Qwen3.5 397B A17B$0.675/M
Qwen3.5 9B$0.080/M
Qwen3.5-27B$0.260/M
Qwen3.5-35B-A3B$0.112/M
Qwen3.6 27B$0.480/M
Qwen3.6 35B A3B$0.100/M
Qwen3.8 27B$0.150/M
R1 0528$0.500/M
Shared(6)
6
models available on both
DeepInfraGroq
68 total14 total
Only on Groq(8)Gemma 7B Instruct$0.070/M
Kimi K2 0711$1.00/M
Llama 3 8B Instruct$0.050/M
meta-llama-llama-guard-3-8b$0.200/M
MiniMax M2.7$0.600/M
Mixtral 8x7B$0.240/M
openai-gpt-oss-safeguard-20b$0.075/M
R1 Distill Llama 70B$0.750/M
Full Provider Pricing
Frequently Asked Questions
Built by @aellman
Also from the founder: BlobCap, a price index for AI training data deals, showing what AI labs actually pay for data.
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 Local LLM
- 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.