vs
DeepInfra vs Together AI
Compare pricing across 47 shared models. DeepInfra offers 71 models, Together AI offers 175.
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.
47
Shared Models
23
DeepInfra Cheaper
22
Together AI Cheaper
2
Same Price
Price Comparison — Shared Models
| Model ↑ | DeepInfra Input | Together AI Input | DeepInfra Output | Together AI Output | Cheaper |
|---|---|---|---|---|---|
| DeepSeek V3 | $0.320 | $— | $0.890 | $— | Together AI |
| DeepSeek V3 0324 | $0.200 | $1.25 | $0.770 | $1.25 | DeepInfra |
| DeepSeek V3.1 | $0.210 | $0.600 | $0.790 | $1.70 | DeepInfra |
| DeepSeek V3.1 Terminus | $0.210 | $— | $0.790 | $— | Together AI |
| DeepSeek V3.2 | $0.260 | $— | $0.380 | $— | Together AI |
| Gemma 3 27B | $0.080 | $— | $0.160 | $— | Together AI |
| Gemma 3 4B | $0.040 | $— | $0.080 | $— | Together AI |
| Gemma 4 26B A4B Instruct | $0.070 | $— | $0.340 | $— | Together AI |
| Gemma 4 31B Instruct | $0.130 | $0.200 | $0.380 | $0.500 | DeepInfra |
| GLM 4.6 | $0.430 | $0.600 | $1.74 | $2.20 | DeepInfra |
| GLM 4.7 | $0.400 | $0.450 | $1.75 | $2.00 | DeepInfra |
| GLM 5 | $0.800 | $1.00 | $2.56 | $3.20 | DeepInfra |
| GLM 5.1 | $1.40 | $1.40 | $4.40 | $4.40 | Same |
| GPT-OSS-120b | $0.150 | $0.150 | $0.600 | $0.600 | Same |
| GPT-OSS-20b | $0.030 | $0.050 | $0.140 | $0.200 | DeepInfra |
| Kimi K2.5 | $0.450 | $0.500 | $2.25 | $2.80 | DeepInfra |
| Llama 3 8B Instruct | $0.030 | $0.100 | $0.040 | $0.100 | DeepInfra |
| Llama 3.1 70B Instruct | $0.400 | $— | $0.400 | $— | Together AI |
| Llama 3.1 8B Instruct | $0.020 | $0.180 | $0.050 | $0.180 | DeepInfra |
| Llama 3.1 Nemotron 70B Instruct | $1.20 | $— | $1.20 | $— | Together AI |
| Llama 3.2 11B Vision Instruct | $0.245 | $— | $0.245 | $— | Together AI |
| Llama 3.3 70B Instruct | $0.100 | $0.880 | $0.320 | $0.880 | DeepInfra |
| Llama 3.3 Nemotron Super 49B V1.5 | $0.100 | $— | $0.400 | $— | Together AI |
| Llama 4 Maverick | $0.150 | $— | $0.600 | $— | Together AI |
| Llama 4 Scout | $0.080 | $— | $0.300 | $— | Together AI |
| meta-llama-llama-guard-4-12b | $0.180 | $0.200 | $0.180 | $0.200 | DeepInfra |
| MiniMax M2.5 | $0.270 | $0.300 | $0.950 | $1.20 | DeepInfra |
| Mistral Nemo | $0.020 | $— | $0.040 | $— | Together AI |
| Mistral Small 3.2 24B | $0.075 | $— | $0.200 | $— | Together AI |
| Mixtral 8x7B Instruct | $0.540 | $0.900 | $0.540 | $0.900 | DeepInfra |
| MythoMax 13B | $0.400 | $0.300 | $0.400 | $0.300 | Together AI |
| Nemotron 3 Nano 30B A3B | $0.050 | $— | $0.200 | $— | Together AI |
| Nemotron 3 Super 120B A12B | $0.100 | $— | $0.500 | $— | Together AI |
| Nemotron Nano 9B V2 | $0.040 | $0.060 | $0.160 | $0.250 | DeepInfra |
| Nemotron-3 Super 120B A12B | $0.100 | $— | $0.500 | $— | Together AI |
| Qwen2.5 72B Instruct | $0.120 | $1.20 | $0.390 | $1.20 | DeepInfra |
| Qwen3 235B A22B Instruct 2507 | $0.071 | $0.200 | $0.100 | $0.600 | DeepInfra |
| Qwen3 235B A22B Thinking 2507 | $0.230 | $0.650 | $2.30 | $3.00 | DeepInfra |
| Qwen3 30B A3B | $0.080 | $— | $0.280 | $— | Together AI |
| Qwen3 Coder 480B A35B (exacto) | $0.220 | $2.00 | $1.00 | $2.00 | DeepInfra |
| Qwen3 Next 80B A3B Instruct | $0.090 | $— | $1.10 | $— | Together AI |
| Qwen3 VL 235B A22B Instruct | $0.200 | $— | $0.880 | $— | Together AI |
| Qwen3.5 397B A17B | $0.540 | $0.600 | $3.40 | $3.60 | DeepInfra |
| Qwen3.5 9B | $0.040 | $0.100 | $0.200 | $0.150 | DeepInfra |
| Qwen3.5-35B-A3B | $0.200 | $— | $0.950 | $— | Together AI |
| R1 0528 | $0.500 | $3.00 | $2.15 | $7.00 | DeepInfra |
| R1 Distill Llama 70B | $0.700 | $2.00 | $0.800 | $2.00 | DeepInfra |
Model Coverage
Only on DeepInfra(24)Gemma 3 12B$0.040/M
GLM 4.6V$0.300/M
GLM-4.7-Flash$0.060/M
Hermes 3 405B Instruct$1.00/M
Hermes 3 70B Instruct$0.300/M
Llama 3 8B Lunaris$0.040/M
Llama 3.1 Euryale 70B v2.2$0.850/M
Llama 3.3 Euryale 70B$0.850/M
Mistral Small 24B Instruct 2501$0.050/M
Nemotron Nano 12B 2 VL$0.200/M
Olmo 3.1 32B Instruct$0.200/M
Phi 4$0.070/M
Qwen3 14B$0.120/M
Qwen3 32B$0.080/M
Qwen3 Max$1.20/M
Qwen3 Max Thinking$1.20/M
Qwen3 VL 30B A3B Instruct$0.150/M
Qwen3.5 0.8B$0.010/M
Qwen3.5 2B (Non-reasoning)$0.020/M
Qwen3.5 4B (Non-reasoning)$0.030/M
Qwen3.5-122B-A10B$0.290/M
Qwen3.5-27B$0.260/M
Qwen3.6 35B A3B$0.200/M
Step 3.5 Flash$0.100/M
Shared(47)
47
models available on both
DeepInfraTogether AI
71 total172 total
Only on Together AI(125)Austism/chronos-hermes-13b$0.300/M
Code Llama 13B Instruct$0.225/M
Code Llama 34B Instruct$0.776/M
Coder Large$0.500/M
DeepSeek Coder 33B Instruct$0.800/M
Facebook CWM$—/M
Gemma 2 27B$0.800/M
Gemma 2 9B$—/M
Gemma 2B$0.100/M
Gemma 2B$0.100/M
Gemma 3 1B$—/M
Gemma 3n 4B$0.060/M
Gemma 4 E2B IT$—/M
Gemma 7B$0.200/M
Gemma 7B Instruct$0.200/M
GLM 4.5 Air$0.200/M
GLM 4.5V$—/M
GLM-5 FP4$—/M
Kimi K2 0711$1.20/M
Kimi K2 0905 (exacto)$0.500/M
LFM2-24B-A2B$0.030/M
LiquidAI/LFM2-24B-A2B$0.030/M
Llama 2 7B Chat$—/M
Llama 3 70B Instruct$0.880/M
Llama 3.1 405B Instruct$5.00/M
lmsys/vicuna-13b-v1.5$0.300/M
Maestro Reasoning$0.900/M
MiniMax M1$—/M
MiniMax M2$—/M
MiniMax M2.1$0.300/M
MiniMax M2.7$0.300/M
Ministral 3 14B 2512$0.200/M
Mistral 7B Instruct v0.1$0.200/M
Mistral 7B Instruct v0.2$0.200/M
Mistral 7B Instruct v0.3$0.200/M
Mistral Small 3.1 24B$0.100/M
Mixtral 8x7B$0.900/M
Nous Capybara 7B v1.9$0.200/M
Nous Hermes 2 Mixtral 8x7B DPO$0.900/M
Nous Hermes 2 Yi 34B$0.800/M
Nous Hermes Llama 2 13B$0.225/M
Nous Hermes Llama 2 7B$0.200/M
OLMo 7B Instruct$0.200/M
Open-Orca/Mistral-7B-OpenOrca$0.200/M
openai-whisper-large-v3$0.270/M
OpenChat 3.5 0106$0.200/M
OpenHermes 2 Mistral 7B$0.200/M
OpenHermes 2.5 Mistral 7B$0.200/M
Qwen1.5 0.5B$0.100/M
Qwen1.5 0.5B Chat$0.100/M
Qwen1.5 14B Chat$0.300/M
Qwen2 1.5B$—/M
Qwen2 1.5B Instruct$0.020/M
Qwen2 VL 72B Instruct$1.20/M
Qwen2.5 14B$—/M
Qwen2.5 14B Instruct$0.800/M
Qwen2.5 32B$—/M
Qwen2.5 72B$1.20/M
Qwen2.5 7B$0.300/M
Qwen2.5 7B Instruct$0.300/M
Qwen2.5 Coder 32B Instruct$0.800/M
Qwen2.5 VL 72B Instruct$1.20/M
Qwen3 0.6B$—/M
Qwen3 0.6B Base$—/M
Qwen3 1.7B$—/M
Qwen3 1.7B Base$—/M
Qwen3 14B Base$—/M
Qwen3 235B A22B$—/M
Qwen3 4B Base$—/M
Qwen3 8B$—/M
Qwen3 8B Base$—/M
Qwen3 Coder Next$0.500/M
Qwen3 Next 80B A3B Thinking$0.150/M
Qwen3 VL 32B Instruct$0.500/M
Qwen3 VL 8B Instruct$0.180/M
QwQ 32B$1.20/M
R1$3.00/M
R1 Distill Qwen 1.5B$0.180/M
R1 Distill Qwen 14B$1.60/M
ReMM SLERP 13B$0.300/M
Rnj 1 Instruct$0.150/M
Sarvam M$—/M
SOLAR 10.7B Instruct v1$0.300/M
Spotlight$0.180/M
together-kokoro-82m$4.00/M
together-llama-rank-v1$0.100/M
together-orpheus-3b-0.1-ft$15.00/M
together-rime-arcana-v2$0.270/M
together-sonic$65.00/M
together-sonic-2$65.00/M
together-sonic-3$65.00/M
Toppy M 7B$0.200/M
Virtuoso Large$0.750/M
WizardLM-2 8x22B$1.20/M
zero-one-ai/Yi-34B$0.800/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 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.