vs
DeepInfra vs Together AI
Compare pricing across 29 shared models. DeepInfra offers 68 models, Together AI offers 120.
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.
29
Shared Models
26
DeepInfra Cheaper
1
Together AI Cheaper
2
Same Price
Price Comparison — Shared Models
| Model ↑ | DeepInfra Input | Together AI Input | DeepInfra Output | Together AI Output | Cheaper |
|---|---|---|---|---|---|
| DeepSeek V3.1 | $0.250 | $0.600 | $0.950 | $1.70 | DeepInfra |
| DeepSeek V4 Pro | $1.30 | $1.32 | $2.60 | $3.96 | DeepInfra |
| DeepSeek V4.1 Flash | $0.200 | $0.300 | $0.600 | $1.20 | DeepInfra |
| deepseek-deepseek-v4-pro-0813 | $1.30 | $1.32 | $2.60 | $3.96 | DeepInfra |
| deepseek-deepseek-v4.1-flash-1017 | $0.098 | $0.300 | $0.294 | $1.20 | DeepInfra |
| Gemma 4 31B Instruct | $0.300 | $0.390 | $0.600 | $0.970 | DeepInfra |
| GLM 4.6 | $0.500 | $0.600 | $2.00 | $2.20 | DeepInfra |
| GLM 4.7 | $0.320 | $0.450 | $1.40 | $2.00 | DeepInfra |
| GLM-5.2 | $0.750 | $1.40 | $2.40 | $4.40 | DeepInfra |
| GLM-5.3 | $0.563 | $1.40 | $2.50 | $4.40 | DeepInfra |
| GLM-5.3 Flash | $0.101 | $0.150 | $0.335 | $0.500 | DeepInfra |
| GPT-OSS-120b | $0.037 | $0.150 | $0.170 | $0.600 | DeepInfra |
| GPT-OSS-20b | $0.030 | $0.050 | $0.140 | $0.200 | DeepInfra |
| Inkling 2 Small | $0.285 | $0.300 | $0.950 | $1.00 | DeepInfra |
| Kimi K2.6 | $0.750 | $1.20 | $3.50 | $4.50 | DeepInfra |
| Kimi K3 | $2.85 | $3.00 | $14.25 | $15.00 | DeepInfra |
| Kimi K3.1 Pro | $2.00 | $2.00 | $10.00 | $10.00 | Same |
| Llama 3.1 8B Instruct | $0.020 | $0.180 | $0.040 | $0.180 | DeepInfra |
| Llama 3.3 70B Instruct | $0.100 | $1.04 | $0.320 | $1.04 | DeepInfra |
| Llama 4 Scout | $0.150 | $0.180 | $0.450 | $0.590 | DeepInfra |
| Muse Glimmer 30B | $0.300 | $0.350 | $1.20 | $1.50 | DeepInfra |
| Nemotron 3 Ultra 550B A55B | $0.400 | $0.600 | $1.76 | $3.60 | DeepInfra |
| Nemotron 3.5 Super VL | $0.150 | $0.150 | $0.500 | $0.500 | Same |
| Qwen2.5 72B Instruct | $0.288 | $1.20 | $0.320 | $1.20 | DeepInfra |
| Qwen3 Coder 480B A35B (exacto) | $0.300 | $2.00 | $1.00 | $2.00 | DeepInfra |
| Qwen3 Next 80B A3B Instruct | $0.090 | $0.150 | $1.10 | $1.50 | DeepInfra |
| Qwen3.5 397B A17B | $0.675 | $0.600 | $4.50 | $3.60 | Together AI |
| Qwen3.5 9B | $0.080 | $0.170 | $0.120 | $0.250 | DeepInfra |
| R1 0528 | $0.500 | $3.00 | $2.15 | $7.00 | DeepInfra |
Model Coverage
Only on DeepInfra(39)DeepSeek V3$0.320/M
DeepSeek V3.2$0.260/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
Granite 4.2 8B$0.060/M
HY4 Preview$0.834/M
Inkling Small$0.450/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
meta-llama-llama-guard-4-12b$0.270/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
Nemotron 3 Super 120B A12B$0.075/M
Nemotron 3.5 Lightning$0.060/M
Nemotron-3 Super 120B A12B$0.075/M
Phi 4$0.070/M
Qwen3 14B$0.180/M
Qwen3 235B A22B Instruct 2507$0.135/M
Qwen3 30B A3B$0.180/M
Qwen3 32B$0.064/M
Qwen3 VL 235B A22B Instruct$0.200/M
Qwen3 VL 30B A3B Instruct$0.150/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
Shared(29)
29
models available on both
DeepInfraTogether AI
68 total117 total
Only on Together AI(88)Austism/chronos-hermes-13b$0.300/M
Code Llama 13B Instruct$0.225/M
Code Llama 34B Instruct$0.776/M
DeepSeek Coder 33B Instruct$0.800/M
elorian-labs/glimpse-1.0$0.600/M
elorian/glimpse$0.600/M
Gemma 2 27B$0.800/M
Gemma 2B$0.100/M
Gemma 2B$0.100/M
Gemma 7B$0.200/M
Gemma 7B Instruct$0.200/M
GLM 4.5 Air$0.200/M
GLM 5.1$1.40/M
Kimi K2.5$0.500/M
Kimi K2.7 Code$0.950/M
Llama 3 70B Instruct$0.880/M
Llama 3 8B Instruct$0.200/M
Llama 3.1 405B Instruct$3.50/M
Llama 3.1 70B Instruct$0.880/M
Llama 3.1 Nemotron 70B Instruct$0.880/M
Llama 3.2 1B Instruct$0.060/M
Llama 3.2 3B Instruct$0.060/M
lmsys/vicuna-13b-v1.5$0.300/M
MiniMax M2.7$0.300/M
MiniMax-M3.1 Flash$0.150/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
Mixtral 8x7B Instruct$0.900/M
Muse Spark Open$1.25/M
MythoMax 13B$0.300/M
Nemotron Nano 9B V2$0.060/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 Instruct$0.020/M
Qwen2 72B Instruct$0.900/M
Qwen2 VL 72B Instruct$1.20/M
Qwen2.5 1.5B Instruct$0.100/M
Qwen2.5 14B Instruct$0.800/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 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
Qwen3.7 Max$2.50/M
Qwen3.7 Plus$0.320/M
Qwen3.8 Flash$0.150/M
QwQ 32B$1.20/M
R1$3.00/M
R1 Distill Llama 70B$2.00/M
R1 Distill Qwen 1.5B$0.180/M
R1 Distill Qwen 14B$1.60/M
ReMM SLERP 13B$0.300/M
ricursiveai/ripple-65b-preview$0.200/M
SOLAR 10.7B Instruct v1$0.300/M
thinkingmachines/Inkling$1.00/M
together-bge-base-en-v1.5$0.0080/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
Trinity Mini$0.045/M
WizardLM-2 8x22B$1.20/M
zero-one-ai/Yi-34B$0.800/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.