DeepInfra vs Together AI.
Prices checked
DeepInfra is cheaper on 40 of the 43 models both sell, the widest gap Llama 3.1 8B Instruct at 2.5¢ against $0.18 per M tokens, checked .
Where to start
DeepInfraall 126 models Serves open-weight models on its own GPUs, often at fp8 or fp4, and publishes the precision per model.
Cheapest of the shared models
2¢/M tokens
Llama 3.2 3B Instruct
Together AIall 61 models Serves open-weight models on its own GPUs; also sells dedicated endpoints by the GPU-hour.
Cheapest of the shared models
6¢/M tokens
Llama 3.2 3B Instruct
Side by side
| Fact | DeepInfra | Together AI |
|---|---|---|
| Kind of provider | Host | Host |
| Models we track | 126 | 61 |
| Cheaper of the two | 40 of 43 | 0 of 43 |
| Trains on your prompts | does not say | does not say |
| Keeps your requests | does not say | does not say |
| How you pay | does not say | does not say |
| Smallest top-up | does not say | does not say |
| Free tier | none listed | none listed |
| Where it runs | does not say | does not say |
Every model both sell
43 models, most widely sold first. Per M tokens, blended 3 in : 1 out.
| Model | DeepInfra | Together AI |
|---|---|---|
| GLM-5.3Z.ai · 1M context | $1.68 $0.90 in · $4 out | $2.15 $1.40 in · $4.40 out |
| GLM-5.3-FlashZ.ai · 1M context | $0.24 $0.15 in · $0.50 out | $0.24 $0.15 in · $0.50 out |
| DeepSeek V4.1 Flash 1017DeepSeek · 1M context | $0.30 $0.20 in · $0.60 out | $0.52 $0.30 in · $1.20 out |
| DeepSeek V4 Flash 0731DeepSeek · 1M context | 9¢ 6¢ in · $0.18 out | $0.18 $0.14 in · $0.28 out |
| GLM-5.2Z.ai · 1M context | $1.16 $0.75 in · $2.40 out | $2.15 $1.40 in · $4.40 out |
| Kimi K3Moonshot AI · 1M context | $5.70 $2.85 in · $14.25 out | $6 $3 in · $15 out |
| DeepSeek V4 ProDeepSeek · 1M context | $1.63 $1.30 in · $2.60 out | $1.98 $1.32 in · $3.96 out |
| Kimi K2.6Moonshot AI · 262k context | $1.44 $0.75 in · $3.50 out | $2.03 $1.20 in · $4.50 out |
| gpt-oss-120bOpenAI · 131k context | 7¢ 3.7¢ in · $0.17 out | $0.26 $0.15 in · $0.60 out |
| MiniMax-M3MiniMax · 1M context | $0.49 $0.28 in · $1.10 out | $0.52 $0.30 in · $1.20 out |
| Kimi K2.7 CodeMoonshot AI · 262k context | $1.36 $0.68 in · $3.40 out | $1.71 $0.95 in · $4 out |
| GLM-5.1Z.ai · 200k context | $1.66 $1.05 in · $3.50 out | $2.15 $1.40 in · $4.40 out |
| Llama 3.3 70B InstructMeta · 131k context | $0.16 $0.10 in · $0.32 out | $1.04 $1.04 in · $1.04 out |
| MiniMax-M2.5MiniMax · 205k context | $0.40 $0.15 in · $1.15 out | $0.52 $0.30 in · $1.20 out |
| MiniMax-M2.7MiniMax · 205k context | $0.44 $0.25 in · $1 out | $0.52 $0.30 in · $1.20 out |
| gpt-oss-20bOpenAI · 131k context | 5.8¢ 3¢ in · $0.14 out | 8.8¢ 5¢ in · $0.20 out |
| Kimi K2.5Moonshot AI · 262k context | $0.90 $0.45 in · $2.25 out | $1.08 $0.50 in · $2.80 out |
| Gemma 4 31B ITGoogle · 262k context | $0.15 9¢ in · $0.34 out | $0.53 $0.39 in · $0.97 out |
| Qwen3.5 397B-A17BAlibaba Cloud · 262k context | $1.09 $0.45 in · $3 out | $1.35 $0.60 in · $3.60 out |
| GLM-4.7Z.ai · 205k context | $0.74 $0.40 in · $1.75 out | $0.84 $0.45 in · $2 out |
| GLM-4.6Z.ai · 205k context | $0.88 $0.50 in · $2 out | $1 $0.60 in · $2.20 out |
| R1 0528DeepSeek · 164k context | $0.91 $0.50 in · $2.15 out | $4 $3 in · $7 out |
| DeepSeek V3 0324DeepSeek · 164k context | $0.41 $0.24 in · $0.90 out | $1.25 $1.25 in · $1.25 out |
| Qwen3.8 2.4T A95BAlibaba Cloud · 1M context | $3 $2 in · $6 out | $3 $2 in · $6 out |
| DeepSeek V3.1DeepSeek · 164k context | $0.42 $0.25 in · $0.95 out | $0.88 $0.60 in · $1.70 out |
| Llama 3.1 8B InstructMeta · 131k context | 2.5¢ 2¢ in · 4¢ out | $0.18 $0.18 in · $0.18 out |
| Qwen3 Coder 480B A35BAlibaba Cloud · 262k context | $0.47 $0.30 in · $1 out | $2 $2 in · $2 out |
| Kimi K2 0905Moonshot AI · 262k context | $0.88 $0.50 in · $2 out | $1.50 $1 in · $3 out |
| Qwen3.5-9BAlibaba Cloud · 262k context | $0.11 $0.10 in · $0.15 out | $0.19 $0.17 in · $0.25 out |
| InklingThinking Machines · 524k context | $1.73 $0.95 in · $4.05 out | $1.76 $1 in · $4.05 out |
| Qwen3 Next 80B A3B InstructAlibaba Cloud · 131k context | $0.34 9¢ in · $1.10 out | $0.49 $0.15 in · $1.50 out |
| Llama 4 ScoutMeta · 1.3M context | $0.15 $0.10 in · $0.30 out | $0.28 $0.18 in · $0.59 out |
| Nemotron 3.5 Super VLNVIDIA · 1M context | $0.24 $0.15 in · $0.50 out | $0.24 $0.15 in · $0.50 out |
| Llama 3.1 70B InstructMeta · 131k context | $0.40 $0.40 in · $0.40 out | $0.88 $0.88 in · $0.88 out |
| Muse Glimmer 30BMeta · 131k context | $0.52 $0.30 in · $1.20 out | $0.64 $0.35 in · $1.50 out |
| Nemotron 3 UltraNVIDIA · 262k context | $0.93 $0.50 in · $2.20 out | $1.35 $0.60 in · $3.60 out |
| Qwen2.5 72B InstructAlibaba Cloud · 33k context | $0.37 $0.36 in · $0.40 out | $1.20 $1.20 in · $1.20 out |
| Llama 3.2 3B InstructMeta · 131k context | 2¢ 2¢ in · 2¢ out | 6¢ 6¢ in · 6¢ out |
| Qwen3-Next 80B-A3B (Thinking)Alibaba Cloud · 131k context | $0.45 $0.14 in · $1.40 out | $0.49 $0.15 in · $1.50 out |
| Mistral Small 3Mistral AI · 33k context | 5.8¢ 5¢ in · 8¢ out | $0.15 $0.10 in · $0.30 out |
The 40 most widely sold of 43 · every row in the open dataset
How we count
DeepInfra is cheaper on 40 of the 43 models both sell, Together AI on 0, and 3 cost the same at both. Both are the same kind of provider, hosts running the same models, so the price is most of what separates them.
Each price is the cheapest that provider charges for the model, per M tokens, blended 3 in : 1 out. The smaller line under it is the price in and the price out.
A free tier is a limit rather than a price, and a price below the maker's own with nothing published to account for it is left out, so neither can be marked as the cheaper of the two.
Frequently asked
- Is DeepInfra cheaper than Together AI?
- On the 43 models both sell, DeepInfra is cheaper on 40, Together AI on 0, and 3 cost the same at both. The widest gap is Llama 3.1 8B Instruct: 2.5¢ per million tokens against $0.18. Prices are per M tokens, blended 3 in : 1 out, and read on 31 Oct 2026.
- Which models do DeepInfra and Together AI both sell?
- 43 of the models we track, led by GLM-5.3, GLM-5.3-Flash, DeepSeek V4.1 Flash 1017. DeepInfra sells 126 in all and Together AI 61, so most of each catalog has no counterpart at the other.
- Does DeepInfra or Together AI train on what you send it?
- DeepInfra does not say whether it trains on what you send it, and does not say how long it keeps requests. Together AI does not say whether it trains on what you send it, and does not say how long it keeps requests. A provider that may train on prompts is often how a price below the maker's own is paid for.
- How current are these prices?
- Both catalogs are read every 3 days. DeepInfra was last read 31 Oct 2026 and Together AI 31 Oct 2026; the whole index was refreshed 31 Oct 2026. Prices exclude tax, and a price below the maker's own with nothing published to account for it is left out of this table entirely.
Provider pages