Together AI models & pricing
Together AI hosts 104 models (100 with public pricing) covering 4 modalities. Open-model inference cloud — Llama, DeepSeek, Qwen, Mixtral, FLUX with serverless and dedicated endpoints. Cheapest input starts at $0.008000/M tokens; the most premium goes up to $3.50/M. Use Future AGI's Agent Command Center to route any Together AI model with cost-optimized fallback and unified observability.
104
chat 99
| Model ↕ | Input / 1M ↕ | Output / 1M ↕ | Blended ↕ | Context ↕ | Caps |
|---|---|---|---|---|---|
| Qwen2.1 5B Instruct | $0.0200/M | $0.0200/M | $0.0200/M | 32,768 | |
| Together Tev1 4B Experimental | $0.0420/M | — | — | 32,768 | |
| Arcee AI Trinity mini | $0.0450/M | $0.150/M | $0.0713/M | 128,000 | |
| gpt-oss 20B Deprecated | $0.0500/M | $0.200/M | $0.0875/M | 131,072 | |
| Llama 3.2 1B Instruct | $0.0600/M | $0.0600/M | $0.0600/M | 131,072 | |
| Llama 3.2 3B Instruct | $0.0600/M | $0.0600/M | $0.0600/M | 131,072 | |
| Nvidia Nvidia Nemotron nano 9B v2 Deprecated | $0.0600/M | $0.250/M | $0.108/M | 131,072 | |
| Arize AI Qwen 2.1 5B Instruct | $0.1000/M | $0.1000/M | $0.1000/M | 32,768 | |
| Mistral Small 24B Instruct 2501 Deprecated | $0.1000/M | $0.300/M | $0.150/M | 32,768 | |
| Together AI Up To 4B | $0.1000/M | $0.1000/M | $0.1000/M | — | |
| DeepSeek V4 Flash 0731 Deprecated | $0.140/M | $0.280/M | $0.175/M | 1,048,576 | tools · cache |
| Nvidia Nvidia Nemotron 3.5 Super VL | $0.150/M | $0.500/M | $0.238/M | 262,144 | tools · vision · reasoning · cache |
| gpt-oss 120B | $0.150/M | $0.600/M | $0.262/M | 131,072 | tools · reasoning |
| Qwen3.8 Flash | $0.150/M | $0.470/M | $0.230/M | 1,000,000 | |
| Qwen3 Next 80B A3B Instruct Deprecated | $0.150/M | $1.50/M | $0.488/M | 262,144 | |
| Qwen3 Next 80B A3B Thinking Deprecated | $0.150/M | $1.50/M | $0.488/M | 262,144 | |
| GLM 5.3 Flash | $0.150/M | $0.500/M | $0.238/M | 1,048,575 | tools · vision · reasoning · cache |
| Qwen3.5 9B | $0.170/M | $0.250/M | $0.190/M | 262,144 | tools · vision · reasoning |
| DeepSeek R1 Distill Qwen 1 5B Deprecated | $0.180/M | $0.180/M | $0.180/M | 131,072 | |
| Llama 4 Scout 17B 16e Instruct Deprecated | $0.180/M | $0.590/M | $0.283/M | 1,048,576 | |
| Llama 3.1 8B Instruct Turbo Deprecated | $0.180/M | $0.180/M | $0.180/M | 131,072 | |
| Qwen3 VL 8B Instruct Deprecated | $0.180/M | $0.680/M | $0.305/M | 262,144 | |
| Llama 3 8B Chat Hf Deprecated | $0.200/M | $0.200/M | $0.200/M | 8,192 | |
| Llama 3 8B Instruct Deprecated | $0.200/M | $0.200/M | $0.200/M | 8,192 | |
| Ministral 3 14B Instruct 2512 | $0.200/M | $0.200/M | $0.200/M | 262,144 | |
| Mistral 7B Instruct v0.1 Deprecated | $0.200/M | $0.200/M | $0.200/M | 32,768 | |
| Mistral 7B Instruct v0.3 | $0.200/M | $0.200/M | $0.200/M | 32,768 | |
| Qwen3 235B A22B FP8 Tput | $0.200/M | $0.600/M | $0.300/M | 40,000 | |
| Qwen3 235B A22B Instruct 2507 Tput | $0.200/M | $6.00/M | $1.65/M | 262,000 | tools |
| Together AI 4 1B 8B | $0.200/M | $0.200/M | $0.200/M | — | |
| GLM 4.5 Air FP8 Deprecated | $0.200/M | $1.10/M | $0.425/M | 131,072 | |
| Llama 4 Maverick 17B 128e Instruct FP8 | $0.270/M | $0.850/M | $0.415/M | — | tools |
| DeepSeek V4.1 Flash | $0.300/M | $1.20/M | $0.525/M | 1,048,576 | tools · cache |
| DeepSeek V4.1 Flash 1017 | $0.300/M | $1.20/M | $0.525/M | 1,048,576 | tools · vision · reasoning · cache |
| MiniMax M2.7 | $0.300/M | $1.20/M | $0.525/M | 196,608 | |
| MiniMax M3 | $0.300/M | $1.20/M | $0.525/M | 524,288 | tools · vision · reasoning · cache |
| Qwen2.5 7B Instruct Turbo | $0.300/M | $0.300/M | $0.300/M | 32,768 | tools |
| Together AI 8 1B 21B | $0.300/M | $0.300/M | $0.300/M | 1,000 | |
| Qwen3.7 Plus | $0.320/M | $1.28/M | $0.560/M | 1,000,000 | |
| Meta Models Muse Glimmer 30B | $0.350/M | $1.50/M | $0.638/M | 131,072 | cache |
| Gemma 4 31B IT Deprecated | $0.390/M | $0.970/M | $0.535/M | 262,144 | |
| Reflection Beam 1.0 501B A23B | $0.400/M | $1.20/M | $0.600/M | 1,048,576 | tools · cache |
| GLM 4.7 Deprecated | $0.450/M | $2.00/M | $0.837/M | 202,752 | |
| Kimi K2.5 | $0.500/M | $2.80/M | $1.08/M | 256,000 | tools · vision · reasoning |
| Kimi K2.5 Fp4 | $0.500/M | $2.80/M | $1.08/M | 262,144 | |
| Qwen3.6 Plus | $0.500/M | $3.00/M | $1.13/M | 1,000,000 | reasoning |
| Qwen3 Coder Next FP8 Deprecated | $0.500/M | $1.20/M | $0.675/M | 262,144 | |
| Qwen3 VL 32B Instruct Deprecated | $0.500/M | $1.50/M | $0.750/M | 262,144 | |
| DeepSeek R1 0528 Tput | $0.550/M | $2.19/M | $0.960/M | 128,000 | tools |
| DeepSeek v3.1 Deprecated | $0.600/M | $1.70/M | $0.875/M | 131,072 | |
| Mixtral 8×7B Instruct v0.1 Deprecated | $0.600/M | $0.600/M | $0.600/M | 32,768 | |
| Nousresearch Nous Hermes 2 Mixtral 8×7B DPO Deprecated | $0.600/M | $0.600/M | $0.600/M | 32,768 | |
| Nvidia Nemotron 3 Ultra 550B A55B Deprecated | $0.600/M | $3.60/M | $1.35/M | 512,288 | |
| Qwen3.5 397B A17B Deprecated | $0.600/M | $3.60/M | $1.35/M | 262,144 | |
| GLM 4.6 | $0.600/M | $2.20/M | $1.00/M | 202,752 | tools · reasoning |
| Qwen3 235B A22B Thinking 2507 | $0.650/M | $3.00/M | $1.24/M | 256,000 | tools |
| DeepSeek Coder 33B Instruct Deprecated | $0.800/M | $0.800/M | $0.800/M | 16,384 | |
| Gemma 2 27B IT Deprecated | $0.800/M | $0.800/M | $0.800/M | 8,192 | |
| Qwen2.5 14B Instruct | $0.800/M | $0.800/M | $0.800/M | 32,768 | |
| Qwen2.5 Coder 32B Instruct Deprecated | $0.800/M | $0.800/M | $0.800/M | 16,384 | |
| Together AI 21 1B 41B | $0.800/M | $0.800/M | $0.800/M | — | |
| Llama 3.1 70B Instruct Turbo Deprecated | $0.880/M | $0.880/M | $0.880/M | 131,072 | |
| Llama 3 70B Instruct Turbo Deprecated | $0.880/M | $0.880/M | $0.880/M | 8,192 | |
| Nvidia Llama 3.1 Nemotron 70B Instruct Hf Deprecated | $0.880/M | $0.880/M | $0.880/M | 32,768 | |
| Qwen2 72B Instruct Deprecated | $0.900/M | $0.900/M | $0.900/M | 32,768 | |
| Together AI 41 1B 80B | $0.900/M | $0.900/M | $0.900/M | — | |
| Kimi K2.7 Code Deprecated | $0.950/M | $4.00/M | $1.71/M | 262,144 | |
| Kimi K2 Instruct | $1.00/M | $3.00/M | $1.50/M | — | tools |
| Kimi K2 Instruct 0905 | $1.00/M | $3.00/M | $1.50/M | 262,144 | tools |
| Thinkingmachines Inkling | $1.00/M | $4.05/M | $1.76/M | 524,288 | tools · cache |
| GLM 5 Deprecated | $1.00/M | $3.20/M | $1.55/M | 202,752 | |
| Llama 3.3 70B Instruct Turbo Deprecated | $1.04/M | $1.04/M | $1.04/M | 131,072 | tools |
| Kimi K2.6 Deprecated | $1.20/M | $4.50/M | $2.03/M | 262,144 | |
| Qwen2.5 72B Instruct | $1.20/M | $1.20/M | $1.20/M | 32,768 | |
| Qwen2.5 72B Instruct Turbo Deprecated | $1.20/M | $1.20/M | $1.20/M | 131,072 | |
| Qwen2 VL 72B Instruct Deprecated | $1.20/M | $1.20/M | $1.20/M | 32,768 | |
| QwQ 32B Deprecated | $1.20/M | $1.20/M | $1.20/M | 131,072 | |
| DeepSeek V3 | $1.25/M | $1.25/M | $1.25/M | 65,536 | tools |
| Meta Models Muse Spark Open 816B A42B | $1.25/M | $4.25/M | $2.00/M | 1,048,576 | tools · cache |
| DeepSeek V4 Pro 0813 | $1.32/M | $3.96/M | $1.98/M | 1,048,576 | tools · cache |
| GLM 5.1 Deprecated | $1.40/M | $4.40/M | $2.15/M | 202,752 | |
| GLM 5.2 | $1.40/M | $4.40/M | $2.15/M | 1,048,575 | tools · reasoning · cache |
| GLM 5.3 | $1.40/M | $4.40/M | $2.15/M | 1,048,575 | tools · reasoning · cache |
| Qwen3.7 Max | $1.50/M | $4.50/M | $2.25/M | 1,000,000 | cache |
| DeepSeek R1 Distill Qwen 14B Deprecated | $1.60/M | $1.60/M | $1.60/M | 131,072 | |
| Together AI 81 1B 110B | $1.80/M | $1.80/M | $1.80/M | — | |
| Qwen2.5 VL 72B Instruct Deprecated | $1.95/M | $8.00/M | $3.46/M | 32,768 | |
| DeepSeek R1 Distill Llama 70B Deprecated | $2.00/M | $2.00/M | $2.00/M | 131,072 | |
| Qwen3.8 2.4t A95B | $2.00/M | $6.00/M | $3.00/M | 1,010,000 | cache |
| Qwen3 Coder 480B A35B Instruct FP8 Deprecated | $2.00/M | $2.00/M | $2.00/M | 262,144 | |
| DeepSeek R1 | $3.00/M | $7.00/M | $4.00/M | 128,000 | tools |
| DeepSeek R1 0528 | $3.00/M | $7.00/M | $4.00/M | 163,840 | |
| Kimi K3 | $3.00/M | $15.00/M | $6.00/M | 1,048,576 | tools · vision · reasoning · cache |
| Llama 3.1 405B Instruct | $3.50/M | $3.50/M | $3.50/M | 4,096 | |
| Llama 3.1 405B Instruct Turbo | $3.50/M | $3.50/M | $3.50/M | — | tools |
| Llama 3.2 3B Instruct Turbo | — | — | — | — | tools |
| Llama 3.3 70B Instruct Turbo Free | — | — | — | — | tools |
| Prism Ml Ternary Bonsai 27B | — | — | — | 262,144 | |
| Togethercomputer Codellama 34B Instruct | — | — | — | — | tools |
embedding 3
| Model ↕ | Input / 1M ↕ | Output / 1M ↕ | Blended ↕ | Context ↕ | Caps |
|---|---|---|---|---|---|
| Baai BGE Base En v1.5 | $0.008000/M | — | — | 512 | |
| Together AI Embedding Up To 150M | $0.008000/M | — | — | — | |
| Together AI Embedding 151M To 350M | $0.0160/M | — | — | — |
completion 1
| Model ↕ | Input / 1M ↕ | Output / 1M ↕ | Blended ↕ | Context ↕ | Caps |
|---|---|---|---|---|---|
| Llama 3.1 8B | $0.200/M | $0.200/M | $0.200/M | 16,384 |
rerank 1
| Model ↕ | Input / 1M ↕ | Output / 1M ↕ | Blended ↕ | Context ↕ | Caps |
|---|---|---|---|---|---|
| Salesforce Llama Rank v1 Deprecated | $0.1000/M | — | — | 8,192 |
FAQ
How many Together AI models are there?
104 Together AI models are listed across 4 modalities on this page. 100 have public per-token pricing.
How is Together AI pricing verified?
Pricing is aggregated from BerriAI/litellm, models.dev, and OpenRouter and refreshed weekly. Each row shows a per-model "verified" date. If a price is wrong, click the row to open the model page and use the inline "suggest edit" link — submissions go into a public review queue.
Which Together AI model is cheapest?
Input pricing on Together AI starts at $0.008000 per 1M tokens. Sort the table by price (or use the in-page filter at the top) to find the cheapest model that matches your capability requirements.
Can I route to Together AI via an OpenAI-compatible API?
Yes — point your OpenAI client at Future AGI's Agent Command Center, configure a Together AI target, and call Together AI models with the standard /v1/chat/completions surface. The same gateway can route to other providers as fallback. Free for the first 100K requests/month.
Route any Together AI model via Agent Command Center →
OpenAI-compatible endpoint. Caching, fallback, guardrails, observability. Free for 100K requests/month.