Together AI models & pricing

Together AI hosts 42 models (35 with public pricing) covering 2 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.

Homepage ↗ Docs ↗
42

chat 39

Model ↕ Input / 1M ↕ Output / 1M ↕ Blended ↕ Context ↕ Caps
OpenAI GPT Oss 20B $0.0500/M $0.200/M $0.0875/M 128,000 tools
Together AI Up To 4B $0.1000/M $0.1000/M $0.1000/M —
OpenAI GPT Oss 120B $0.150/M $0.600/M $0.262/M 131,072 tools · reasoning
Qwen Qwen3 Next 80B A3b Instruct $0.150/M $1.50/M $0.488/M 262,144 tools
Qwen Qwen3 Next 80B A3b Thinking $0.150/M $1.50/M $0.488/M 262,144 tools
Meta Llama Llama 4 Scout 17B 16e Instruct $0.180/M $0.590/M $0.283/M — tools
Meta Llama Meta Llama 3.1 8B Instruct Turbo $0.180/M $0.180/M $0.180/M — tools
Qwen Qwen3.235b A22b Fp8 Tput $0.200/M $0.600/M $0.300/M 40,000
Qwen 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 —
Zai Org Glm 4.5 Air Fp8 $0.200/M $1.10/M $0.425/M 128,000 tools
Meta Llama Llama 4 Maverick 17B 128e Instruct Fp8 $0.270/M $0.850/M $0.415/M — tools
Together AI 8.1B 21B $0.300/M $0.300/M $0.300/M 1,000
Zai Org Glm 4.7 $0.450/M $2.00/M $0.837/M 200,000 tools · reasoning
Moonshotai Kimi K2.5 $0.500/M $2.80/M $1.08/M 256,000 tools · vision · reasoning
DeepSeek AI DeepSeek R1.0528 Tput $0.550/M $2.19/M $0.960/M 128,000 tools
DeepSeek AI DeepSeek v3.1 $0.600/M $1.70/M $0.875/M 128,000 tools · reasoning
Mistralai Mixtral 8×7B Instruct v0.1 $0.600/M $0.600/M $0.600/M — tools
Qwen Qwen3.5 397B A17b $0.600/M $3.60/M $1.35/M 262,144 tools
Zai Org Glm 4.6 $0.600/M $2.20/M $1.00/M 200,000 tools · reasoning
Qwen Qwen3.235b A22b Thinking 2507 $0.650/M $3.00/M $1.24/M 256,000 tools
Together AI 21.1B 41B $0.800/M $0.800/M $0.800/M —
Meta Llama Llama 3.3 70B Instruct Turbo $0.880/M $0.880/M $0.880/M — tools
Meta Llama Meta Llama 3.1 70B Instruct Turbo $0.880/M $0.880/M $0.880/M — tools
Together AI 41.1B 80B $0.900/M $0.900/M $0.900/M —
Moonshotai Kimi K2 Instruct $1.00/M $3.00/M $1.50/M — tools
Moonshotai Kimi K2 Instruct 0905 $1.00/M $3.00/M $1.50/M 262,144 tools
DeepSeek AI DeepSeek v3 $1.25/M $1.25/M $1.25/M 65,536 tools
Together AI 81.1B 110B $1.80/M $1.80/M $1.80/M —
Qwen Qwen3 Coder 480B A35b Instruct Fp8 $2.00/M $2.00/M $2.00/M 256,000 tools
DeepSeek AI DeepSeek R1 $3.00/M $7.00/M $4.00/M 128,000 tools
Meta Llama Meta Llama 3.1 405B Instruct Turbo $3.50/M $3.50/M $3.50/M — tools
Meta Llama Llama 3.2 3B Instruct Turbo — — — — tools
Meta Llama Llama 3.3 70B Instruct Turbo Free — — — — tools
Mistralai Mistral 7B Instruct v0.1 — — — — tools
Mistralai Mistral Small 24B Instruct 2501 — — — — tools
Qwen Qwen2.5 72B Instruct Turbo — — — — tools
Qwen Qwen2.5 7B Instruct Turbo — — — — tools
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 — — —

FAQ

How many Together AI models are there?

42 Together AI models are listed across 2 modalities on this page. 35 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.