Together AI API pricing and models
Together AI publishes per-token prices for 31 text models, plus 1 free variant, as of October 20, 2026. The lowest output rate is $0.14 per million tokens, on Llama 3 8B Instruct Lite, and the highest-scoring model it serves is Kimi K3, at 79 on our 100-point score.
Together AI runs a serverless API for open-weight models and rents GPU clusters. This page covers the serverless per-token prices only.
Every model Together AI prices, with its score
Prices are US dollars per million tokens, read from Together AI pricing page (serverless table) on the date above. The score is our 100-point rating of the model, the same on every host. “vs maker” compares this host’s output rate with the model maker’s own API.
| Model | Score | Input /1M | Output /1M | Cached /1M | Context | vs maker |
|---|---|---|---|---|---|---|
| Kimi K3moonshotai/Kimi-K3 | 79 | $3.00 | $15.00 | $0.30 | 1.05M | Same |
| Qwen3.7 MaxQwen/Qwen3.7-Max | 76 | $2.50 | $7.50 | $0.50 | — | — |
| DeepSeek V4.1 Flashdeepseek-ai/DeepSeek-V4.1-Flash | 73 | $0.30 | $1.20 | $0.006 | 1M | Same |
| DeepSeek V4.1 Flash 1017deepseek-ai/DeepSeek-V4.1-Flash-1017 | 73 | $0.30 | $1.20 | $0.006 | 1M | Same |
| Qwen3.7 PlusQwen/Qwen3.7-Plus | 71 | $0.32 | $1.28 | — | 1M | — |
| GLM-5.3 Flashzai-org/GLM-5.3-Flash | 69 | $0.15 | $0.50 | $0.03 | 1.05M | — |
| DeepSeek V4 Pro 0813deepseek-ai/DeepSeek-V4-Pro-0813 | 69 | $1.32 | $3.96 | $0.13 | 1.05M | Same |
| Beam 1.0 501B A23Breflection/Beam-1.0-501B-A23B | 68 | $0.40 | $1.20 | $0.04 | 1.05M | — |
| Qwen3.6 PlusQwen/Qwen3.6-Plus | 68 | $0.50 | $3.00 | — | 1M | — |
| GLM-5.3zai-org/GLM-5.3 | 68 | $1.40 | $4.40 | $0.26 | 1.05M | — |
| Inklingthinkingmachines/Inkling | 67 | $1.00 | $4.05 | $0.17 | 524K | −13% |
| Minimax M3MiniMaxAI/MiniMax-M3 | 65 | $0.30 | $1.20 | $0.06 | 524K | Same |
| GLM-5.2zai-org/GLM-5.2 | 65 | $1.40 | $4.40 | $0.26 | 1.05M | Same |
| DeepSeek V4 Flash 0731deepseek-ai/DeepSeek-V4-Flash-0731 | 62 | $0.14 | $0.28 | $0.03 | — | Same |
| Llama 3.3 70Bmeta-llama/Llama-3.3-70B-Instruct-Turbo | 61 | $1.04 | $1.04 | — | — | — |
| Muse Glimmer 30Bmeta-models/Muse-Glimmer-30B | 61 | $0.35 | $1.50 | $0.04 | 131K | — |
| MiniMax M2.7MiniMaxAI/MiniMax-M2.7 | 60 | $0.30 | $1.20 | $0.06 | — | Same |
| Gemma 4 31Bgoogle/gemma-4-31B-it | 56 | $0.39 | $0.97 | — | — | — |
| GPT-OSS 120Bopenai/gpt-oss-120b | 55 | $0.15 | $0.60 | — | 131K | — |
| Ternary Bonsai 27BPrism-ML/Ternary-Bonsai-27B | 0 | $0 | $0 | — | 262K | — |
| Tev1 4B ExperimentalPreviewtogether/Tev1-4B-experimental | 0 | $0.042 | $0 | — | 33K | — |
11 more models Together AI prices that we don’t score
| Model | Input /1M | Output /1M | Cached /1M | Context |
|---|---|---|---|---|
| Llama 3 8B Instruct Litemeta-llama/Meta-Llama-3-8B-Instruct-Lite | $0.14 | $0.14 | — | — |
| Rnj-1 Instructessentialai/rnj-1-instruct | $0.15 | $0.15 | — | — |
| Qwen3.5 9BQwen/Qwen3.5-9B | $0.17 | $0.25 | — | 262K |
| Qwen2.5 7B Instruct TurboQwen/Qwen2.5-7B-Instruct-Turbo | $0.30 | $0.30 | — | — |
| Qwen3.8 FlashQwen/Qwen3.8-Flash | $0.15 | $0.47 | — | 1M |
| NVIDIA Nemotron 3.5 Super VLnvidia/NVIDIA-Nemotron-3.5-Super-VL | $0.15 | $0.50 | $0.02 | 262K |
| Qwen3 235B A22B Instruct 2507 FP8 ThroughputQwen/Qwen3-235B-A22B-Instruct-2507-tput | $0.20 | $0.60 | — | — |
| Cogito v2.1 671Bdeepcogito/cogito-v2-1-671b | $1.25 | $1.25 | — | — |
| Qwen3.5-397B-A17BQwen/Qwen3.5-397B-A17B | $0.60 | $3.60 | $0.35 | — |
| Muse Spark Open 816B A42Bmeta-models/Muse-Spark-Open-816B-A42B | $1.25 | $4.25 | $0.15 | 1.05M |
| Qwen3.8-2.4T-A95BQwen/Qwen3.8-2.4T-A95B | $2.00 | $6.00 | $0.50 | — |
We paid for 900 requests on Together AI
All 900 requests succeeded, and Together’s GLM-5.2 p95 was second only to OpenRouter. Its invoice charged 2,928,000 GLM-5.2 input tokens against 1,667,041 reported by its own API responses, 76% more, while the same method reconciled to the token on DeepSeek Flash. We record this as observed and unexplained; the findings section has the figures, and we have invited a correction. It scored 61 of 100, third of 5 platforms we scored.
| Model run | Invoiced /1M blended | Median latency | p95 latency | Succeeded |
|---|---|---|---|---|
| DeepSeek V4 Flash | $0.11 | 2.55 s | 10.09 s | 100.0% |
| GLM-5.2 | $1.67 | 2.53 s | 5.66 s | 100.0% |
Run on September 1, 2026 with 450 requests per model: short prompts, 20,000-token documents and tool calls. Method and every invoice are on the OpenRouter alternatives audit.
Hosts that sell the same models
Each row counts the scored models both hosts price, and how many of those cost less per output token there than on Together AI.
Questions
How much does the Together AI API cost?
Together AI bills per million tokens, with separate input and output rates for each model. On October 20, 2026 its output rates ran from $0.14 on Llama 3 8B Instruct Lite to $15.00 across 31 paid models. Input is usually cheaper than output, so a long prompt with a short reply costs less than the output rate suggests.
Which models can you run on Together AI?
32 text models are listed, and 20 of them match a model we score. The highest-scoring is Kimi K3 at 79. The table on this page has every model with its input, output and cached-input rate, the context window, and the date we read the price.
Is Together AI fast?
In our paid September 1, 2026 run, Together AI returned a median of 2.55 seconds on DeepSeek V4 Flash and 2.53 seconds on GLM-5.2, over 450 requests per model. That is one workload on one date, so check your own prompts before you rely on it.
What are the alternatives to Together AI?
OpenRouter lists 18 of the same models and charges less output per token on 12 of them. DeepInfra and Novita AI also overlap. Price is only part of the choice: speed, rate limits and which model snapshot a host serves differ too.