Pricing | Together AI

💰 Announcing our Series C. Intelligence should be abundant, not expensive →

🤝 Together AI & Y Combinator announce partnership to deliver the first dedicated YC GPU cluster →

⚡ On-demand B200s now available on Together GPU Clusters →

🚀 Now serving MiniMax-M3 for efficient inference →

INFERENCE

Compute

Model Shaping

Need help choosing?

Our team can help you find the best fit for your needs.

Contact us

Pricing

Pricing

Serverless Inference

Most teams start with serverless inference and move to dedicated endpoints at scale.

Chat Vision Image Audio Video Transcribe Embeddings Rerank Moderation

Thank you! Your submission has been received!

Oops! Something went wrong while submitting the form.

Price per 1M tokens

Batch API price

Model Input output
<br><br>DeepSeek V4 Pro](/content/models/deepseek-v4-pro/index.html) $1.74
$0.20 (cached)		 $3.48
<br><br>MiniMax M3](/content/models/minimax-m3/index.html) $0.30
$0.06 (cached)		 $1.20
<br><br>GLM-5.2](/content/models/glm-52/index.html) $1.40
$0.26 (cached)		 $4.40
<br><br>Kimi K3](/content/models/kimi-k3/index.html) $3.00
$0.30 (cached)		 $15.00
<br><br>Inkling Small](/content/models/inkling-small/index.html) $0.50
$0.10 (cached)		 $1.20
<br><br>DeepSeek V4 Flash 0731](/content/models/deepseek-v4-flash-0731/index.html) $0.14
$0.03 (cached)		 $0.28
<br><br>Gemma 4 31B](/content/models/gemma-4-31b/index.html) $0.39 $0.97
<br><br>NVIDIA Nemotron 3 Ultra](/content/models/nvidia-nemotron-3-ultra/index.html) $0.60
$0.20 (cached)		 $3.60
<br><br>Kimi K2.7 Code](/content/models/kimi-k27-code/index.html) $0.95
$0.19 (cached)		 $4.00
<br><br>Qwen3.7-Plus](/content/models/qwen37-plus/index.html) $0.32 $1.28
<br><br>PrismMLTernary Bonsai 27B](/content/models/prism-ml-ternary-bonsai-27b/index.html) 0.00
<br><br>Inkling](/content/models/inkling/index.html) $1.00
$0.17 (cached)		 $4.05
<br><br>LFM2.5-8B-A1B](/content/models/liquid-lfm2-5-8b-a1b/index.html) $0.03 $0.12
<br><br>Kimi K2.6](/content/models/kimi-k26/index.html) $1.20
$0.20 (cached)		 $4.50
<br><br>Qwen3.7-Max](/content/models/qwen37-max/index.html) $1.25
$0.13 (cached)		 $3.75
<br><br>gpt-oss-120B](/content/models/gpt-oss-120b/index.html) $0.15 $0.60
<br><br>Qwen3.5-397B-A17B](/content/models/qwen3-5-397b-a17b/index.html) $0.60
$0.35 (cached)		 $3.60
<br><br>Qwen3.5 9B](/content/models/qwen3-5-9b/index.html) $0.17 $0.25
<br><br>Gemma-4-31B-it-Pearl](/content/models/gemma-4-31b-it-pearl/index.html) $0.28 $0.86
<br><br>Cogito v2.1 671B](/content/models/cogito-v2-1-671b/index.html) $1.25 $1.25
<br><br>Rnj-1 Instruct](/content/models/rnj-1-instruct/index.html) $0.15 $0.15
<br><br>Llama 3.3 70B](/content/models/llama-3-3-70b/index.html) $1.04 $1.04
<br><br>Gemma 3n E4B Instruct](/content/models/gemma-3n-e4b-it/index.html) $0.06 $0.12
<br><br>gpt-oss-20B](/content/models/gpt-oss-20b/index.html) $0.05 $0.20
<br><br>GLM-5.1](/content/models/glm-51/index.html) $1.40
$0.26 (cached)		 $4.40
<br><br>MiniMax M2.7](/content/models/minimax-m2-7/index.html) $0.30
$0.06 (cached)		 $1.20
<br><br>Qwen3.6-Plus](/content/models/qwen36-plus/index.html) $0.50 $3.00
<br><br>Qwen2.5 7B Instruct Turbo](/content/models/qwen2-5-7b-instruct-turbo/index.html) $0.30 $0.30
<br><br>Llama 3 8B Instruct Lite](/content/models/llama-3-8b-instruct-lite/index.html) $0.14 $0.14
<br><br>Qwen3 235B A22B Instruct 2507 FP8 Throughput](/content/models/qwen3-235b-a22b-instruct-2507-fp8/index.html) $0.20 $0.60

Displayed prices refer to the lowest resolution/duration settings. Actual prices might vary.

Price per 1M tokens

Model Input output
<br><br>MiniMax M3](/content/models/minimax-m3/index.html) $0.30 $1.20
<br><br>Kimi K3](/content/models/kimi-k3/index.html) $3.00 $15.00
<br><br>Inkling Small](/content/models/inkling-small/index.html) $0.50 $1.20
<br><br>Gemma 4 31B](/content/models/gemma-4-31b/index.html) $0.39 $0.97
<br><br>Kimi K2.7 Code](/content/models/kimi-k27-code/index.html) $0.95 $4.00
<br><br>Qwen3.7-Plus](/content/models/qwen37-plus/index.html) $0.32 $1.28
<br><br>PrismMLTernary Bonsai 27B](/content/models/prism-ml-ternary-bonsai-27b/index.html) 0.00
<br><br>Inkling](/content/models/inkling/index.html) $1.00 $4.05
<br><br>Kimi K2.6](/content/models/kimi-k26/index.html) $1.20 $4.50
<br><br>Qwen3.5 9B](/content/models/qwen3-5-9b/index.html) $0.17 $0.25
<br><br>Gemma 3n E4B Instruct](/content/models/gemma-3n-e4b-it/index.html) $0.06 $0.12
<br><br>Qwen3.6-Plus](/content/models/qwen36-plus/index.html) $0.50 $3.00

Displayed prices refer to the lowest resolution/duration settings. Actual prices might vary.

Model Price per mp Price per iMAGE Default steps
<br><br>Qwen3.7-Plus](/content/models/qwen37-plus/index.html) - - -
<br><br>GPT Image 2](/content/models/gpt-image-2/index.html) - $0.053 -
<br><br>Wan 2.6 Image](/content/models/wan-2-6-image/index.html) - $0.03 -
<br><br>Nano Banana Pro (Gemini 3 Pro Image)](/content/models/nano-banana-pro/index.html) - $0.134 -
<br><br>FLUX.2 [pro]](/content/models/flux-2-pro/index.html) - $0.03 -
<br><br>Ideogram 4.0](/content/models/ideogram-40/index.html) - $0.06 -
<br><br>Gemini 3.1 Flash Image (Nano Banana 2)](/content/models/gemini-31-flash-image/index.html) - $0.05 -
<br><br>Qwen Image 2.0 Pro](/content/models/qwen-image-20-pro/index.html) - $0.08 -
<br><br>Qwen Image 2.0](/content/models/qwen-image-20/index.html) - $0.04 -
<br><br>FLUX.2 [dev]](/content/models/flux-2-dev/index.html) - $0.0154 -
<br><br>FLUX.2 [flex]](/content/models/flux-2-flex/index.html) - $0.03 -
<br><br>FLUX.2 [max]](/content/models/flux-2-max/index.html) $0.070 - 50
<br><br>FLUX.1 Kontext [pro]](/content/models/flux-1-kontext-pro/index.html) $0.04 - 28
<br><br>FLUX1.1 [pro]](/content/models/flux1-1-pro/index.html) $0.04 - -
<br><br>Juggernaut Pro Flux](/content/models/juggernaut-pro-flux/index.html) $0.0049 - -
<br><br>GPT Image 1.5](/content/models/gpt-image-1-5/index.html) - $0.034 -
<br><br>FLUX.1 Kontext [max]](/content/models/flux-1-kontext-max/index.html) $0.08 - 28
<br><br>FLUX.1 [schnell]](/content/models/flux-1-schnell-2/index.html) $0.0027 - 4
<br><br>SD XL](/content/models/sd-xl/index.html) $0.0019 - -
<br><br>Ideogram 3.0](/content/models/ideogram-3-0/index.html) $0.06 - -
<br><br>HiDream-I1-Full](/content/models/hidream-i1-full/index.html) $0.009 - -
<br><br>Juggernaut Lightning Flux](/content/models/juggernaut-lightning-flux/index.html) $0.0017 - -
<br><br>Qwen Image](/content/models/qwen-image/index.html) $0.0058 - -
<br><br>Google Imagen 4.0 Fast](/content/models/google-imagen-4-0-fast/index.html) $0.02 - -
<br><br>ByteDance Seedream 4.0](/content/models/bytedance-seedream-4-0/index.html) $0.03 - -
<br><br>Google Imagen 4.0 Preview](/content/models/google-imagen-4-0-preview/index.html) $0.04 - -
<br><br>Gemini Flash Image 2.5 (Nano Banana)](/content/models/gemini-flash-image-2-5/index.html) - $0.039 -
<br><br>Google Imagen 4.0 Ultra](/content/models/google-imagen-4-0-ultra/index.html) $0.06 - -
<br><br>ByteDance Seedream 3.0](/content/models/bytedance-seedream-3-0/index.html) $0.018 - -

Prices include default steps shown above. Additional costs apply only when exceeding default steps. See full pricing details →

Price per 1M Characters

Model Price
<br><br>Inkling Small](/content/models/inkling-small/index.html) $0.50
<br><br>Inkling](/content/models/inkling/index.html) $1.00
<br><br>NVIDIA Parakeet TDT 0.6B V3 Realtime](/content/models/parakeet-tdt-0-6b-v3-realtime/index.html) $0.0035
<br><br>NVIDIA Nemotron 3 ASR Streaming 0.6B](/content/models/nemotron-3-asr-streaming-0-6b/index.html) $0.0015
<br><br>Cartesia Sonic-3](/content/models/cartesia-sonic-3/index.html) $65.00
<br><br>Orpheus TTS](/content/models/orpheus-tts/index.html) $15
<br><br>Kokoro-82M TTS](/content/models/kokoro-82m/index.html) $4.00
<br><br>Cartesia Sonic-2](/content/models/cartesia-sonic/index.html) $65.00

Price per video

Model Price
<br><br>ByteDance Seedance 2.0](/content/models/seedance-2-0/index.html) $0.16
<br><br>ByteDance Seedance 2.5](/content/models/seedance-2-5/index.html) $0.115
<br><br>FLUX 3](/content/models/flux-3/index.html) $0.17
<br><br>Google Veo 3.0](/content/models/google-veo-3-0/index.html) $1.60
<br><br>Kling 1.6 Standard](/content/models/kling-1-6-standard/index.html) $0.19
<br><br>Kling 2.1 Master](/content/models/kling-2-1-master/index.html) $0.92
<br><br>Kling 2.1 Pro](/content/models/kling-2-1-pro/index.html) $0.32
<br><br>Kling 2.1 Standard](/content/models/kling-2-1-standard/index.html) $0.18
<br><br>Vidu 2.0](/content/models/vidu-2-0/index.html) $0.28
<br><br>Vidu Q1](/content/models/vidu-q1/index.html) $0.22
<br><br>Wan 2.2 I2V](/content/models/wan-2-2-i2v/index.html) $0.31
<br><br>Wan 2.2 T2V](/content/models/wan-2-2-t2v/index.html) $0.66
<br><br>Qwen3.6-Plus](/content/models/qwen36-plus/index.html) $0.50
<br><br>Sora 2](/content/models/sora-2/index.html) $0.80
<br><br>PixVerse v5](/content/models/pixverse-v5/index.html) $0.30
<br><br>ByteDance Seedance 1.0 Lite](/content/models/bytedance-seedance-1-0-lite/index.html) $0.14
<br><br>ByteDance Seedance 1.0 Pro](/content/models/bytedance-seedance-1-0-pro/index.html) $0.57
<br><br>Google Veo 3.0 Fast + Audio](/content/models/google-veo-3-0-fast-audio/index.html) $1.20
<br><br>Google Veo 3.0 Fast](/content/models/google-veo-3-0-fast/index.html) $0.80
<br><br>Google Veo 3.0 + Audio](/content/models/google-veo-3-0-audio/index.html) $3.20
<br><br>Google Veo 2.0](/content/models/google-veo-2-0/index.html) $2.50
<br><br>MiniMax Hailuo 02](/content/models/minimax-hailuo-02/index.html) $0.49
<br><br>MiniMax 01 Director](/content/models/minimax-01-director/index.html) $0.28

Price per audio minute

Batch API price

Model Price
<br><br>NVIDIA Parakeet TDT 0.6B v3](/content/models/parakeet-tdt-0-6b-v3/index.html) $0.0015
<br><br>NVIDIA Nemotron 3.5 ASR](/content/models/nvidia-nemotron-35-asr/index.html) $0.0045/min
<br><br>Whisper Large v3](/content/models/openai-whisper-large-v3/index.html) $0.0015
<br><br>Whisper Large v3 (Streaming)](/content/models/whisper-large-v3-streaming/index.html) $0.0035/min

Price per 1M tokens

Model Price
<br><br>Multilingual e5 large instruct](/content/models/multilingual-e5-large-instruct/index.html) $0.02

Price per 1M tokens

Model Price

No matching models

Price per 1M tokens

Model Price
<br><br>Llama Guard 4 12B](/content/models/llama-guard-4-12b/index.html) $0.20

Provisioned Throughput

Reserve dedicated capacity in throughput units (PTUs). Each PTU represents fixed capacity. The tokens-per-minute it delivers depends on the model and the token type.

Estimate your PTUs & cost

Model

MiniMax M3GLM-5.2Kimi K3

Compare vs.

GPT-5.6 SolGPT-5.6 TerraGPT-5.6 LunaGPT 5.5GPT 5.4GPT 5.2GPT 5.4 miniClaude Fable 5Claude Opus 4.8Claude Sonnet 5Claude Haiku 4.5Gemini 3.5 FlashGemini 3 Flash

Peak requests / Sec

Cache hit rate

%

Input tokens / request

output tokens / request

PTUs required

353

Est. monthly cost

$773,070

Est. monthly savings

$1,802,37070% LOWER

Compute costs Input
TPM/PTU		 Cached
TPM/PTU		 Output
TPM/PTU		 Price
PTU/MIN
Kimi K3 16,667 166,667 3,333 $0.05
MiniMax M3 138,840 694,200 23,140 $0.05
GLM-5.2 35,731 192,400 9,620 $0.05

Savings compare Together PTU cost against the selected commercial model's published list price ($/1M tokens) on the same traffic profile. Estimates assume continuous 24/7 provisioning (~43,800 min/mo).

Dedicated Inference

Deploy models on custom hardware with guaranteed performance and full control.

Single-tenant GPU instances with:

Hardware
All prices per gpu per hour		 On-demand
Pay as you go		 Reserved
NVIDIA HGX H100 $5.49 Contact sales
NVIDIA HGX H200 Contact us
NVIDIA HGX B200 $8.99
NVIDIA HGX B300 Contact us
NVIDIA GB200 NVL72 Contact us
NVIDIA GB300 NVL72 Contact us

GPU Clusters

On-demand

Pay as you go GPU capacity on an hourly basis.

Hardware Hourly
NVIDIAGB200 NVL72 —
NVIDIAGB300 NVL72 —
NVIDIAHGX B200 $8.19
NVIDIAHGX B300 —
NVIDIAHGX H100 $3.99
NVIDIAHGX H200 $5.99

On-demand hourly rates and reserved capacity

All prices are per GPU per hour.

Hardware ON-Demand Reserved
Pay as you go 7-30 days 31-90 days
--- --- ---
NVIDIAHGX H100 $3.99 $3.69
NVIDIAHGX H200 $5.99 $4.99
NVIDIAHGX B200 $8.19 $7.99
NVIDIAGB200 NVL72 — Contact us
NVIDIAGB300 NVL72 — Contact us
NVIDIAHGX B300 — Contact us

Sandbox

Code Sandbox

Customize a deployment of VM sandboxes for large development environments.

Compute costs Price/Hour
Per vCPU $0.0446
Per GiB RAM $0.0149

Code Interpreter

Execute LLM-generated code securely using our API.

Duration? Price/Session
Session (60 minutes) $0.03

Storage

High-bandwidth, parallel filesystem colocated with your compute.

Compute costs Price Unit
Shared Filesystem $0.16 GiB/month

Fine-Tuning

Train open-source models for
real production use.

Per 1M tokens

Supervised Fine-Tuning Direct Preference Optimization
Size LoRA Full Fine-Tuning
--- --- ---
Up to 16B $0.48 $0.54
17B-69B $1.50 $1.65
70-100B $2.90 $3.20

Price is based on the sum of tokens processed in the fine-tuning training dataset (training dataset size * number of epochs) plus any tokens in the optional evaluation dataset (validation dataset size * number of evaluations). Each job is subject to a minimum charge of $4.00.

Size Supervised
Fine-Tuning (LoRA)		 Direct Preference
Optimization (LoRA)		 Minimum charge
DeepSeek-R1
DeepSeek-R1-0528
DeepSeek-V3
DeepSeek-V3-0324
DeepSeek-V3.1
DeepSeek-V3.1-Base		 $10.00 $25.00 $20.00
GLM-4.6
GLM-4.7		 $9.00 $22.50 $27.00
GLM-5
GLM-5.1		 $40 $100 $60
gpt-oss-120B $5.00 $12.50 $6.00
Kimi K2 Thinking
Kimi K2 Instruct-0905
Kimi K2 Instruct
Kimi K2 Base
Kimi K2.5
Kimi K2.6
Kimi K2.7-Code		 $15.00 $37.50 $60.00
Llama 4 Maverick
Llama 4 Maverick Instruct		 $8.00 $20.00 $16.00
Llama 4 Scout
Llama 4 Scout		 $3.00 $7.50 $6.00
Qwen3-Coder-480B-A35B-Instruct $9.00 $22.50 $18.00
Qwen3-235B-A22B
Qwen3-235B-A22B-Instruct-2507		 $6.00 $15.00 No min. price
Qwen3.5-122B-A10B $6.00 $15.00 $10.00
Qwen3.5-397B-A17B $8.00 $20.00 $22.00

Price is based on the sum of tokens processed in the  fine-tuning training dataset (training dataset size * number of epochs)  plus any tokens in the optional evaluation dataset (validation dataset  size * number of evaluations).

Trusted by