Model Shaping
Pricing
Serverless Inference
Most teams start with serverless inference and move to dedicated endpoints at scale.
Price per 1M tokens
Batch API price
Model | Input | output |
|---|---|---|
 DeepSeek V4 Pro | $1.74 $0.20 (cached) | $3.48 |
 MiniMax M3 | $0.30 $0.06 (cached) | $1.20 |
 Kimi K2.7 Code | $0.95 $0.19 (cached) | $4.00 |
 GLM-5.2 | $1.40 $0.26 (cached) | $4.40 |
 Gemma 4 31B | $0.39 | $0.97 |
 NVIDIA Nemotron 3 Ultra | $0.60 $0.20 (cached) | $3.60 |
 Qwen3.7-Plus | $0.32 | $1.28 |
Kimi K2.6 | $1.20 $0.20 (cached) | $4.50 |
Qwen3.7-Max | $1.25 $0.13 (cached) | $3.75 |
 gpt-oss-120B | $0.15 | $0.60 |
Qwen3.5-397B-A17B | $0.60 $0.35 (cached) | $3.60 |
Qwen3.5 9B | $0.17 | $0.25 |
 Gemma-4-31B-it-Pearl | $0.28 | $0.86 |
 Cogito v2.1 671B | $1.25 | $1.25 |
 Rnj-1 Instruct | $0.15 | $0.15 |
 Llama 3.3 70B | $1.04 | $1.04 |
Gemma 3n E4B Instruct | $0.06 | $0.12 |
gpt-oss-20B | $0.05 | $0.20 |
GLM-5.1 | $1.40 $0.26 (cached) | $4.40 |
MiniMax M2.7 | $0.30 $0.06 (cached) | $1.20 |
Qwen3.6-Plus | $0.50 | $3.00 |
Qwen2.5 7B Instruct Turbo | $0.30 | $0.30 |
Llama 3 8B Instruct Lite | $0.14 | $0.14 |
Displayed prices refer to the lowest resolution/duration settings. Actual prices might vary.
Price per 1M tokens
Model | Input | output |
|---|---|---|
MiniMax M3 | $0.30 | $1.20 |
Kimi K2.7 Code | $0.95 | $4.00 |
Gemma 4 31B | $0.39 | $0.97 |
Qwen3.7-Plus | $0.32 | $1.28 |
Kimi K2.6 | $1.20 | $4.50 |
Qwen3.5 9B | $0.17 | $0.25 |
Gemma 3n E4B Instruct | $0.06 | $0.12 |
Qwen3.6-Plus | $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 |
|---|---|---|---|
Qwen3.7-Plus | - | - | - |
GPT Image 2 | - | $0.053 | - |
 Wan 2.6 Image | - | $0.03 | - |
 FLUX.2 [pro] | - | $0.03 | - |
 Ideogram 4.0 | - | $0.06 | - |
Qwen Image 2.0 Pro | - | $0.08 | - |
Qwen Image 2.0 | - | $0.04 | - |
FLUX.2 [dev] | - | $0.0154 | - |
FLUX.2 [flex] | - | $0.03 | - |
FLUX.2 [max] | $0.070 | - | 50 |
FLUX.1 Kontext [pro] | $0.04 | - | 28 |
FLUX1.1 [pro] | $0.04 | - | - |
 Juggernaut Pro Flux | $0.0049 | - | - |
GPT Image 1.5 | - | $0.034 | - |
FLUX.1 Kontext [max] | $0.08 | - | 28 |
FLUX.1 [schnell] | $0.0027 | - | 4 |
 SD XL | $0.0019 | - | - |
Ideogram 3.0 | $0.06 | - | - |
 HiDream-I1-Full | $0.009 | - | - |
Juggernaut Lightning Flux | $0.0017 | - | - |
Qwen Image | $0.0058 | - | - |
Google Imagen 4.0 Fast | $0.02 | - | - |
 ByteDance Seedream 4.0 | $0.03 | - | - |
Google Imagen 4.0 Preview | $0.04 | - | - |
Google Imagen 4.0 Ultra | $0.06 | - | - |
ByteDance Seedream 3.0 | $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 |
|---|
Price per video
Model | Price |
|---|---|
Google Veo 3.0 | $1.60 |
 Kling 1.6 Standard | $0.19 |
Kling 2.1 Master | $0.92 |
Kling 2.1 Pro | $0.32 |
Kling 2.1 Standard | $0.18 |
 Vidu 2.0 | $0.28 |
Vidu Q1 | $0.22 |
Wan 2.2 I2V | $0.31 |
Wan 2.2 T2V | $0.66 |
Qwen3.6-Plus | $0.50 |
Sora 2 | $0.80 |
 PixVerse v5 | $0.30 |
Google Veo 3.0 Fast | $0.80 |
Google Veo 2.0 | $2.50 |
MiniMax Hailuo 02 | $0.49 |
MiniMax 01 Director | $0.28 |
Price per audio minute
Batch API price
Model | Price |
|---|---|
NVIDIA Parakeet TDT 0.6B v3 | $0.0015 |
NVIDIA Nemotron 3.5 ASR | $0.0045/min |
Whisper Large v3 | $0.0015 |
Whisper Large v3 (Streaming) | $0.0035/min |
Price per 1M tokens
Model | Price |
|---|
Price per 1M tokens
Model | Price |
|---|
Price per 1M tokens
Model | Price |
|---|---|
Llama Guard 4 12B | $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.
Compute costs | Input | Cached | Output | Price |
|---|---|---|---|---|
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 | |
NVIDIA HGX H200 | ||
NVIDIA HGX B200 | $8.99 | |
NVIDIA HGX B300 | ||
NVIDIA GB200 NVL72 | ||
NVIDIA GB300 NVL72 |
GPU Clusters
On-demand
Pay as you go GPU capacity on an hourly basis.
Hardware | Hourly |
|---|---|
NVIDIA GB200 NVL72 | — |
NVIDIA GB300 NVL72 | — |
NVIDIA HGX B200 | $8.19 |
NVIDIA HGX B300 | — |
NVIDIA HGX HGX H100 | $3.99 |
NVIDIA HGX HGX 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 | 91-180 days | 181+ days | |
NVIDIA HGX H100 | $3.99 | $3.59 | $3.29 | $3.09 | |
NVIDIA HGX H200 | $5.99 | $4.99 | $4.15 | $3.99 | |
NVIDIA HGX B200 | $8.19 | $7.99 | $7.79 | $6.79 | |
NVIDIA GB200 NVL72 | — | ||||
NVIDIA GB300 NVL72 | — | ||||
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 | LoRA | Full Fine-Tuning |
|---|---|---|---|---|
Up to 16B | $0.48 | $0.54 | $1.20 | $1.35 |
17B-69B | $1.50 | $1.65 | $3.75 | $4.12 |
70-100B | $2.90 | $3.20 | $7.25 | $8.00 |
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). Each job is subject to a minimum charge of $4.00.
Size | Supervised | Direct Preference | 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).
No matching models
Trusted by
