Simple, transparent pricing

Pay only for what you use. $1 free credit on signup. All rates are pulled live from the same database that bills your account.

Rates last verified Aug 4, 2026 (UTC)

Inference API

Pay per token across all platform models. OpenAI-compatible endpoints, multi-region routing.

Language

ModelInputOutputNotes
DeepSeek-V4-Flash
$0.16/1M$0.33/1M
GLM-5-Turbo
$0.83/1M$3.67/1M
GLM-5.2
$1.00/1M$4.00/1M
gpt-oss-20b
$0.20/1M$0.28/1MContext: 125K
Llama-3.1-8B-Instruct
$0.10/1M$0.10/1MContext: 125K
MiniMax-M2.7
$0.35/1M$1.40/1M
Qwen2.5-7B-Instruct
$0.20/1M$0.20/1MContext: 16K
Qwen3-235B-A22B
$0.33/1M$1.33/1M
qwen3-coder-30b-a3b-instruct
$0.10/1M$0.30/1MContext: 32K

Vision

ModelInputOutputNotes
Gemma-4-31B-IT
$0.50/1M$0.50/1MContext: 32K
Kimi-K2.6
$1.08/1M$4.50/1M
qwen3-omni-30b-a3b-instruct
$0.40/1M$0.80/1M
qwen3-vl-8b-instruct
$0.15/1M$0.50/1MContext: 32K
Qwen3.5-27B
$0.30/1M$0.60/1MContext: 32K
Qwen3.5-35B-A3B
$0.40/1M$0.40/1M
Qwen3.6-27B
$0.30/1M$0.60/1MContext: 32K
Qwen3.6-35B-A3B
$0.40/1M$0.40/1MContext: 32K

Embedding

ModelInputOutputNotes
Jina-Embeddings-V3
$0.02/1M
Jina-Embeddings-V4
$0.12/1M
qwen3-embedding-0.6b
$0.12/1M
qwen3-embedding-4b
$0.12/1M
qwen3-embedding-8b
$0.12/1M

Reranker

ModelInputOutputNotes
BGE-Reranker-V2-M3
$0.03/1M

Image

ModelInputOutputNotes
FLUX.2 Klein
flux2-klein
$20.00/1M out tokTokens / item: 1,000
Qwen-Image
$30.00/1M out tokTokens / item: 1,000
Z-Image-Turbo
$10.00/1M out tokTokens / item: 1,000

Speech

ModelInputOutputNotes
Chatterbox
$2.00/1M out tokTokens / sec audio: 100
Fun-ASR-Nano
$0.05/1M in tokTokens / sec audio: 1,000
Kokoro-82M
$1.00/1M out tokTokens / sec audio: 100
Qwen3-ASR-1.7B
qwen3-asr-1-7b
$0.05/1M in tokTokens / sec audio: 1,000
Qwen3-TTS
$2.00/1M out tokTokens / sec audio: 100
Whisper-Large-V3-Turbo
$0.10/1M in tokTokens / sec audio: 1,000

Video Generation

Billed on actual tokens used, at a rate set by output resolution and whether you supply a reference video. Higher resolutions bill at a lower per-token rate but consume substantially more tokens per second of video, so a 4K clip still costs more than the same clip at 720p.

EcoLink-Video-Gen-2.0

ecolink-video-gen-2.0
ResolutionText / image inputWith reference video
480p / 720p$7.14/1M$4.39/1M
1080p$7.85/1M$4.79/1M
4K$4.08/1M$2.45/1M

GPU Compute

Pay per GPU-hour. Same rate for dedicated inference, workspace instances, and clusters. Billed per second of running time.

GPUVRAMOn-Demand
RTX Pro 600096 GB$1.98/GPU-hr

Storage

Persistent storage attached to your GPU instances and clusters. Cloud Drives are single-instance (ReadWriteOnce); Shared Filesystems mount across multiple instances (ReadWriteMany). Billed per second of attached time.

TypeSizeMonthly
Cloud Drive50 GB$5.00/mo
Cloud Drive100 GB$10.00/mo
Cloud Drive200 GB$20.00/mo
Cloud Drive300 GB$30.00/mo
Cloud Drive400 GB$40.00/mo
Cloud Drive500 GB$50.00/mo
Shared Filesystem50 GB$5.00/mo
Shared Filesystem100 GB$10.00/mo
Shared Filesystem200 GB$20.00/mo
Shared Filesystem300 GB$30.00/mo
Shared Filesystem400 GB$40.00/mo
Shared Filesystem500 GB$50.00/mo

$1 free credit on signup. No minimum commitment.