AI inference.Up to 97% below OpenRouter.

Lower prices, one API, no subscriptions.

Max discount
97%
Models
294
Model labs
55
Routing overhead
<100ms
ModelFluence
MiniMax M2.7MiniMaxin$0.019out$0.056−91%
GPT-5.6 SolOpenAIin$0.107out$0.534−97%
Claude Sonnet 5.5Anthropicin$1.07out$5.36−46%

Pay less for the models you already run.

Compare our quoted prices with OpenRouter's current featured prices. Providers, features and retention can differ; supplier bills can adjust the final charge.

RetentionZDR

Zero data retention. Only providers that keep no copy of your prompts or replies, and never train on them. Send zdr: true on a request to require it. That pool is smaller than the full one, so these prices are usually higher than standard.

Read the docs
Prices for requests that send zdr: true
ModelOpenRouterFluence
GPT-5.6 Solopenai/gpt-5.6-sol−97%in$4.00out$20.00Above 272Kin$8.00out$30.00in$0.107out$0.534Above 272Kin$4.44out$16.67
MiniMax M2.7minimax/minimax-m2.7−91%in$0.21out$0.84in$0.019out$0.056
GLM 5.3 Flashz-ai/glm-5.3-flash−87%in$0.15out$0.50in$0.019out$0.056
DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-0731−71%in$0.065out$0.30in$0.019out$0.056
Kimi K2.7 Codemoonshotai/kimi-k2.7-code−56%in$0.60out$3.50in$0.259out$1.09
GPT-6 Solopenai/gpt-6-sol−55%in$2.00out$10.00Above 272Kin$4.00out$15.00in$0.889out$4.44Above 272Kin$2.45out$9.21
MiMo-V2.6-Flashxiaomi/mimo-v2.6-flash−55%in$0.14out$0.28in$0.062out$0.124
Grok 4.7x-ai/grok-4.7−55%in$2.00out$6.00Above 200Kin$4.00out$12.00in$0.90out$2.70Above 200Kin$1.80out$5.40
Nemotron 3 Ultranvidia/nemotron-3-ultra-550b-a55b−55%in$0.50out$2.20in$0.222out$0.978
Qwen2.5 72B Instructqwen/qwen-2.5-72b-instruct−55%in$0.36out$0.40in$0.16out$0.178
Gemini 4 Argongoogle/gemini-4-argon−55%in$2.00out$10.00in$0.889out$4.44
Phi 4microsoft/phi-4−55%in$0.07out$0.14in$0.031out$0.062
Llama 3.2 3B Instructmeta-llama/llama-3.2-3b-instruct−53%in$0.051out$0.335in$0.023out$0.023
Qwen3 235B A22Bqwen/qwen3-235b-a22b−53%in$0.455out$1.82in$0.211out$0.633
Hy4tencent/hy4−52%in$0.417out$1.25in$0.20out$0.60
Hy4 flashtencent/hy4-flash−49%in$0.035out$0.141in$0.018out$0.07
MiniMax M3.1 Flashminimax/minimax-m3.1-flash−49%in$0.15out$0.60in$0.075out$0.30
Claude Sonnet 5.5anthropic/claude-sonnet-5.5−46%in$2.00out$10.00in$1.07out$5.36
MiMo-V2.6-Pro-UltraSpeedxiaomi/mimo-v2.6-pro-ultraspeed−44%in$4.35out$8.70in$2.42out$4.83
Mercury 3inception/mercury-3−44%in$0.10out$0.35in$0.056out$0.194
Claude Opus 5.5anthropic/claude-opus-5.5−44%in$4.00out$20.00in$2.22out$11.08
Claude Fable 5.2anthropic/claude-fable-5.2−44%in$8.00out$40.00in$4.43out$22.17
Mistral Large 4mistralai/mistral-large-4-0−44%in$0.70out$2.10in$0.389out$1.17
Seed 2.1 Turbobytedance-seed/seed-2-1-turbo−44%in$0.50out$2.50in$0.278out$1.39
Nova Micro 1.0amazon/nova-micro-v1−44%in$0.035out$0.14in$0.019out$0.078
Command R (08-2024)cohere/command-r-08-2024−44%in$0.15out$0.60in$0.083out$0.333
GPT-6.2 Astraopenai/gpt-6.2-astra−41%in$8.00out$40.00Above 272Kin$16.00out$60.00in$4.71out$23.56Above 272Kin$5.78out$28.89
Qwen2.5 Coder 32B Instructqwen/qwen-2.5-coder-32b-instruct−38%in$0.66out$1.00in$0.405out$0.405
Particle-1particle-ai/particle-1−36%in$0.06out$0.50in$0.038out$0.316
DeepSeek V4.1 Flash 1017deepseek/deepseek-v4.1-flash-1017−36%in$0.30out$1.20in$0.19out$0.607
Step 5 Previewstepfun/step-5-preview−27%in$1.00out$2.70in$0.722out$1.95
Fugu Ultrasakana/fugu-ultra−27%in$5.00out$30.00Above 272Kin$10.00out$45.00in$3.61out$21.67Above 272Kin$7.22out$32.50
Inkling Smallthinkingmachines/inkling-small−27%in$0.45out$1.20in$0.217out$0.867
Ling 3.0 Flash Santeinclusionai/ling-3.0-flash-sante−27%in$0.042out$0.123in$0.03out$0.089
Command Acohere/command-a−27%in$2.50out$10.00in$1.81out$7.22
Schematron V2 Turboinference-net/schematron-v2-turbo−27%in$0.03out$0.15in$0.022out$0.108
Morph V3 Largemorph/morph-v3-large−27%in$0.90out$1.90in$0.65out$1.37
Qwen4 Maxqwen/qwen4-max−23%in$1.43out$4.28in$1.08out$3.25
Llama 3.3 Euryale 70Bsao10k/l3.3-euryale-70b−15%in$0.65out$0.75in$0.548out$0.548
GLM 5.3 FlashX Legalz-ai/glm-5.3-flashx-legal−14%in$0.37out$1.25in$0.317out$1.07
Muse Embermeta/muse-ember−13%in$0.10out$0.50in$0.087out$0.434
LFM2.5-24B-A2Bliquid/lfm-2.5-24b-a2b−13%in$0.05out$0.70in$0.043out$0.606
Glimpseelorian/glimpse−12%in$0.60out$3.00in$0.523out$2.61
WizardLM-2 8x22Bmicrosoft/wizardlm-2-8x22b−11%in$0.62out$0.62in$0.548out$0.548
Fugu Ultra v2sakana/fugu-ultra-v2−7%in$5.00out$30.00in$4.63out$27.76
Gemini 4 Neongoogle/gemini-4-neon−6%in$3.00out$15.00in$2.79out$13.95
Inkling 2 Smallthinkingmachines/inkling-2-small−5%in$0.30out$1.00in$0.283out$0.945
Ember-1fireworks/ember-1−5%in$3.00out$15.00in$2.83out$14.17
Ling 3.0 Flash VLinclusionai/ling-3.0-flash-vl−5%in$0.06out$0.18in$0.057out$0.17
Nemotron 3.5 Super VLnvidia/nemotron-3.5-super-vl−1%in$0.15out$0.50in$0.148out$0.371

Security and routing without changing your stack.

Auto routing

Auto serves the first model on your list within your price ceiling, then your default model.

Sensitive data redaction

Redact credentials and personal data before dispatch, or block the request.

Prototype

Tool-call protection

Block exfiltration, destructive actions, and instruction injection before delivery.

Scoped API keys

Set scopes, expiry, allowlists, rate limits, and budgets per key.

Zero data retention

Use verified zero-retention routes with caching and temporary uploads disabled.

Connect with your base URL and API key.

client = OpenAI(base_url="https://api.fluence.cloud/v1", api_key=os.environ["FLUENCE_API_KEY"])
  1. 1

    Point your client at Fluence

    Set the base URL to api.fluence.cloud/v1 in any OpenAI-compatible SDK, or in curl.

  2. 2

    Paste one key

    One key covers all 294 models, and you call each one by the id shown in the list.

  3. 3

    Pay per token

    You add funds from $5 and pay per token, with no monthly plan. Each request shows what it cost.

Import to your coding tool.

The tools you already use, connected to Fluence. Copy a setup prompt and let your agent handle the configuration.

  • Hermes Agent
  • Claude Code
  • Kilo Code
  • Cline
  • pi
  • omp
  • Codex
  • OpenCode
  • OpenHands
  • OpenClaw
  • DeepSeek Harness
  • Cursor

The discount comes from providers with spare capacity competing for your requests.

Three glass GPU units in a rack, the front one lit with the Fluence gradient, the two behind it dark

Spare capacity serves the same models

Idle GPUs host the open weights; providers with spare API capacity carry GPT, Claude and Gemini. All of it priced below OpenRouter.

Set routing per API key

A routing profile orders the models Auto may use, caps token prices, and picks cheaper or faster providers. Your privacy settings apply to every request.

OpenRouter's rate is the ceiling

With no better offer, you pay OpenRouter's public rate and nothing above it.

We pay for idle GPUs and spare API capacity.

You serve open models per request and keep your own hardware, accounts and credentials.

Apply as a provider

Fluence Cloud

Cloud VPS for AI from $2.54 a month.

Host your agents, APIs and workers on Fluence Cloud. It also rents dedicated VDS, block storage and on-demand GPUs.

Explore Fluence Cloud

from$2.54/mo2 vCPU · 2 GB RAM · 25 GB

Questions

Check model compatibility, pricing and data retention before you connect.

Sign up
Is it the same model?

Yes. Each row names the vendor's own model. Open-weight models run as the exact Hugging Face checkpoint; closed models go through the vendor's API, served by a provider with spare capacity.

Which models are on the list?

294 models with a public rate on OpenRouter, from OpenAI, Qwen, Google, Z.ai, Anthropic, DeepSeek, Mistral, Meta, Moonshot AI, MiniMax, xAI, AionLabs, inclusionAI, NVIDIA, Xiaomi, Amazon, Cohere, Sakana, Tencent, ByteDance Seed, LiquidAI, StepFun, Thinking Machines, IBM, Inception, Inference.net, Moondream, Morph, Perceptron, PrismML, Upstage, Baidu, Elorian, Fireworks, Magnum v4 72B, Meituan, Microsoft, Mistral Large, Mistral Large 2407, MythoMax 13B, Nous, Pareto 26.10, Pareto 26.9, Particle AI, Perplexity, Qwen2.5 72B Instruct, Qwen2.5 Coder 32B Instruct, Reflection, Reka Edge, Reka Flash 3, Ricursive, Sao10K, TypeSafe, WizardLM-2 8x22B and Writer.

What changes in my code?

You change two values: the base URL (api.fluence.cloud/v1) and your API key. Requests and responses follow the OpenAI format, so your SDKs, agents and tools keep working.

How are prices set?

Provider offers have their own rates. Your routing profile ranks them by price or by measured speed, within your privacy settings. You pay the provider's verified bill plus the model markup, with price matching when it covers supplier cost. For a delayed supplier bill, quoted rates apply first; after three unsuccessful checks, the charge moves to the captured full list price for actual usage. That charge stays provisional while Fluence checks for the bill for 30 days. A later bill corrects the charge with a debit or credit in your balance history. Some models charge more for long prompts; the price table marks their thresholds. A valid actual bill can exceed the quote or reference rate.

What do you keep from my requests?

We store the model, the token counts, the cost and the time, and none of the prompt or completion text. Pick a zero data retention route when your policy requires it.

When do I get access?

You get access when you sign up. Add credits from $5 and create an API key in the console.

Get your API key

Sign up with your email, add credits from $5 and send your first request. You pay per token, with no subscription.

Sign up with your email

No card needed to sign up. We email you a 6-digit code.