Auto routing
Auto serves the first model on your list within your price ceiling, then your default model.
Lower prices, one API, no subscriptions.
| Model | OpenRouter | Fluence | Save |
|---|---|---|---|
| MiniMax M2.7MiniMax | in$0.21out$0.84 | in$0.019out$0.056−91% | −91% |
| GPT-5.6 SolOpenAI | in$4.00out$20.00 | in$0.107out$0.534−97% | −97% |
| Claude Sonnet 5.5Anthropic | in$2.00out$10.00 | in$1.07out$5.36−46% | −46% |
Compare our quoted prices with OpenRouter's current featured prices. Providers, features and retention can differ; supplier bills can adjust the final charge.
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| Model | OpenRouter | Fluence | Difference | Context |
|---|---|---|---|---|
| GPT-5.6 Solopenai/gpt-5.6-sol−97% | in$4.00out$20.00in$8.00out$30.00 | in$0.107out$0.534in$4.44out$16.67 | −97% | 1M |
| MiniMax M2.7minimax/minimax-m2.7−91% | in$0.21out$0.84 | in$0.019out$0.056 | −91% | 180K |
| GLM 5.3 Flashz-ai/glm-5.3-flash−87% | in$0.15out$0.50 | in$0.019out$0.056 | −87% | 390K |
| DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-0731−71% | in$0.065out$0.30 | in$0.019out$0.056 | −71% | 380K |
| Kimi K2.7 Codemoonshotai/kimi-k2.7-code−56% | in$0.60out$3.50 | in$0.259out$1.09 | −56% | 262K |
| GPT-6 Solopenai/gpt-6-sol−55% | in$2.00out$10.00in$4.00out$15.00 | in$0.889out$4.44in$2.45out$9.21 | −55% | 1M |
| MiMo-V2.6-Flashxiaomi/mimo-v2.6-flash−55% | in$0.14out$0.28 | in$0.062out$0.124 | −55% | 1M |
| Grok 4.7x-ai/grok-4.7−55% | in$2.00out$6.00in$4.00out$12.00 | in$0.90out$2.70in$1.80out$5.40 | −55% | 500K |
| Nemotron 3 Ultranvidia/nemotron-3-ultra-550b-a55b−55% | in$0.50out$2.20 | in$0.222out$0.978 | −55% | 262K |
| Qwen2.5 72B Instructqwen/qwen-2.5-72b-instruct−55% | in$0.36out$0.40 | in$0.16out$0.178 | −55% | 33K |
| Gemini 4 Argongoogle/gemini-4-argon−55% | in$2.00out$10.00 | in$0.889out$4.44 | −55% | 33K |
| Phi 4microsoft/phi-4−55% | in$0.07out$0.14 | in$0.031out$0.062 | −55% | 16K |
| Llama 3.2 3B Instructmeta-llama/llama-3.2-3b-instruct−53% | in$0.051out$0.335 | in$0.023out$0.023 | −53% | 131K |
| Qwen3 235B A22Bqwen/qwen3-235b-a22b−53% | in$0.455out$1.82 | in$0.211out$0.633 | −53% | 41K |
| Hy4tencent/hy4−52% | in$0.417out$1.25 | in$0.20out$0.60 | −52% | 1M |
| Hy4 flashtencent/hy4-flash−49% | in$0.035out$0.141 | in$0.018out$0.07 | −49% | 1M |
| MiniMax M3.1 Flashminimax/minimax-m3.1-flash−49% | in$0.15out$0.60 | in$0.075out$0.30 | −49% | 1M |
| Claude Sonnet 5.5anthropic/claude-sonnet-5.5−46% | in$2.00out$10.00 | in$1.07out$5.36 | −46% | 1M |
| MiMo-V2.6-Pro-UltraSpeedxiaomi/mimo-v2.6-pro-ultraspeed−44% | in$4.35out$8.70 | in$2.42out$4.83 | −44% | 1M |
| Mercury 3inception/mercury-3−44% | in$0.10out$0.35 | in$0.056out$0.194 | −44% | 1M |
| Claude Opus 5.5anthropic/claude-opus-5.5−44% | in$4.00out$20.00 | in$2.22out$11.08 | −44% | 1M |
| Claude Fable 5.2anthropic/claude-fable-5.2−44% | in$8.00out$40.00 | in$4.43out$22.17 | −44% | 1M |
| Mistral Large 4mistralai/mistral-large-4-0−44% | in$0.70out$2.10 | in$0.389out$1.17 | −44% | 524K |
| Seed 2.1 Turbobytedance-seed/seed-2-1-turbo−44% | in$0.50out$2.50 | in$0.278out$1.39 | −44% | 262K |
| Nova Micro 1.0amazon/nova-micro-v1−44% | in$0.035out$0.14 | in$0.019out$0.078 | −44% | 128K |
| Command R (08-2024)cohere/command-r-08-2024−44% | in$0.15out$0.60 | in$0.083out$0.333 | −44% | 128K |
| GPT-6.2 Astraopenai/gpt-6.2-astra−41% | in$8.00out$40.00in$16.00out$60.00 | in$4.71out$23.56in$5.78out$28.89 | −41% | 1M |
| Qwen2.5 Coder 32B Instructqwen/qwen-2.5-coder-32b-instruct−38% | in$0.66out$1.00 | in$0.405out$0.405 | −38% | 32K |
| Particle-1particle-ai/particle-1−36% | in$0.06out$0.50 | in$0.038out$0.316 | −36% | 1M |
| DeepSeek V4.1 Flash 1017deepseek/deepseek-v4.1-flash-1017−36% | in$0.30out$1.20 | in$0.19out$0.607 | −36% | 1M |
| Step 5 Previewstepfun/step-5-preview−27% | in$1.00out$2.70 | in$0.722out$1.95 | −27% | 1M |
| Fugu Ultrasakana/fugu-ultra−27% | in$5.00out$30.00in$10.00out$45.00 | in$3.61out$21.67in$7.22out$32.50 | −27% | 1M |
| Inkling Smallthinkingmachines/inkling-small−27% | in$0.45out$1.20 | in$0.217out$0.867 | −27% | 524K |
| Ling 3.0 Flash Santeinclusionai/ling-3.0-flash-sante−27% | in$0.042out$0.123 | in$0.03out$0.089 | −27% | 256K |
| Command Acohere/command-a−27% | in$2.50out$10.00 | in$1.81out$7.22 | −27% | 256K |
| Schematron V2 Turboinference-net/schematron-v2-turbo−27% | in$0.03out$0.15 | in$0.022out$0.108 | −27% | 128K |
| Morph V3 Largemorph/morph-v3-large−27% | in$0.90out$1.90 | in$0.65out$1.37 | −27% | 82K |
| Qwen4 Maxqwen/qwen4-max−23% | in$1.43out$4.28 | in$1.08out$3.25 | −23% | 1M |
| Llama 3.3 Euryale 70Bsao10k/l3.3-euryale-70b−15% | in$0.65out$0.75 | in$0.548out$0.548 | −15% | 20K |
| GLM 5.3 FlashX Legalz-ai/glm-5.3-flashx-legal−14% | in$0.37out$1.25 | in$0.317out$1.07 | −14% | 1M |
| Muse Embermeta/muse-ember−13% | in$0.10out$0.50 | in$0.087out$0.434 | −13% | 1M |
| LFM2.5-24B-A2Bliquid/lfm-2.5-24b-a2b−13% | in$0.05out$0.70 | in$0.043out$0.606 | −13% | 128K |
| Glimpseelorian/glimpse−12% | in$0.60out$3.00 | in$0.523out$2.61 | −12% | 262K |
| WizardLM-2 8x22Bmicrosoft/wizardlm-2-8x22b−11% | in$0.62out$0.62 | in$0.548out$0.548 | −11% | 66K |
| Fugu Ultra v2sakana/fugu-ultra-v2−7% | in$5.00out$30.00 | in$4.63out$27.76 | −7% | 272K |
| Gemini 4 Neongoogle/gemini-4-neon−6% | in$3.00out$15.00 | in$2.79out$13.95 | −6% | 1M |
| Inkling 2 Smallthinkingmachines/inkling-2-small−5% | in$0.30out$1.00 | in$0.283out$0.945 | −5% | 1M |
| Ember-1fireworks/ember-1−5% | in$3.00out$15.00 | in$2.83out$14.17 | −5% | 1M |
| Ling 3.0 Flash VLinclusionai/ling-3.0-flash-vl−5% | in$0.06out$0.18 | in$0.057out$0.17 | −5% | 131K |
| Nemotron 3.5 Super VLnvidia/nemotron-3.5-super-vl−1% | in$0.15out$0.50 | in$0.148out$0.371 | −1% | 262K |
Auto serves the first model on your list within your price ceiling, then your default model.
Redact credentials and personal data before dispatch, or block the request.
Block exfiltration, destructive actions, and instruction injection before delivery.
Set scopes, expiry, allowlists, rate limits, and budgets per key.
Use verified zero-retention routes with caching and temporary uploads disabled.
client = OpenAI(base_url="https://api.fluence.cloud/v1", api_key=os.environ["FLUENCE_API_KEY"])const client = new OpenAI({ baseURL: "https://api.fluence.cloud/v1", apiKey: process.env.FLUENCE_API_KEY });curl https://api.fluence.cloud/v1/chat/completions -H "Content-Type: application/json" -H "Authorization: Bearer $FLUENCE_API_KEY" \
-d '{"model": "deepseek/deepseek-v4-flash", "messages": [{"role": "user", "content": "Hi"}]}'Set the base URL to api.fluence.cloud/v1 in any OpenAI-compatible SDK, or in curl.
One key covers all 294 models, and you call each one by the id shown in the list.
You add funds from $5 and pay per token, with no monthly plan. Each request shows what it cost.
The tools you already use, connected to Fluence. Copy a setup prompt and let your agent handle the configuration.

Idle GPUs host the open weights; providers with spare API capacity carry GPT, Claude and Gemini. All of it priced below OpenRouter.
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.
With no better offer, you pay OpenRouter's public rate and nothing above it.
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.
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.
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.
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.
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.
You get access when you sign up. Add credits from $5 and create an API key in the console.


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