Inference.net
Cheap batch inference on spare GPU capacity, plus a path from traces to custom models.
- Founded
- 2023
- Example models
- open catalog models plus customer fine-tunes served on dedicated GPUs
By The Subconscious Team · Updated
What is Inference.net?
Inference.net started as a buyer of last resort for idle GPU time. Its scheduler aggregates small unused chunks of capacity across data centers and runs models on them, and it passes the steep discounts it gets from those data centers on to customers. That origin still shows in its OpenAI-compatible Batch API, which takes up to 1M requests per file with completion windows from 24 hours to 7 days and far higher headroom than synchronous limits.
The company now pitches a full loop for teams that want to leave closed APIs. Inference Gateway routes traffic to open, closed or custom models under one key, captures every request, and turns that traffic into eval and training datasets. From there, Inference.net fine-tunes a task-specific model and deploys it on a dedicated GPU with a 99.99% uptime target. A tracing product with an open-source optimizer called Halo reads agent traces and suggests fixes to prompts, tools and harness. Customers named on the site include GravityAds and Cal AI.
Inference.net pros, cons and use cases
Upsides
- Cheap bulk inference built on otherwise wasted GPU capacity.
- One workflow from production traces to a distilled custom model.
Core use cases
- Large offline jobs like extraction, classification and synthetic data.
- Replacing a narrow GPT-class workload with a smaller fine-tuned model to cut cost and latency.
Downsides
- Fragmented spare capacity suits batch work better than strict real-time SLAs.
- Few independent benchmarks or public pricing comparisons, so buyers depend on the vendor's numbers.
Inference.net alternatives compared
Pick any row for the full head-to-head.
| Provider | Model access | Flagship models | Speed | Price | Customization | Deployment | Long context | Compare |
|---|---|---|---|---|---|---|---|---|
| Inference.net | Open, closed and custom | Customer fine-tunes | Batch windows of 24h to 7 days | Discounted spare GPU capacity | Distill traces into custom models | Batch API, gateway, dedicated GPUs | Varies by model | |
 Subconscious | Open weights | GLM 5.3, DeepSeek V4.1 Flash | 2x faster task completion | 50–80% lower cost; billed on processed tokens | Marathon post-trained variants | Managed API, dedicated, on-prem | 5M+ effective context | Compare |
 OpenAI | Closed, plus open gpt-oss | GPT-6 Astra, GPT-5.6 Sol, Terra, Luna | Fast mode: up to 2.5x at 2x price | $0.20–$10 in, $1.20–$50 out per 1M | N/A | API, Azure OpenAI, Bedrock | 1.05M; 2x input past 272K | Compare |
 Anthropic | Closed | Claude Fable 5.1, Opus, Sonnet, Haiku 4.5 | Fable is the slowest tier | $1–$10 in, $5–$50 out per 1M | N/A | API, Bedrock, Vertex AI, Microsoft Foundry | 1M, no surcharge past 200K | Compare |
 Google Vertex AI | Closed and open, 200+ models | Gemini 3.8 Flash, Claude, Gemma | Flash tier built for low latency | Gemini 3.8 Flash $0.75 in, $3.75 out | Custom training on GPUs or TPUs | Managed on Google Cloud | 1M on Gemini 3.8 Flash | Compare |
 Amazon Bedrock | Closed and open, 100+ models | Claude, GPT-6 Astra, Nova, DeepSeek | Latency-optimized option on some models | ~20–35% above direct; Claude at parity | Fine-tuning, Custom Model Import | Managed on AWS, AgentCore | Varies by model | Compare |
 Together AI | Open weights | Kimi K3, DeepSeek V4, GLM 5.2, Qwen 3.8 | 0.99s TTFT on DeepSeek V4 Pro | Parity with Fireworks and Baseten | LoRA and full SFT; RL in beta | Serverless, dedicated, GPU clusters | 512K on DeepSeek V4 Pro | Compare |
 Fireworks AI | Open weights | DeepSeek V4 Pro, Kimi K3 | 167–174 tok/s on DeepSeek V4 Pro | Fine-tunes served at base price | SFT, DPO, RFT; Training API | Serverless, dedicated GPUs | Full 1M on DeepSeek V4 Pro | Compare |
 Baseten | Open weights, 13 curated | GLM 5.2, DeepSeek V4, Kimi K3, gpt-oss 120B | 0.49s TTFT, lowest measured | H100 about $6.50/hr dedicated | Deploy any model with Truss | Model APIs, dedicated, self-host | Varies by model | Compare |
 Groq | Open weights | GPT-OSS 120B, Qwen 3.6 27B | 500–1,000 tok/s | Near the floor on small models | No fine-tuned model hosting | GroqCloud API | Around 131K max | Compare |
 Cerebras | Open weights | GPT-OSS 120B, Gemma 4 31B | ~3,000 tok/s on GPT-OSS 120B | $0.35 in, $0.75 out (GPT-OSS 120B) | Unknown | Shared API, dedicated, partners | Unknown | Compare |
 DeepInfra | Open weights | DeepSeek V4 Flash, Llama 3.1 8B | ~33 tok/s on DeepSeek V4 Pro (FP4) | From $0.02 per 1M | No managed fine-tuning | Shared API, no contracts | 66K on FP4 DeepSeek V4 Pro | Compare |
 Modal | Bring your own weights | None hosted | ~1s container boot | Per second; H100 $3.95/hr list | Run any training code | Serverless GPU containers | Depends on the model you deploy | Compare |
 xAI | Closed | Grok 4.6, Grok 4.20, grok-build | ~54 tok/s on Grok 4.6 | $2 in, $6 out (Grok 4.6); 2x past 200K | Unknown | First-party API | 500K (4.6), 1M (4.20, 4.3) | Compare |
 DeepSeek | Open weights (MIT) | DeepSeek V4.1 Flash, V4 Pro | ~35 tok/s on V4 Pro | Off-peak hours at half price | Open weights to fine-tune | First-party API, Hugging Face weights | 1M, 384K max output | Compare |
 Moonshot AI | Open weights, custom license | Kimi K3, Kimi K2.6 | ~33 tok/s on Kimi K3 | $3 in, $15 out (Kimi K3) | Open weights to fine-tune | API, Kimi Code, OpenRouter | 1M | Compare |
 Z.ai | Open weights (MIT) | GLM-5.3, GLM-5.3-Flash | ~80 tok/s on GLM-5.3 | $1.40 in, $4.40 out (GLM-5.3); free Flash tier | Open weights, no license limits | API, GLM Coding Plan | 1M (GLM-5.3) | Compare |
 Alibaba Cloud | Closed Max; open smaller Qwen | Qwen 3.8-Max, Qwen 3.7-Max | ~40 tok/s on Qwen 3.8-Max | $2 in, $6 out international | No fine-tuning on Max | Model Studio on Alibaba Cloud | 1M (Qwen 3.8-Max) | Compare |
 Meta | Closed API; open Muse Glimmer | Muse Spark 1.3, Muse Glimmer | ~145–233 tok/s on Muse Spark 1.3 | $1.25 in, $4.25 out; Contributor tier cheaper | Open Muse Glimmer weights to fine-tune | Meta Model API (preview) | 1M | Compare |
 SambaNova | Open weights | MiniMax M2.7, GPT-OSS 120B, DeepSeek | ~820 tok/s on MiniMax M2.7 (SN50) | $0.22 in, $0.59 out (GPT-OSS 120B) | Unknown | SambaCloud, racks for neoclouds | Up to 192K (MiniMax M2.7) | Compare |
 Nebius | Open weights, 60+ models | DeepSeek, Qwen, GLM, Kimi, GPT-OSS | Among top hosts on throughput | From $0.06 per 1M input | Serve uploaded fine-tunes | Token Factory, dedicated, raw GPUs | Varies by model | Compare |
 fal | Hosted media models | FLUX, Kling, Seedream | Cold starts on less popular endpoints | Per image, per video second, GPU time | LoRA training endpoints | Hosted API, serverless GPUs | Not applicable | Compare |
 Novita AI | Open weights | DeepSeek V4 Pro, Gemma 4 | ~36 tok/s on DeepSeek V4 Pro | From $0.02 per 1M; batch 50% off | Hot-swappable LoRA adapters | Serverless, GPU cloud, dedicated | Full 1M on DeepSeek V4 Pro | Compare |
 Parasail | Any Hugging Face model | GTE-Qwen2, Qwen3-VL-8B-Instruct | 600ms p99 real-time budget | Per-parameter rates; batch 50% off | Private Hugging Face repos | Serverless, elastic, dedicated, batch | Varies by model | Compare |
 GMI Cloud | Open and third-party models | GLM-4.7-Flash, Google Veo | Near bare-metal performance | $0.07 in, $0.40 out (GLM-4.7-Flash) | Unknown | Shared, autoscaling, reserved GPUs | Varies by model | Compare |
 Sail Research | Open weights | Kimi K2.6, GLM-5, GPT-OSS 120B | Minutes per turn by design | 30–80% off by completion window | Customer LoRA fine-tunes | API plus Sailboxes | Varies by model | Compare |
 Morph | Specialist models | morph-v3-fast, morph-v3-large | 10,500+ tok/s Fast Apply | ~40% fewer tokens than full rewrites | Fine-tuning offered | OpenAI-compatible API | Unknown | Compare |
 Relace | Specialist models | relace-apply-3, agentic search | ~10,000 tok/s apply | 3x+ cheaper than full rewrites | Unknown | Hosted API or self-hosted | 128K max | Compare |
 TypeSafe AI | Decision models | Jev, jev-1.13 | ~100ms per call | A fraction of an LLM call | Unknown | Early-access API | Unknown | Compare |
 StepFun | Open (Apache 2.0) and API models | Step 3.7 Flash, Step3 | ~128 tok/s on Step 3.7 Flash | $0.20 in, $1.15 out (Step 3.7 Flash) | Open weights to fine-tune | First-party API, OpenRouter | 256K | Compare |
 Runware | Hosted media models | Seedance 2.5, Qwen-Image-3.0 | Unknown | Images from fractions of a cent | Fine-tuned diffusion checkpoints | Unified API, raw GPUs | Not applicable | Compare |
 StreamLake | Proprietary coding models | KAT-Coder-Pro V2.5, KAT-Coder-Air | Unknown | Per token or KwaiKAT Coding Plan | Unknown | MaaS API, bare metal | Unknown | Compare |
 Wafer | Open weights | Qwen 3.5 397B Turbo, GLM 5.1 Turbo | 2–2.8x vs stock vLLM or SGLang | Wafer Pass from $10 a week | Agent-tuned dedicated deployments | Serverless pass, dedicated | Varies by model | Compare |
 RunInfra | Open weights | Nemotron 3.5 Lightning 30B, Qwen 3.8 27B | Cold starts under 2s | Coding plans from $10 a month | Uploads up to 50 GB; auto-quantization | Model APIs, agent-built endpoints | Varies by model | Compare |
 Particle.AI | Open weights | DeepSeek V4.1 Flash, GLM 5.3 Flash | ~157 tok/s on DeepSeek V4.1 Flash | $0.10 in, $0.40 out (GLM 5.3 Flash) | Unknown | Via Vercel AI Gateway | 1M | Compare |
Frequently asked questions
What is Inference.net?
Inference.net started as a buyer of last resort for idle GPU time. Its scheduler aggregates small unused chunks of capacity across data centers and runs models on them, and it passes the steep discounts it gets from those data centers on to customers. That origin still shows in its OpenAI-compatible Batch API, which takes up to 1M requests per file with completion windows from 24 hours to 7 days and far higher headroom than synchronous limits.
What is Inference.net best for?
Large offline jobs like extraction, classification and synthetic data; Replacing a narrow GPT-class workload with a smaller fine-tuned model to cut cost and latency.
How much does Inference.net cost?
Inference.net pricing at a glance: Discounted spare GPU capacity. Rates change often, so check Inference.net's pricing page before committing.
How much context does Inference.net support?
Inference.net's long-context support: Varies by model.
What are the downsides of Inference.net?
Fragmented spare capacity suits batch work better than strict real-time SLAs; Few independent benchmarks or public pricing comparisons, so buyers depend on the vendor's numbers.
What are the best alternatives to Inference.net?
Common alternatives include Subconscious, OpenAI, Anthropic, Google Vertex AI, Amazon Bedrock. Each has a head-to-head comparison with Inference.net on this site.
Sources: Inference.net, Inference.net company, Batch API docs. Pricing and model lineups change often; figures are a snapshot.