Wafer
Agent-tuned inference stacks that run open models faster on the same weights.
- Founded
- 2025
- Example models
- Qwen 3.5 397B Turbo, GLM 5.1 Turbo
By The Subconscious Team · Updated
What is Wafer?
Wafer builds AI agents that act as GPU performance engineers, then sells inference on the stacks those agents tune. The company came out of Y Combinator's Summer 2025 batch as a "Cursor for CUDA" that turned slow PyTorch into custom kernels. Founders Emilio Andere and Steven Arellano are based in San Francisco. Its agents profile a workload, generate candidate configs across batching, decoding, quantization, engines, kernels and hardware, measure each one and deploy the winner.
Wafer calls the result continual inference. A dedicated deployment gets built around a customer's model, traffic shape and SLO, and the agent keeps re-tuning as load, models or hardware change, on NVIDIA or AMD. The serverless side, Wafer Pass, is a flat-rate subscription from $10 a week that covers every hosted model and drops into Claude Code, Cline, OpenHands and similar harnesses. Wafer reports its tuned Qwen 3.5 397B running 2.8x faster than stock SGLang, with GLM 5.1 and DeepSeek V4 Pro each 2x faster than a vLLM baseline.
Wafer pros, cons and use cases
Upsides
- Faster open models on the same weights, since most hosts run stock vLLM or SGLang.
- Cheap flat-rate access for agentic coding tools.
- Works across NVIDIA and AMD, which helps teams hedge GPU supply.
Core use cases
- Coding agents that want big open models at interactive speed.
- Dedicated endpoints for teams with a strict latency SLO and no in-house kernel engineers.
Downsides
- Very young company with a small hosted catalog.
- Speedup claims are self-reported against stock baselines, so compare against tuned hosts like Fireworks before buying.
Wafer alternatives compared
Pick any row for the full head-to-head.
| Provider | Model access | Flagship models | Speed | Price | Customization | Deployment | Long context | 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 | |
 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 |
 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 | 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 |
 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 Wafer?
Wafer builds AI agents that act as GPU performance engineers, then sells inference on the stacks those agents tune. The company came out of Y Combinator's Summer 2025 batch as a "Cursor for CUDA" that turned slow PyTorch into custom kernels. Founders Emilio Andere and Steven Arellano are based in San Francisco. Its agents profile a workload, generate candidate configs across batching, decoding, quantization, engines, kernels and hardware, measure each one and deploy the winner.
What is Wafer best for?
Coding agents that want big open models at interactive speed; Dedicated endpoints for teams with a strict latency SLO and no in-house kernel engineers.
How much does Wafer cost?
Wafer pricing at a glance: Wafer Pass from $10 a week. Rates change often, so check Wafer's pricing page before committing.
How much context does Wafer support?
Wafer's long-context support: Varies by model.
What are the downsides of Wafer?
Very young company with a small hosted catalog; Speedup claims are self-reported against stock baselines, so compare against tuned hosts like Fireworks before buying.
What are the best alternatives to Wafer?
Common alternatives include Subconscious, OpenAI, Anthropic, Google Vertex AI, Amazon Bedrock. Each has a head-to-head comparison with Wafer on this site.
Sources: Wafer, Wafer company info, Wafer on Y Combinator. Pricing and model lineups change often; figures are a snapshot.