By Sagar Shankaran, Founder of CallSphere
Per-FLOP and per-token cost trends across NVIDIA H200/B200, AMD MI325X, and Google TPU v6 in 2026 — and what the curve says about 2027.
Key takeaways
Compute costs for AI workloads in 2026 are dropping fast for inference and roughly flat per-FLOP for training. The mix of available hardware has broadened: NVIDIA still dominates but AMD and Google have gained share. This piece walks through the 2026 numbers and where the curves are heading.
flowchart TB
NV[NVIDIA] --> H100[H100<br/>2022-2024 mainstream]
NV --> H200[H200<br/>2024-2026 mainstream]
NV --> B200[Blackwell B200<br/>2025-2026 frontier]
NV --> GB[GB200 NVL72<br/>rack-scale]
AMD[AMD] --> MI300[MI300X<br/>2024]
AMD --> MI325[MI325X<br/>2025]
AMD --> MI355[MI355X<br/>2026]
Goo[Google] --> TPU5[TPU v5p<br/>2024]
Goo --> TPU6[TPU v6 'Trillium'<br/>2025-2026]
For BF16/FP8 throughput per dollar, the rough 2026 picture (numbers approximate, vary by deal):
For FP4 training and inference (Blackwell native, MI355X native, TPU v6 partial), the per-FLOP cost is roughly 2-3x cheaper still.
Per-million-token inference cost for a 70B-class model in 2026:
The 2026 inference cost curve has dropped roughly 5-10x from 2024 levels for comparable quality. Training costs have dropped less — perhaps 2x for like-for-like compute.
flowchart LR
Param[Parameters] --> Mem[Memory required]
Mem -->|HBM3e is fast and expensive| Cost[Cost dominated by memory]
The dominant cost in 2026 inference is memory bandwidth, not raw compute. HBM3e capacity per GPU varies:
Hear it before you finish reading
Talk to a live CallSphere AI voice agent in your browser — 60 seconds, no signup.
Larger memory per GPU lets you fit larger models on fewer cards, dropping serving cost.
By 2026, data center power is the binding constraint for new AI capacity in many regions. A B200 rack runs at 120-140 kW; existing data centers were not built for this density. The capex shift toward purpose-built AI campuses (Microsoft, Meta, Amazon, OpenAI, x.AI) is partly a response.
This is a topic in itself; covered in the next article.
flowchart TD
Q1{New deployment?} -->|Yes| Q2
Q1 -->|No, existing H100 fleet| Keep[Keep until H100 depreciated]
Q2{Frontier training?} -->|Yes| BTPU[B200 or TPU v6]
Q2 -->|No, inference| Q3{Cost optimized?}
Q3 -->|Yes| MI[MI355X or hosted]
Q3 -->|No, lowest latency| B[B200]
The doubling cadence of AI compute capacity per dollar that drove 2022-2025 is showing signs of slowing as we approach physical limits. 2026-2028 will be a slower curve than 2022-2025.
For most teams, the action is straightforward:
For teams that own infrastructure: the 2024 H100s are still useful but the depreciation schedule should reflect that B200 / MI355X are 2-3x cheaper per equivalent throughput. New deployments should default to current generation.
Cost of Compute 2026: H200, B200, MI325X, and the TPU v6 Trendline is also a cost-per-conversation problem hiding in plain sight. Once you instrument tokens-in, tokens-out, tool calls, ASR seconds, and TTS seconds against booked-revenue per call, the right tradeoff between Realtime API and an async ASR + LLM + TTS pipeline becomes obvious — and it's almost never the same answer for healthcare as it is for salons.
Still reading? Stop comparing — try CallSphere live.
CallSphere ships complete AI voice agents per industry — 14 tools for healthcare, 10 agents for real estate, 4 specialists for salons. See how it actually handles a call before you book a demo.
The protocol layer determines what's possible: WebRTC for browser-side widgets, SIP trunks (Twilio, Telnyx) for PSTN voice, WebSockets for the Realtime API streaming session. Each has its own jitter buffer, its own ICE/STUN dance, and its own failure modes when a customer's corporate firewall is hostile.
Front-end is Next.js 15 + React 19 for the marketing surface and the in-app dashboards, with server components used heavily for the SEO-critical pages. Backend splits across FastAPI for the AI worker, NestJS + Prisma for the customer-facing API, and a thin Go gateway that does auth, rate limiting, and routing — letting each service scale on its own characteristics.
Datastores: Postgres as the source of truth (per-vertical schemas like healthcare_voice, realestate_voice), ChromaDB for RAG over support docs, Redis for ephemeral session state. Postgres RLS enforces tenant isolation at the row level so a misconfigured query can't leak across customers.
What's the right way to scope the proof-of-concept? Setup runs 3–5 business days, the trial is 14 days with no credit card, and pricing tiers are $149, $499, and $1,499 — so a vertical-specific pilot is a same-week decision, not a quarterly project. For a topic like "Cost of Compute 2026: H200, B200, MI325X, and the TPU v6 Trendline", that means you're not starting from scratch — you're configuring an agent template that's already been hardened across thousands of conversations.
How do you handle compliance and data isolation? Day one is integration mapping (scheduler, CRM, messaging) and prompt tuning against your top 20 real call transcripts. Day two through five is shadow-mode running, where the agent transcribes and recommends but a human still answers, so you can compare side-by-side. Go-live is the moment your eval pass-rate clears your internal bar.
When does it make sense to switch from a managed model to a self-hosted one? The honest answer: it scales until your tool catalog gets stale. The agent is only as good as the integrations it can actually call, so the operational discipline is keeping schemas, webhooks, and fallback paths green. The platform handles the rest — observability, retries, multi-region routing — without your team owning the GPU layer.
Want to see how this maps to your stack? Book a live walkthrough at calendly.com/sagar-callsphere/new-meeting, or try the vertical-specific demo at escalation.callsphere.tech. 14-day trial, no credit card, pilot live in 3–5 business days.
Written by
Sagar Shankaran· Founder, CallSphere
Sagar Shankaran is the founder of CallSphere, where he builds production AI voice and chat agents deployed across healthcare, hospitality, real estate, and home services. He writes about agentic AI, LLM engineering, and shipping voice agents that handle real calls in production.
See how AI voice agents work for your industry. Live demo available -- no signup required.
H100 spot at $1.49 vs on-demand at $2.49. The 40-65% savings are real, but interruption math and warmup tax change the answer for live voice. Here is when spot wins.
Serverless GPU at $0.59–$3.95 per hour looks tempting until you measure cold start. Here is the honest break-even for self-hosting voice TTS or STT vs paying Deepgram or ElevenLabs.
Ring attention enables million-token contexts by distributing attention across GPUs. The 2026 implementations and what they enable.
Beyond pundit takes — what the 2026 BLS occupational data actually shows about AI displacement, augmentation, and wage effects.
When custom CUDA via Triton beats stock PyTorch ops in 2026 — the patterns, the tooling, and what production teams have shipped.
Flash Attention 3 is the kernel behind nearly every fast 2026 LLM. How it works, what it changed, and what's next.
© 2026 CallSphere LLC. All rights reserved.
Watch how CallSphere handles real customer calls, schedules appointments, and processes payments — live.
Try Live DemoBook a DemoCalculate Your ROI