Pricing
Subscriptions buy a guaranteed share of a model. Pay-as-you-go credits fill the slack, and both run the same model at the same speed — service tiers change queue order, never tokens per second.
Subscriptions
Every context ceiling is the same model on the same hardware. What you choose is the longest context your subscription reserves — a longer ceiling costs more per share unit because it holds more of the card.
Qwen 3.8 27B
qwen3.8-27b
Qwen 3.8, 27 billion parameters, served with FP8 weights and an FP8 KV cache, with image input, streaming and tool calls. One model resident in memory; a subscription picks the context ceiling it is billed at, and nothing else changes between rungs.
Live capacity
Qwen 3.8 27B
Live numbers are unavailable this second. The commitment behind them does not move: committed shares stay at or under capacity as exact integer arithmetic, checked under a database lock on every checkout — which is why tiers here sell out instead of getting slower.
Beyond one full share. Max is the GPU load of one always-on agent. If you need several, or a pool nothing else runs on, we size it with you rather than from a table.
Talk to usPay as you go
Prepaid credits, priced per million tokens. Same model and the same tokens per second as a subscription — what differs is admission.
Pay-as-you-go is best-effort: it fills capacity that reserved tenants are not using, which is most of the time. Under contention a subscriber stays ahead of it — but only inside the share they bought. Past that, their traffic falls below every paying pay-as-you-go request, because the reservation is spent. Whoever ranks lower queues, and past your share you are best-effort like anyone else: we will queue you while there is room, but we cannot promise to serve work you have not reserved.
Credits run up to the widest context ceiling the model serves — one model id, no rung to name. A subscription reserves a ceiling: requests longer than your plan's ceiling are refused rather than run on someone else's reservation.
Qwen 3.8 27B
Priority
queue-jump under contention
- Input
- $0.80
- Cache write
- Free
- Cached read
- $0.10
- Output
- $6.00
per 1M tokens
Standard
the default
- Input
- $0.40
- Cache write
- Free
- Cached read
- $0.05
- Output
- $3.00
per 1M tokens
Flex
same model and speed; last in line
- Input
- $0.30
- Cache write
- Free
- Cached read
- $0.0375
- Output
- $2.25
per 1M tokens
Batch
async; completes within 24h or 7d
- Input
- $0.20
- Cache write
- Free
- Cached read
- $0.025
- Output
- $1.50
per 1M tokens
No context surcharge at launch.
Batch finishes inside the window you pick — 24 hours or 7 days, same price. We refuse work we cannot schedule in time rather than accept it and run late; anything still unfinished at the deadline expires and is not billed. Results stay available for 30 days after completion, or less if you ask. Files up to 512 MiB, batches up to 100,000 requests or 256 MiB; storage is included with every plan.
Credits are bought in packages starting at $5.00. Credits expire 12 months after purchase.
Questions
The ones we are asked before the page above has answered them. Anything else: sales@partitionlabs.ai.
Are the context ceilings different models or different pools?
Neither. Every context ceiling of a model is the same weights on the same hardware, behind one model id. The ceiling is the longest context your subscription reserves, and a longer one costs more per share unit because a request that long holds more of the card. A request longer than your plan's ceiling is refused (HTTP 400), not truncated and not billed. So pick the longest context your agent actually needs.
Do service tiers change speed?
No. Every tier runs the same model at the same tokens per second; a tier sets queue admission order, so a higher tier starts sooner when the pool is busy. The tiers are Priority (queue-jump under contention), Standard (the default), Flex (same model and speed; last in line), Batch (async; completes within 24h or 7d). Pass service_tier on a request (OpenAI: top-level; Anthropic: the same field) and the tier that served it is echoed back in usage.
Does it work with the OpenAI and Anthropic SDKs?
Yes. Set OPENAI_BASE_URL to https://api.partitionlabs.ai/v1 or ANTHROPIC_BASE_URL to https://api.partitionlabs.ai and keep the client, the types and the retries you already have. Streaming, tool calls and image input work on both. Files and batches use the OpenAI shapes (/v1/files, /v1/batches).
What do prefix-cache writes cost?
Nothing. Cache writes are free on every service tier: a write is an ordinary prefill, already billed once at the input rate, so there is nothing left to charge for. Cached reads are billed at the model's cached-read price: $0.05 per million tokens on Standard for Qwen 3.8 27B.
What is the difference between a subscription and pay-as-you-go credits?
A subscription reserves a share of one model at one context ceiling for a flat monthly price. Pay-as-you-go credits are prepaid, priced per million tokens, and best-effort: they fill the capacity reserved tenants are not using, which is most of the time. Packages start at $5.00 and credits expire 12 months after purchase. Credits run up to the widest context ceiling the model serves, priced from its rate card; there is no rung to name.
What do "Sold out" and "Waitlist only" mean?
Sold out means every share unit at that ceiling is committed; we never oversell. Waitlist only means that ceiling is not taking new subscriptions right now, whatever its room. Either way, join the waitlist for the tier you want and we notify in the order people joined as capacity opens.
Which models and context lengths are available?
Qwen 3.8 27B, 27B multimodal, model id qwen3.8-27b, reserved ceilings of 4k, 8k, 16k, 32k, 64k, 128k, 256k. A subscription reserves one ceiling of one model, and the one id serves every ceiling.