One bill. Every model.
One bill for every lab. Rates are the lab's list. Spend caps, roles, and keys are in the product, not a plan.
Billing
747.29
tokens remaining
- topped up
- 1,000
- spent
- 165.55
- per-request ceiling
- 12
- $ / Token
- 1.00
- tokens / min
- 2,000,000
- auto-reload
- 20%
- BYOK
- 2 providers · not debited
List prices.
| MODEL | CONTEXT | UPSTREAMS | IN / 1M | OUT / 1M | CACHED |
|---|---|---|---|---|---|
| qwen/qwen3.8-27b | 262.1k | 3 | 0.06 | 0.24 | — |
| google/gemini-2.5-flash-lite | 1.0M | 1 | 0.10 | 0.40 | 0.01 |
| mistral/mistral-small-4 | 262.1k | 2 | 0.15 | 0.60 | 0.015 |
| mistral/ministral-3-8b | 262.1k | 1 | 0.15 | 0.15 | 0.015 |
| openai/gpt-5.6-luna | 1.0M | 1 | 0.20 | 1.20 | 0.02 |
| openai/gpt-5.4-nano | 1.0M | 1 | 0.20 | 1.25 | 0.02 |
| google/gemini-3.5-flash-lite | 1.0M | 1 | 0.30 | 2.50 | 0.03 |
| google/gemini-2.5-flash | 1.0M | 1 | 0.30 | 2.50 | 0.03 |
| meta/muse-glimmer-30b | 131.1k | 3 | 0.30 | 1.20 | 0.04 |
| deepseek/deepseek-v4-flash | 1.0M | 4 | 0.44 | 1.32 | 0.014 |
| mistral/mistral-large-3 | 262.1k | 2 | 0.50 | 1.50 | 0.05 |
| openai/gpt-5.4-mini | 1.0M | 1 | 0.75 | 4.50 | 0.075 |
| anthropic/claude-haiku-4-5 | 200.0k | 1 | 1.00 | 5.00 | 0.10 |
| xai/grok-build-0.1 | 256.0k | 1 | 1.00 | 2.00 | 0.20 |
| zai/glm-5-turbo | 202.8k | 2 | 1.20 | 4.00 | — |
| xai/grok-4.3 | 256.0k | 1 | 1.25 | 2.50 | 0.20 |
| meta/muse-spark-1.2 | 1.0M | 4 | 1.25 | 4.25 | 0.125 |
| deepseek/deepseek-v4-pro | 1.0M | 3 | 1.32 | 3.96 | 0.044 |
| zai/glm-5.2 | 1.0M | 3 | 1.40 | 4.40 | — |
Per million tokens, at the primary upstream. Extra upstreams have their own prices. A dash means no cached rate. Reasoning bills as completion. Cached reads are the lab's cache, at their rate.
Project caps.
Each project has a spend cap. Each call has a ceiling. Go over either and the request is refused before it runs.
Billing
Allocation
- wallet
- 1,000
- allocated
- 1,000
- unallocated
- 0
- latticeceiling 12 · 600 rpmcap152.71 / 900
- hearthceiling 12 · 600 rpmcap12.84 / 100
Access follows the role.
Owners and admins see billing and usage. Developers see usage, not invoices. Consumers can call the API and see neither. One owner per workspace. Keys can be limited to specific people.
| ROLE | GATEWAY | USAGE | BILLING |
|---|---|---|---|
| owner | yes | yes | yes |
| admin | yes | yes | yes |
| developer | yes | yes | no |
| consumer | yes | no | no |
Limits live on the key.
Each key has its own rate, throughput, and concurrency. Revoke one without touching the others. Use your own provider keys and those tokens never hit the balance.
- productionsk-hopscotch-7f3a…600 rpm · 2,000,000 tpm · 20 concurrent
- stagingsk-hopscotch-c21e…600 rpm · 2,000,000 tpm · 20 concurrent
- robsk-hopscotch-a91c…600 rpm · 2,000,000 tpm · 20 concurrent · held by 1
- localsk-hopscotch-9aa1…600 rpm · 2,000,000 tpm · 20 concurrent
- OpenAIsk-proj-4c8e…
- Anthropicsk-ant-api03-9…
Tried first. Logged. Not billed to the balance.
One bill. Caps in the product.
No plan. Buy tokens and spend them at the lab's price. Auto-reload at 20% remaining, or leave it off. Need an invoice or a volume commit? That is enterprise.