# Models and Usage Bkper AI curates models for useful capability per dollar. The inference provider is independent of the client or harness making the request. Bkper applies effective context, output, and reasoning settings, enforces a monthly allowance, and shows where usage goes. To configure authentication, endpoints, and compatible clients, see [Bkper AI Provider](https://bkper.com/docs/ai/bkper-ai-provider.md). ## Choose a model Choose a model based on its workload, cost profile, and effective settings. Upstream provider defaults may differ from the Bkper configuration below. | Model | Best for | Effective settings | | --- | --- | --- | | **Claude Fable 5** `anthropic/claude-fable-5` | Claude model for creative writing, analysis, and controlled agent workflows. | Thinking: `off`, `low`, `medium`
Max context: 200k tokens
Max output: 32k tokens | | **GPT-5.6 Luna** `openai/gpt-5.6-luna` | Cost-efficient GPT-5.6 model for fast, high-volume workloads. | Thinking: `off`, `medium`, `high`
Max context: 200k tokens
Max output: 32k tokens | | **GPT-5.6 Terra** `openai/gpt-5.6-terra` | Balanced GPT-5.6 model for capable, cost-efficient everyday work. | Thinking: `off`, `medium`, `high`
Max context: 200k tokens
Max output: 32k tokens | | **GPT-5.6 Sol** `openai/gpt-5.6-sol` | Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows. | Thinking: `off`, `medium`, `high`
Max context: 200k tokens
Max output: 32k tokens | | **Grok 4.5** `xai/grok-4.5` | xAI's latest Grok for chat, coding, agentic tools, and lower hallucination risk. | Thinking: `off`, `medium`, `high`
Max context: 200k tokens
Max output: 32k tokens | ## Usage rates **USD of included usage per one million tokens** | Model | Input | Cache read | Cache write | Output | | --- | ---: | ---: | ---: | ---: | | Claude Fable 5 | $10.00 | $1.00 | $12.50 | $50.00 | | GPT-5.6 Luna | $1.00 | $0.10 | $1.25 | $6.00 | | GPT-5.6 Terra | $2.50 | $0.25 | $3.125 | $15.00 | | GPT-5.6 Sol | $5.00 | $0.50 | $6.25 | $30.00 | | Grok 4.5 | $2.00 | $0.50 | $0.00 | $6.00 | Usage rates reduce the included monthly allowance. They are not billed separately by Bkper. Input means tokens sent without a cache match. Cache read means reused input already stored by the provider. Cache write means input added to a provider cache. Output includes generated response and reasoning tokens reported by the provider. ## Effective limits Bkper applies the context cap, available thinking levels, default thinking level, and maximum output listed for each model above. These effective limits take precedence over generic provider limits. GPT-5.6 and Grok requests can use `off`, `medium`, or `high` thinking. Claude Fable 5 can use `off`, `low`, or `medium`. Each model's default applies when a request does not select a level. Every current model has a server-enforced maximum output of **32,000 tokens per request**. Bounded context, output, and reasoning help make usage more predictable. They do not guarantee response quality or accounting accuracy. ## Monthly allowance For paid plans: > **Monthly AI usage allowance = 50% of normalized monthly software subscription value.** The calculation works as follows: - Monthly plans use the active recurring software subscription value. - Annual plans divide the annual recurring value by 12, then apply 50%. - Professional and custom plans use only the recurring software subscription component. - Professional services, implementation, consulting, taxes, unrelated one-time charges, credits, refunds, and prorations do not increase the allowance. - Free users receive a separately configured trial allowance. The 50% formula does not apply to Free. The allowance is an inference entitlement. It is not cash, refund value, a separately billed balance, or transferable account credit. The allowance resets monthly. Unused allowance does not roll over. The authenticated [Bkper AI usage dashboard](https://ai.bkper.app) is authoritative for your exact current allowance. ## Individual and pooled usage Allowance scope follows the subscription: - Free and Standard usage is assigned to the individual user. - Business and Professional usage can be pooled when the subscription has domain-wide scope. - Everyone sharing a pooled allowance reduces the same monthly total. A pooled allowance does not make every user's request history visible to everyone. Visibility depends on the viewer's billing role. ## Usage visibility and privacy The [Bkper AI usage dashboard](https://ai.bkper.app) separates allowance visibility from request attribution: - Regular users see the shared allowance remaining and their own requests and usage. - The billing or subscription administrator sees domain-wide usage attributed by user, AI model, and app or source. - The dashboard does not expose prompts or responses. Usage value is an estimate based on the published rates above. It shows how much of the included allowance a request consumed; it is not a separate Bkper charge. ## When the limit is reached Bkper AI stops serving allowance-backed requests when the monthly limit is reached. There are **no automatic paid Bkper AI overages at launch**. Where supported, you can connect an external model provider. External subscriptions, API keys, charges, privacy terms, and limits are governed by that provider and do not use the included Bkper AI allowance. ## How Bkper selects models We build Bkper with the Bkper CLI Agent and use it every day. We test many models through real work and include only those that consistently work well for us within our cost and control constraints. The catalog is a practical, opinionated shortlist—not a directory of every available model. Bkper prioritizes capability per dollar rather than pursuing the highest benchmark score at any cost. Selection also considers: - results and reliability in daily agent workflows; - provider capabilities and tool use; - observed usage cost; - effective context and reasoning controls; - public benchmarks. [Explore the live DeepSWE leaderboard](https://deepswe.datacurve.ai/). DeepSWE measures long-horizon software-engineering work. It is one input into model selection, not a measure of accounting accuracy or a guarantee of performance in Bkper workflows. ## Model references | Model | Provider | Released | | --- | --- | --- | | Claude Fable 5 | [Anthropic](https://www.anthropic.com/news/claude-fable-5-mythos-5) | 2026-06-09 | | GPT-5.6 Luna | [OpenAI](https://openai.com/index/gpt-5-6/) | 2026-07-09 | | GPT-5.6 Terra | [OpenAI](https://openai.com/index/gpt-5-6/) | 2026-07-09 | | GPT-5.6 Sol | [OpenAI](https://openai.com/index/gpt-5-6/) | 2026-07-09 | | Grok 4.5 | [xAI](https://x.ai/news/grok-4-5) | 2026-07-08 | ## Sources Last synchronized: **2026-07-14** - [Bkper AI effective model configuration](https://ai.bkper.app/v1/models) - [Models.dev model metadata](https://models.dev/models.json) - [DeepSWE live leaderboard](https://deepswe.datacurve.ai/) Models.dev metadata is provided under the MIT License. Provider names and logos remain trademarks of their respective owners. ## Next steps - [Connect a client to Bkper AI](https://bkper.com/docs/ai/bkper-ai-provider.md). - [Open the Bkper AI usage dashboard](https://ai.bkper.app). - [Use the preconfigured Bkper CLI Agent](https://bkper.com/docs/ai/bkper-cli-agent.md).