> ## Documentation Index > Fetch the complete documentation index at: https://freesolo.co/docs/llms.txt > Use this file to discover all available pages before exploring further. # Deploy & chat > Serve a trained adapter and talk to it over an OpenAI-compatible API. Once a [training run](/guides/training) reaches `done`, deploy its adapter and chat with it, from the CLI or any OpenAI-compatible client. `flash deploy` registers your adapter with Freesolo's **managed serving service**. Register the adapter, send requests to it, and pay per token (see [Billing](#billing)). ## Deploy ```bash theme={null} flash deploy ``` Preview what a deploy would do without creating it: ```bash theme={null} flash deploy --dry-run ``` Skip the server-side post-deploy smoke check. Registration alone does not guarantee the adapter serves, so use this only when you'll verify separately: ```bash theme={null} flash deploy --no-verify ``` ## Deploy a specific checkpoint Every training step that saved an adapter is independently deployable. List a run's deployable checkpoints: ```bash theme={null} flash checkpoints ``` Then serve a specific step instead of the final adapter: ```bash theme={null} flash deploy /step- ``` You can deploy a checkpoint while a run is still training, or after a GRPO run stops with useful intermediate steps. Checkpoint deployments attach serving metadata to the run while preserving the run's training state. A run that never finalized (cancelled or preempted mid-training) has no final adapter, so a plain `flash deploy ` fails with an error that lists the saved checkpoint steps and the exact `flash deploy /step-N` command to deploy one of them instead. ## Billing Serving is **billed per token**. Prompt and completion tokens have per-model rates, and cached prompt tokens use the model's cached-input rate. Prices are listed in [Supported models](/reference/models#serving-prices). **Cached prompt tokens are cheaper than uncached prompt tokens.** Prefix caching is always on: when a request's prompt shares a leading prefix with a recent one — a shared system prompt, or the growing context of a multi-turn chat — the serving engine reuses that prefix from cache instead of recomputing it. Only the input prefix can be cached, so completion tokens always bill at the full per-token rate. When a request hits the prefix cache, the response reports how many prompt tokens were served from cache in `usage.prompt_tokens_details.cached_tokens`. ## Chat from the CLI ```bash theme={null} flash chat -m "Summarize the plot of Hamlet in two sentences." ``` `-m`/`--message` is required; `--system`, `--max-tokens` (default 512), and `--temperature` (default 0.0) are optional — see the [CLI reference](/reference/cli#serving) for the full flag list. ```bash theme={null} flash chat -m "Write a haiku about mountain weather" --temperature 0.8 --max-tokens 128 ``` `--system` is transient — it applies to that one request and is not stored with the deployment. Use it to probe the adapter with the same system prompt it was trained with: ```bash theme={null} flash chat -m "What is 6*7?" --system "Answer with just the number." ``` ## Manage deployments ```bash theme={null} flash deployments # list active deployments and endpoints flash undeploy # deregister the adapter from serving ``` ## Use it from your own code Deployments are OpenAI-compatible, so you can point any OpenAI SDK at the endpoint from `flash deployments`. The `model` is your run id: ```python theme={null} from openai import OpenAI client = OpenAI( base_url="https:///v1", # from `flash deployments` api_key="", # your Freesolo API key (the same one `flash login` uses); the endpoint checks that your org owns the adapter ) resp = client.chat.completions.create( model="", messages=[{"role": "user", "content": "Hello!"}], ) print(resp.choices[0].message.content) ``` ### Call it with the freesolo SDK The `freesolo` SDK ships a small hosted-LoRA client if you'd rather not pull in an OpenAI SDK: ```python theme={null} from freesolo.utils.hosting import HostedLoraClient, chat_completion_with_lora client = HostedLoraClient(hosting_url="https://") resp = client.chat_completion("", [{"role": "user", "content": "Hello!"}]) # or the one-shot module helper resp = chat_completion_with_lora( "", [{"role": "user", "content": "Hello!"}], hosting_url="https://", ) ``` Every call — `chat_completion`, `generate`, and the module-level `chat_completion_with_lora` / `generate_with_lora` helpers — accepts a per-call `timeout_seconds` override, so a single slow request can be given its own budget (or a tight one) without changing the client-wide timeout set at construction: ```python theme={null} client.chat_completion("", messages, timeout_seconds=120.0) ``` ### Pin and verify the serving checkpoint Redeploying an adapter id (for example sweeping over checkpoint steps with `flash deploy /step-N`) replaces what that id serves. When requests and redeploys can race, the inference endpoints support two headers so you always know — and can require — which checkpoint answered: * **`X-Freesolo-Checkpoint`** (response): echoes the checkpoint that actually served the request. The header is omitted entirely when the adapter has no checkpoint (a plain final-adapter deployment). * **`X-Freesolo-Expected-Checkpoint`** (request): pins the request to an expected checkpoint. If the adapter is currently serving a different one (e.g. a parallel sweep redeployed another step in between), the request fails with **409 Conflict** — naming the checkpoint that is live — instead of silently generating from the wrong checkpoint. The value is compared after stripping whitespace; send an empty value to require "no checkpoint". Both headers work on streaming and non-streaming requests. ```python theme={null} resp = client.chat.completions.with_raw_response.create( model="", messages=[{"role": "user", "content": "Hello!"}], extra_headers={"X-Freesolo-Expected-Checkpoint": ""}, ) print(resp.headers.get("X-Freesolo-Checkpoint")) ``` ## Export to your own HuggingFace repo To take a trained adapter out of Freesolo's managed storage, copy it into a HuggingFace repo you own: ```bash theme={null} flash export --adapter-id --repository / ``` `--adapter-id` and `--repository` are required; `--api-key` (defaults to `HF_TOKEN`) and `--public` are optional. See the [CLI reference](/reference/cli#export) for the full flag list.