Skip to main content
Inspect inference requests and responses captured by Gateway. List and filter inferences in the active project, sort by tokens / cost / latency, discover the available filter values, and fetch the complete stored request and response bodies. Alias: inf inferences

​
inf inference list

List and filter inferences in the active project. 
inf inference list
Alias: inf inference ls

​
Options

FlagRequiredDescriptionDefault
-l, --limit <n>NoMaximum number of results (1–100)20
--sort <key>NoSort key: sent_at, http_code, cost, duration, tokens, input_tokens, output_tokens, input_size, output_sizesent_at
--order <asc|desc>NoSort orderdesc
--filter <expr>NoNumeric filter <field><op><number> (repeatable). Fields: inputTokens, outputTokens, inputSizeBytes, outputSizeBytes, durationMs, totalCost. Ops: > >= < <= = !=—
--metadata <expr>NoMetadata filter <key><op><value> (repeatable). Ops: = != ~ !~, plus <key> is_empty / <key> is_not_empty—
-m, --model <name>NoFilter by model (repeatable or comma-separated)All models
--provider <name>NoFilter by downstream provider (repeatable or comma-separated)All
--environment <name>NoFilter by environment (repeatable or comma-separated)All
--status <code>NoFilter by HTTP status code, e.g. 200,500 (repeatable or comma-separated)All
--task <id>NoFilter by task ID — matches the x-inference-task-id header set by inf instrument --task-id (repeatable or comma-separated)—
--upload <id>NoFilter by upload ID (repeatable or comma-separated)—
--stream <bool>NoFilter by streamed responses (true / false)—
--from <iso> / --to <iso>NoAbsolute time range (ISO-8601). Use both together.—
--range <preset>NoRelative time range: 1h, 6h, 12h, 1d, 3d, 7d, 14d, 30d, 90d, all—
--cursor <cursor>NoPagination cursor (from a previous --json response)—
Don’t hardcode filter values — run inf inference facets to discover the valid models, providers, environments, tasks, and metadata keys for the active project, along with the full filter reference.
The human-readable table shows the inference ID, model, status code (color-coded), input/output token counts, latency, cost, and timestamp. Add the global --json flag to emit the full result object — { items, nextCursor, hasMore, totalCount } — so scripts can read .items and paginate by passing .nextCursor back via --cursor.

​
Examples

# List the 10 most recent inferences
inf inference list --limit 10

# Largest-input requests first — e.g. find prompts over 39k tokens
inf inference list --sort input_tokens --order desc --limit 50
inf inference list --filter inputTokens>39000

# Combine numeric, array, and metadata filters over a time window
inf inference list --model meta-llama/llama-3.1-8b-instruct/fp-8 --status 200 --range 7d
inf inference list --filter durationMs>5000 --metadata user_id=abc123

# Paginate from a script — JSON output includes nextCursor
cursor=$(inf --json inference list --sort input_tokens --order desc | jq -r '.nextCursor')
inf --json inference list --sort input_tokens --order desc --cursor "$cursor"

​
inf inference facets

Probe the active project for the values you can filter on — models, providers, environments, task IDs, and metadata keys — plus the full numeric/metadata/sort reference. Values are discovered from your data, not hardcoded, which makes this the starting point for building a filtered inf inference list query (and a one-call way for an AI agent to learn the filter surface). Alias: inf inference filters 
inf inference facets
Add the global --json flag to emit a machine-readable object combining the probed values with a static reference (numeric fields, operators, and sort keys).

​
inf inference get

Fetch the complete stored request and response for a specific inference — method, path, headers, and the full request/response bodies (returned only when payload storage was enabled for the request; otherwise the sides come back null). Useful for debugging specific calls, inspecting model behavior, or archiving payloads. 
inf inference get <id>

​
Arguments

ArgumentRequiredDescription
idYesFull inference UUID or a 4+ character prefix

​
Options

FlagRequiredDescriptionDefault
--requestNoOutput only the request (omit the response)Both
--responseNoOutput only the response (omit the request)Both
--bodyNoOutput only the raw body content (no method/path/headers). Requires --request or --response—
-o, --output <path>NoWrite the output to a file instead of stdoutstdout
Add the global --json flag to print the full { request, response } payload (method, path, headers, and complete bodies) as clean JSON for piping into jq or saving.

​
Examples

# Using a 4+ character UUID prefix (human-readable view)
inf inference get inf_abc1

# Pull a full UUID from list output, then fetch it
inf inference list --json | jq -r '.items[0].id' | xargs inf inference get

# Full request + response as clean JSON, then extract the response body
inf --json inference get <id> | jq '.response.body'

# Dump just the raw response body to a file
inf inference get <id> --response --body -o response.json