inference_offerings


Columns

Column Type Size Nulls Auto Default Children Parents Comments
id serial 10 √ nextval('inference_offerings_id_seq'::regclass)
provider_id text 2147483647 null
inference_providers.id inference_offerings_provider_id_fkey R
model_id text 2147483647 null
inference_providers.id Implied Constraint R
model_ref int4 10 √ null
models.id inference_offerings_model_ref_fkey R
model_display_name text 2147483647 √ null
quant text 2147483647 'unknown'::text
quant_source text 2147483647 'unknown'::text
input_price_per_mtok float8 17,17 √ null
output_price_per_mtok float8 17,17 √ null
cache_price_per_mtok float8 17,17 √ null
context_length int4 10 √ null
max_output_tokens int4 10 √ null
supports_function_calling bool 1 √ false
supports_vision bool 1 √ false
supports_streaming bool 1 √ true
throughput_tokens_per_sec float8 17,17 √ null
time_to_first_token_ms float8 17,17 √ null
available bool 1 √ true
availability_checked_at timestamptz 35,6 √ null
created_at timestamptz 35,6 now()
updated_at timestamptz 35,6 now()
fleet_proxy_url text 2147483647 √ null
fleet_lane text 2147483647 √ null
served_model_verified text 2147483647 √ null
honors_max_tokens bool 1 √ null
supports_reasoning_effort bool 1 √ null
supports_seed bool 1 √ null
supports_json_mode bool 1 √ null
region text 2147483647 √ null
ttft_ms_p50 float8 17,17 √ null
decode_tok_s_n1 float8 17,17 √ null
prefill_tok_s_n1 float8 17,17 √ null
mean_tpot_ms float8 17,17 √ null
benchmark_run_id text 2147483647 √ null
inference_providers.id Implied Constraint R
benchmarked_at timestamptz 35,6 √ null
prefill_agg_tok_s_n4 float8 17,17 √ null
prefill_agg_tok_s_n8 float8 17,17 √ null
prefill_agg_tok_s_n16 float8 17,17 √ null
prefill_agg_tok_s_n32 float8 17,17 √ null
prefill_agg_tok_s_n64 float8 17,17 √ null
prefill_agg_tok_s_n128 float8 17,17 √ null
prefill_agg_tok_s_n256 float8 17,17 √ null
decode_agg_tok_s_n4 float8 17,17 √ null
decode_agg_tok_s_n8 float8 17,17 √ null
decode_agg_tok_s_n16 float8 17,17 √ null
decode_agg_tok_s_n32 float8 17,17 √ null
decode_agg_tok_s_n64 float8 17,17 √ null
decode_agg_tok_s_n128 float8 17,17 √ null
decode_agg_tok_s_n256 float8 17,17 √ null
context_length_verified int4 10 √ null
context_source text 2147483647 √ null

Indexes

Constraint Name Type Sort Column(s)
inference_offerings_pkey Primary key Asc id
idx_inf_off_model Performance Asc model_id
idx_inf_off_provider Performance Asc provider_id
idx_inf_off_quant Performance Asc quant
inference_offerings_provider_id_model_id_key Must be unique Asc/Asc provider_id + model_id

Relationships

Close relationships within degrees of separation