# litellm-rust vs gomodel

Operated by the Busbar team; Busbar is also an entrant. Gateway overhead against a local mock is not end-to-end model latency.  [Methodology and limitations](https://onthebench.ai/gateways/method) .

Requested cell: openai → openai. Metric: added_latency_p99_us.

Comparability: comparable. Ratios require an identical protocol pair, hardware, architecture, metric definition, clean harness commit, recorded mock digest, and metric-specific workload. Missing evidence never matches missing evidence. These are observed gateway measurements against a local mock, not a claim about model latency or statistical significance.

- Load-generator binary digests were not recorded; instrument equivalence is based on the identical clean harness source commit and mock digest.
- Measurements were made at different times on independently provisioned machines.

Ratio (B ÷ A): 2.025089605734767. No statistical significance is asserted.

[Comparison JSON](https://onthebench.ai/api/v1/compare?a=litellm-rust&b=gomodel&ingress=openai&egress=openai&metric=added_latency_p99_us)  ·  [All LiteLLM · Rust evidence](https://onthebench.ai/gateways/litellm-rust)  ·  [All GoModel evidence](https://onthebench.ai/gateways/gomodel)

## litellm-rust

Build src/litellm-rust/target/release/litellm-gateway. Measured 2026-11-10T17:39:51Z.  [Run evidence](https://onthebench.ai/gateways/runs/run-litellm-rust-69d8e6ed325740d9da7f0aaf31b815418c4801eb6549b2e2c68f768a92af3ad4)

| Ingress → upstream | Metric | Value | State / reason | p99 bound (ms) |
| --- | --- | --- | --- | --- |
| openai → openai | added_latency_p50_us | 249 | valid; gateway_c1_samples=22021; direct_c1_samples=267021 | — |
| openai → openai | added_latency_p99_us | 279 | valid; gateway_c1_samples=22021; direct_c1_samples=267021 | — |
| openai → openai | gateway_c1_p99_us | 306 | valid; gateway_c1_samples=22021 | — |
| openai → openai | direct_c1_p99_us | 27 | valid; direct_c1_samples=267021 | — |
| openai → openai | cpu_us_per_request | 272.6013913681787 | valid | — |
| openai → openai | rps_per_cpu_second | 3668.359853121175 | valid | — |
| openai → openai | cost_window_conc | 8 | valid | — |
| openai → openai | cost_core_utilisation | 0.6790579018170796 | valid | — |
| openai → openai | cost_window_ok | 59941 | valid | — |
| openai → openai | cost_window_rps | 9989 | valid | — |
| openai → openai | cost_threads | 5 | valid | — |
| openai → openai | cost_nonvol_ctxt_per_request | 0 | valid | — |
| openai → openai | cost_majflt | 0 | valid | — |
| openai → openai | added_ttft_p50_us | not_measured | not_measured | — |
| openai → openai | added_ttft_p99_us | not_measured | not_measured | — |
| openai → openai | added_gap_p50_us | not_measured | not_measured | — |
| openai → openai | added_gap_p99_us | not_measured | not_measured | — |
| openai → openai | streams_sustained_fps | 0 (measured_failure) | valid | — |
| openai → openai | streams_sustained | 0 (measured_failure) | valid | — |
| openai → openai | idle_rss_mib | 12.73828125 | valid | — |
| openai → openai | steady_state_rss_mib | 18.9921875 | valid | — |
| openai → openai | recovered_rss_mib | 18.99609375 | valid | — |
| openai → openai | peak_rss_mib | 19.875 | valid | — |
| openai → openai | peak_rss_hwm_mib | 19.484375 | valid | — |
| openai → openai | time_to_plateau_s | not_measured | not_measured | — |
| openai → openai | growth_rate_mib_per_min | -0.1791634760562065 | valid | — |
| openai → openai | load_s | 300 | valid | — |
| openai → openai | shape | 0 | valid | — |
| openai → openai | idle_shape | not_measured | not_measured | — |
| openai → openai | idle_static | 1 | valid | — |
| openai → openai | idle_growth_rate_mib_per_min | 0 | valid | — |
| openai → openai | throughput_rps | 8404 req/s | concurrency 4; samples 50435 | 1 |
| openai → openai | throughput_rps | 10049 req/s | concurrency 16; samples 60306 | 5 |
| openai → openai | throughput_rps | 10049 req/s | concurrency 16; samples 60306 | 10 |
| openai → openai | throughput_rps | 10049 req/s | concurrency 16; samples 60306 | 50 |
| openai → openai | throughput_rps | 10049 req/s | concurrency 16; samples 60306 | 100 |
| openai → openai | throughput_rps | 10049 req/s | concurrency 16; samples 60306 | unbounded |

## gomodel

Build enterpilot/gomodel:0.2.3@sha256:c50627e093ff88bff311e582a43d7de14e0be29d52cb333ecb3191eac7874f05. Measured 2026-11-10T17:39:52Z.  [Run evidence](https://onthebench.ai/gateways/runs/run-gomodel-f6e038780b29f86549f840f902ac96740154f0f0ef2a66a3fd9dcd4bc3b83bad)

| Ingress → upstream | Metric | Value | State / reason | p99 bound (ms) |
| --- | --- | --- | --- | --- |
| openai → openai | added_latency_p50_us | 343 | valid; gateway_c1_samples=15837; direct_c1_samples=239533 | — |
| openai → openai | added_latency_p99_us | 565 | valid; gateway_c1_samples=15837; direct_c1_samples=239533 | — |
| openai → openai | gateway_c1_p99_us | 596 | valid; gateway_c1_samples=15837 | — |
| openai → openai | direct_c1_p99_us | 31 | valid; direct_c1_samples=239533 | — |
| openai → openai | cpu_us_per_request | 439.1503284680862 | valid | — |
| openai → openai | rps_per_cpu_second | 2277.1245634458674 | valid | — |
| openai → openai | cost_window_conc | 8 | valid | — |
| openai → openai | cost_core_utilisation | 0.7135981462725213 | valid | — |
| openai → openai | cost_window_ok | 39121 | valid | — |
| openai → openai | cost_window_rps | 6519 | valid | — |
| openai → openai | cost_threads | 14 | valid | — |
| openai → openai | cost_nonvol_ctxt_per_request | 0 | valid | — |
| openai → openai | cost_majflt | 0 | valid | — |
| openai → openai | added_ttft_p50_us | 479 | valid; ttft_gw_samples=100; ttft_direct_samples=100 | — |
| openai → openai | added_ttft_p99_us | 601 | valid; ttft_gw_samples=100; ttft_direct_samples=100 | — |
| openai → openai | added_gap_p50_us | below_resolution | below_resolution; gap_gw_samples=63; gap_direct_samples=63 | — |
| openai → openai | added_gap_p99_us | 26 | valid; gap_gw_samples=63; gap_direct_samples=63 | — |
| openai → openai | streams_sustained_fps | 50390.08056872798 | valid | — |
| openai → openai | streams_sustained | 1208 | valid | — |
| openai → openai | idle_rss_mib | 53.00390625 | valid | — |
| openai → openai | steady_state_rss_mib | 87.26171875 | valid | — |
| openai → openai | recovered_rss_mib | 90.45703125 | valid | — |
| openai → openai | peak_rss_mib | 90.5078125 | valid | — |
| openai → openai | peak_rss_hwm_mib | 89.015625 | valid | — |
| openai → openai | time_to_plateau_s | not_measured | not_measured | — |
| openai → openai | growth_rate_mib_per_min | -0.33822817505778513 | valid | — |
| openai → openai | load_s | 300 | valid | — |
| openai → openai | shape | 0 | valid | — |
| openai → openai | idle_shape | not_measured | not_measured | — |
| openai → openai | idle_static | 1 | valid | — |
| openai → openai | idle_growth_rate_mib_per_min | 0.41083926712820346 | valid | — |
| openai → openai | throughput_rps | 4555 req/s | concurrency 2; samples 27335 | 1 |
| openai → openai | throughput_rps | 6685 req/s | concurrency 8; samples 40117 | 5 |
| openai → openai | throughput_rps | 6862 req/s | concurrency 16; samples 41180 | 10 |
| openai → openai | throughput_rps | 7415 req/s | concurrency 64; samples 44496 | 50 |
| openai → openai | throughput_rps | 7475 req/s | concurrency 128; samples 44859 | 100 |
| openai → openai | throughput_rps | 7475 req/s | concurrency 128; samples 44859 | unbounded |
