# Plano benchmark measurements

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) .

Rust · recorded build: katanemo/plano:0.4.39@sha256:35a84cb873ee5f16cded33eeda72736f90798962b7489d58650c0db7b546e9ac. Measured: 2026-11-10T17:40:07Z.

[JSON](https://onthebench.ai/api/v1/gateways/plano)  ·  [Markdown](https://onthebench.ai/gateways/plano.md)  ·  [CSV](https://onthebench.ai/gateways/data.csv?gateway=plano&compact=1)  ·  [Project source](https://github.com/katanemo/plano)  ·  [Interactive dashboard](https://onthebench.ai/gateways)

Each row below names its protocol pair. A representative dashboard cell may differ between gateways; compare an identical pair before interpreting a ranking. Unavailable metrics retain their reason; below-resolution readings are not exact zeroes.

## Published measurements

| Ingress → upstream | Metric | Value | State / reason | p99 bound (ms) |
| --- | --- | --- | --- | --- |
| openai → bedrock | added_latency_p50_us | 205998 | valid; gateway_c1_samples=29; direct_c1_samples=262765 | — |
| openai → bedrock | added_latency_p99_us | 212984 | valid; gateway_c1_samples=29; direct_c1_samples=262765 | — |
| openai → bedrock | gateway_c1_p99_us | 213012 | valid; gateway_c1_samples=29 | — |
| openai → bedrock | direct_c1_p99_us | 28 | valid; direct_c1_samples=262765 | — |
| openai → bedrock | cpu_us_per_request | 189176.47058823527 | valid | — |
| openai → bedrock | rps_per_cpu_second | 5.286069651741294 | valid | — |
| openai → bedrock | cost_window_conc | 8 | valid | — |
| openai → bedrock | cost_core_utilisation | 0.6169920805069831 | valid | — |
| openai → bedrock | cost_window_ok | 85 | valid | — |
| openai → bedrock | cost_window_rps | 14 | valid | — |
| openai → bedrock | cost_threads | 68 | valid | — |
| openai → bedrock | cost_nonvol_ctxt_per_request | 5.141176470588236 | valid | — |
| openai → bedrock | cost_majflt | 0 | valid | — |
| openai → bedrock | added_ttft_p50_us | untestable | untestable | — |
| openai → bedrock | added_ttft_p99_us | untestable | untestable | — |
| openai → bedrock | added_gap_p50_us | untestable | untestable | — |
| openai → bedrock | added_gap_p99_us | untestable | untestable | — |
| openai → bedrock | streams_sustained_fps | untestable | untestable | — |
| openai → bedrock | streams_sustained | untestable | untestable | — |
| openai → bedrock | idle_rss_mib | 598.80078125 | valid | — |
| openai → bedrock | steady_state_rss_mib | 1006.28515625 | valid | — |
| openai → bedrock | recovered_rss_mib | 1006.22265625 | valid | — |
| openai → bedrock | peak_rss_mib | 1006.6875 | valid | — |
| openai → bedrock | peak_rss_hwm_mib | 1006.46875 | valid | — |
| openai → bedrock | time_to_plateau_s | 61 | valid | — |
| openai → bedrock | growth_rate_mib_per_min | -0.329296963138252 | valid | — |
| openai → bedrock | load_s | 306 | valid | — |
| openai → bedrock | shape | not_measured | not_measured | — |
| openai → bedrock | idle_shape | not_measured | not_measured | — |
| openai → bedrock | idle_static | 1 | valid | — |
| openai → bedrock | idle_growth_rate_mib_per_min | 0.046660991313913644 | valid | — |
| openai → bedrock | throughput_rps | bound_not_met req/s | concurrency not recorded; every cleanly-served rung that reported a tail had it at or above 1ms, so this gateway carried no measurable throughput under that bound | 1 |
| openai → bedrock | throughput_rps | bound_not_met req/s | concurrency not recorded; every cleanly-served rung that reported a tail had it at or above 5ms, so this gateway carried no measurable throughput under that bound | 5 |
| openai → bedrock | throughput_rps | bound_not_met req/s | concurrency not recorded; every cleanly-served rung that reported a tail had it at or above 10ms, so this gateway carried no measurable throughput under that bound | 10 |
| openai → bedrock | throughput_rps | bound_not_met req/s | concurrency not recorded; every cleanly-served rung that reported a tail had it at or above 50ms, so this gateway carried no measurable throughput under that bound | 50 |
| openai → bedrock | throughput_rps | bound_not_met req/s | concurrency not recorded; every cleanly-served rung that reported a tail had it at or above 100ms, so this gateway carried no measurable throughput under that bound | 100 |
| openai → bedrock | throughput_rps | 21 req/s | concurrency 8; samples 127 | unbounded |
| cohere → bedrock | — | — | not_declared: Pinned 0.4.39 source b13ddd632bde1fea7678386c345665ea5fa671af: hermesllm/src/clients/endpoints.rs accepts Chat, Responses and Messages ingress, with no Gemini, Cohere or Bedrock client API. providers/id.rs::compatible_api_for_client selects native Responses only for Responses ingress to OpenAI, Chat for Messages-to-OpenAI, native Messages for Messages-to-Anthropic, and Converse for all three ingress APIs to amazon_bedrock. Anthropic Chat/Responses ingress and Gemini provider use OpenAI-compatible upstream wire; they are not native Anthropic/Gemini translations. The normal provider mapping is retained rather than substituting a different provider for the OpenAI column. Seven supported pairs are enabled, including the documented Bedrock upstream. | — |
| gemini → bedrock | — | — | not_declared: Pinned 0.4.39 source b13ddd632bde1fea7678386c345665ea5fa671af: hermesllm/src/clients/endpoints.rs accepts Chat, Responses and Messages ingress, with no Gemini, Cohere or Bedrock client API. providers/id.rs::compatible_api_for_client selects native Responses only for Responses ingress to OpenAI, Chat for Messages-to-OpenAI, native Messages for Messages-to-Anthropic, and Converse for all three ingress APIs to amazon_bedrock. Anthropic Chat/Responses ingress and Gemini provider use OpenAI-compatible upstream wire; they are not native Anthropic/Gemini translations. The normal provider mapping is retained rather than substituting a different provider for the OpenAI column. Seven supported pairs are enabled, including the documented Bedrock upstream. | — |
| openai-responses → bedrock | added_latency_p50_us | 200013 | valid; gateway_c1_samples=30; direct_c1_samples=265071 | — |
| openai-responses → bedrock | added_latency_p99_us | 205956 | valid; gateway_c1_samples=30; direct_c1_samples=265071 | — |
| openai-responses → bedrock | gateway_c1_p99_us | 205984 | valid; gateway_c1_samples=30 | — |
| openai-responses → bedrock | direct_c1_p99_us | 28 | valid; direct_c1_samples=265071 | — |
| openai-responses → bedrock | cpu_us_per_request | 182500 | valid | — |
| openai-responses → bedrock | rps_per_cpu_second | 5.47945205479452 | valid | — |
| openai-responses → bedrock | cost_window_conc | 8 | valid | — |
| openai-responses → bedrock | cost_core_utilisation | 0.8586890105703885 | valid | — |
| openai-responses → bedrock | cost_window_ok | 116 | valid | — |
| openai-responses → bedrock | cost_window_rps | 19 | valid | — |
| openai-responses → bedrock | cost_threads | 68 | valid | — |
| openai-responses → bedrock | cost_nonvol_ctxt_per_request | 4.620689655172414 | valid | — |
| openai-responses → bedrock | cost_majflt | 0 | valid | — |
| openai-responses → bedrock | added_ttft_p50_us | untestable | untestable | — |
| openai-responses → bedrock | added_ttft_p99_us | untestable | untestable | — |
| openai-responses → bedrock | added_gap_p50_us | untestable | untestable | — |
| openai-responses → bedrock | added_gap_p99_us | untestable | untestable | — |
| openai-responses → bedrock | streams_sustained_fps | untestable | untestable | — |
| openai-responses → bedrock | streams_sustained | untestable | untestable | — |
| openai-responses → bedrock | idle_rss_mib | 621.60546875 | valid | — |
| openai-responses → bedrock | steady_state_rss_mib | 1055.50390625 | valid | — |
| openai-responses → bedrock | recovered_rss_mib | 1055.875 | valid | — |
| openai-responses → bedrock | peak_rss_mib | 1055.9375 | valid | — |
| openai-responses → bedrock | peak_rss_hwm_mib | 1055.87109375 | valid | — |
| openai-responses → bedrock | time_to_plateau_s | 66 | valid | — |
| openai-responses → bedrock | growth_rate_mib_per_min | 0.07183335358262208 | valid | — |
| openai-responses → bedrock | load_s | 305 | valid | — |
| openai-responses → bedrock | shape | not_measured | not_measured | — |
| openai-responses → bedrock | idle_shape | not_measured | not_measured | — |
| openai-responses → bedrock | idle_static | 1 | valid | — |
| openai-responses → bedrock | idle_growth_rate_mib_per_min | 0.04844942521841008 | valid | — |
| openai-responses → bedrock | throughput_rps | bound_not_met req/s | concurrency not recorded; every cleanly-served rung that reported a tail had it at or above 1ms, so this gateway carried no measurable throughput under that bound | 1 |
| openai-responses → bedrock | throughput_rps | bound_not_met req/s | concurrency not recorded; every cleanly-served rung that reported a tail had it at or above 5ms, so this gateway carried no measurable throughput under that bound | 5 |
| openai-responses → bedrock | throughput_rps | bound_not_met req/s | concurrency not recorded; every cleanly-served rung that reported a tail had it at or above 10ms, so this gateway carried no measurable throughput under that bound | 10 |
| openai-responses → bedrock | throughput_rps | bound_not_met req/s | concurrency not recorded; every cleanly-served rung that reported a tail had it at or above 50ms, so this gateway carried no measurable throughput under that bound | 50 |
| openai-responses → bedrock | throughput_rps | bound_not_met req/s | concurrency not recorded; every cleanly-served rung that reported a tail had it at or above 100ms, so this gateway carried no measurable throughput under that bound | 100 |
| openai-responses → bedrock | throughput_rps | 20 req/s | concurrency 16; samples 121 | unbounded |
| anthropic → bedrock | added_latency_p50_us | 193978 | valid; gateway_c1_samples=31; direct_c1_samples=259772 | — |
| anthropic → bedrock | added_latency_p99_us | 197949 | valid; gateway_c1_samples=31; direct_c1_samples=259772 | — |
| anthropic → bedrock | gateway_c1_p99_us | 197977 | valid; gateway_c1_samples=31 | — |
| anthropic → bedrock | direct_c1_p99_us | 28 | valid; direct_c1_samples=259772 | — |
| anthropic → bedrock | cpu_us_per_request | 175360 | valid | — |
| anthropic → bedrock | rps_per_cpu_second | 5.702554744525547 | valid | — |
| anthropic → bedrock | cost_window_conc | 8 | valid | — |
| anthropic → bedrock | cost_core_utilisation | 0.8601191828446305 | valid | — |
| anthropic → bedrock | cost_window_ok | 125 | valid | — |
| anthropic → bedrock | cost_window_rps | 20 | valid | — |
| anthropic → bedrock | cost_threads | 68 | valid | — |
| anthropic → bedrock | cost_nonvol_ctxt_per_request | 5.32 | valid | — |
| anthropic → bedrock | cost_majflt | 0 | valid | — |
| anthropic → bedrock | added_ttft_p50_us | untestable | untestable | — |
| anthropic → bedrock | added_ttft_p99_us | untestable | untestable | — |
| anthropic → bedrock | added_gap_p50_us | untestable | untestable | — |
| anthropic → bedrock | added_gap_p99_us | untestable | untestable | — |
| anthropic → bedrock | streams_sustained_fps | untestable | untestable | — |
| anthropic → bedrock | streams_sustained | untestable | untestable | — |
| anthropic → bedrock | idle_rss_mib | 612.45703125 | valid | — |
| anthropic → bedrock | steady_state_rss_mib | 967.6796875 | valid | — |
| anthropic → bedrock | recovered_rss_mib | 967.421875 | valid | — |
| anthropic → bedrock | peak_rss_mib | 967.99609375 | valid | — |
| anthropic → bedrock | peak_rss_hwm_mib | 967.70703125 | valid | — |
| anthropic → bedrock | time_to_plateau_s | 60 | valid | — |
| anthropic → bedrock | growth_rate_mib_per_min | 0.25204829296188547 | valid | — |
| anthropic → bedrock | load_s | 302 | valid | — |
| anthropic → bedrock | shape | not_measured | not_measured | — |
| anthropic → bedrock | idle_shape | not_measured | not_measured | — |
| anthropic → bedrock | idle_static | 1 | valid | — |
| anthropic → bedrock | idle_growth_rate_mib_per_min | 0.05193333183537614 | valid | — |
| anthropic → bedrock | throughput_rps | bound_not_met req/s | concurrency not recorded; every cleanly-served rung that reported a tail had it at or above 1ms, so this gateway carried no measurable throughput under that bound | 1 |
| anthropic → bedrock | throughput_rps | bound_not_met req/s | concurrency not recorded; every cleanly-served rung that reported a tail had it at or above 5ms, so this gateway carried no measurable throughput under that bound | 5 |
| anthropic → bedrock | throughput_rps | bound_not_met req/s | concurrency not recorded; every cleanly-served rung that reported a tail had it at or above 10ms, so this gateway carried no measurable throughput under that bound | 10 |
| anthropic → bedrock | throughput_rps | bound_not_met req/s | concurrency not recorded; every cleanly-served rung that reported a tail had it at or above 50ms, so this gateway carried no measurable throughput under that bound | 50 |
| anthropic → bedrock | throughput_rps | bound_not_met req/s | concurrency not recorded; every cleanly-served rung that reported a tail had it at or above 100ms, so this gateway carried no measurable throughput under that bound | 100 |
| anthropic → bedrock | throughput_rps | 21 req/s | concurrency 16; samples 127 | unbounded |
| bedrock → bedrock | — | — | not_declared: Pinned 0.4.39 source b13ddd632bde1fea7678386c345665ea5fa671af: hermesllm/src/clients/endpoints.rs accepts Chat, Responses and Messages ingress, with no Gemini, Cohere or Bedrock client API. providers/id.rs::compatible_api_for_client selects native Responses only for Responses ingress to OpenAI, Chat for Messages-to-OpenAI, native Messages for Messages-to-Anthropic, and Converse for all three ingress APIs to amazon_bedrock. Anthropic Chat/Responses ingress and Gemini provider use OpenAI-compatible upstream wire; they are not native Anthropic/Gemini translations. The normal provider mapping is retained rather than substituting a different provider for the OpenAI column. Seven supported pairs are enabled, including the documented Bedrock upstream. | — |
| openai → anthropic | — | — | not_declared: Pinned 0.4.39 source b13ddd632bde1fea7678386c345665ea5fa671af: hermesllm/src/clients/endpoints.rs accepts Chat, Responses and Messages ingress, with no Gemini, Cohere or Bedrock client API. providers/id.rs::compatible_api_for_client selects native Responses only for Responses ingress to OpenAI, Chat for Messages-to-OpenAI, native Messages for Messages-to-Anthropic, and Converse for all three ingress APIs to amazon_bedrock. Anthropic Chat/Responses ingress and Gemini provider use OpenAI-compatible upstream wire; they are not native Anthropic/Gemini translations. The normal provider mapping is retained rather than substituting a different provider for the OpenAI column. Seven supported pairs are enabled, including the documented Bedrock upstream. | — |
| openai-responses → anthropic | — | — | not_declared: Pinned 0.4.39 source b13ddd632bde1fea7678386c345665ea5fa671af: hermesllm/src/clients/endpoints.rs accepts Chat, Responses and Messages ingress, with no Gemini, Cohere or Bedrock client API. providers/id.rs::compatible_api_for_client selects native Responses only for Responses ingress to OpenAI, Chat for Messages-to-OpenAI, native Messages for Messages-to-Anthropic, and Converse for all three ingress APIs to amazon_bedrock. Anthropic Chat/Responses ingress and Gemini provider use OpenAI-compatible upstream wire; they are not native Anthropic/Gemini translations. The normal provider mapping is retained rather than substituting a different provider for the OpenAI column. Seven supported pairs are enabled, including the documented Bedrock upstream. | — |
| anthropic → anthropic | added_latency_p50_us | 193933 | valid; gateway_c1_samples=31; direct_c1_samples=264589 | — |
| anthropic → anthropic | added_latency_p99_us | 195022 | valid; gateway_c1_samples=31; direct_c1_samples=264589 | — |
| anthropic → anthropic | gateway_c1_p99_us | 195049 | valid; gateway_c1_samples=31 | — |
| anthropic → anthropic | direct_c1_p99_us | 27 | valid; direct_c1_samples=264589 | — |
| anthropic → anthropic | cpu_us_per_request | 181353.38345864663 | valid | — |
| anthropic → anthropic | rps_per_cpu_second | 5.514096185737976 | valid | — |
| anthropic → anthropic | cost_window_conc | 8 | valid | — |
| anthropic → anthropic | cost_core_utilisation | 0.9610214676333437 | valid | — |
| anthropic → anthropic | cost_window_ok | 133 | valid | — |
| anthropic → anthropic | cost_window_rps | 22 | valid | — |
| anthropic → anthropic | cost_threads | 69 | valid | — |
| anthropic → anthropic | cost_nonvol_ctxt_per_request | 5.879699248120301 | valid | — |
| anthropic → anthropic | cost_majflt | 0 | valid | — |
| anthropic → anthropic | added_ttft_p50_us | 153935 | valid; ttft_gw_samples=100; ttft_direct_samples=100 | — |
| anthropic → anthropic | added_ttft_p99_us | 165859 | valid; ttft_gw_samples=100; ttft_direct_samples=100 | — |
| anthropic → anthropic | added_gap_p50_us | below_resolution | below_resolution; gap_gw_samples=63; gap_direct_samples=63 | — |
| anthropic → anthropic | added_gap_p99_us | below_resolution | below_resolution; gap_gw_samples=63; gap_direct_samples=63 | — |
| anthropic → anthropic | streams_sustained_fps | 919.9861683706454 | valid | — |
| anthropic → anthropic | streams_sustained | 65 | valid | — |
| anthropic → anthropic | idle_rss_mib | 593.06640625 | valid | — |
| anthropic → anthropic | steady_state_rss_mib | 948.5078125 | valid | — |
| anthropic → anthropic | recovered_rss_mib | 948.43359375 | valid | — |
| anthropic → anthropic | peak_rss_mib | 949.0078125 | valid | — |
| anthropic → anthropic | peak_rss_hwm_mib | 948.77734375 | valid | — |
| anthropic → anthropic | time_to_plateau_s | 67 | valid | — |
| anthropic → anthropic | growth_rate_mib_per_min | -0.30135980491154135 | valid | — |
| anthropic → anthropic | load_s | 303 | valid | — |
| anthropic → anthropic | shape | not_measured | not_measured | — |
| anthropic → anthropic | idle_shape | not_measured | not_measured | — |
| anthropic → anthropic | idle_static | 1 | valid | — |
| anthropic → anthropic | idle_growth_rate_mib_per_min | 0.05169704844231903 | valid | — |
| anthropic → anthropic | throughput_rps | bound_not_met req/s | concurrency not recorded; every cleanly-served rung that reported a tail had it at or above 1ms, so this gateway carried no measurable throughput under that bound | 1 |
| anthropic → anthropic | throughput_rps | bound_not_met req/s | concurrency not recorded; every cleanly-served rung that reported a tail had it at or above 5ms, so this gateway carried no measurable throughput under that bound | 5 |
| anthropic → anthropic | throughput_rps | bound_not_met req/s | concurrency not recorded; every cleanly-served rung that reported a tail had it at or above 10ms, so this gateway carried no measurable throughput under that bound | 10 |
| anthropic → anthropic | throughput_rps | bound_not_met req/s | concurrency not recorded; every cleanly-served rung that reported a tail had it at or above 50ms, so this gateway carried no measurable throughput under that bound | 50 |
| anthropic → anthropic | throughput_rps | bound_not_met req/s | concurrency not recorded; every cleanly-served rung that reported a tail had it at or above 100ms, so this gateway carried no measurable throughput under that bound | 100 |
| anthropic → anthropic | throughput_rps | 21 req/s | concurrency 8; samples 128 | unbounded |
| cohere → anthropic | — | — | not_declared: Pinned 0.4.39 source b13ddd632bde1fea7678386c345665ea5fa671af: hermesllm/src/clients/endpoints.rs accepts Chat, Responses and Messages ingress, with no Gemini, Cohere or Bedrock client API. providers/id.rs::compatible_api_for_client selects native Responses only for Responses ingress to OpenAI, Chat for Messages-to-OpenAI, native Messages for Messages-to-Anthropic, and Converse for all three ingress APIs to amazon_bedrock. Anthropic Chat/Responses ingress and Gemini provider use OpenAI-compatible upstream wire; they are not native Anthropic/Gemini translations. The normal provider mapping is retained rather than substituting a different provider for the OpenAI column. Seven supported pairs are enabled, including the documented Bedrock upstream. | — |
| gemini → anthropic | — | — | not_declared: Pinned 0.4.39 source b13ddd632bde1fea7678386c345665ea5fa671af: hermesllm/src/clients/endpoints.rs accepts Chat, Responses and Messages ingress, with no Gemini, Cohere or Bedrock client API. providers/id.rs::compatible_api_for_client selects native Responses only for Responses ingress to OpenAI, Chat for Messages-to-OpenAI, native Messages for Messages-to-Anthropic, and Converse for all three ingress APIs to amazon_bedrock. Anthropic Chat/Responses ingress and Gemini provider use OpenAI-compatible upstream wire; they are not native Anthropic/Gemini translations. The normal provider mapping is retained rather than substituting a different provider for the OpenAI column. Seven supported pairs are enabled, including the documented Bedrock upstream. | — |
| bedrock → anthropic | — | — | not_declared: Pinned 0.4.39 source b13ddd632bde1fea7678386c345665ea5fa671af: hermesllm/src/clients/endpoints.rs accepts Chat, Responses and Messages ingress, with no Gemini, Cohere or Bedrock client API. providers/id.rs::compatible_api_for_client selects native Responses only for Responses ingress to OpenAI, Chat for Messages-to-OpenAI, native Messages for Messages-to-Anthropic, and Converse for all three ingress APIs to amazon_bedrock. Anthropic Chat/Responses ingress and Gemini provider use OpenAI-compatible upstream wire; they are not native Anthropic/Gemini translations. The normal provider mapping is retained rather than substituting a different provider for the OpenAI column. Seven supported pairs are enabled, including the documented Bedrock upstream. | — |
| anthropic → openai-responses | — | — | not_declared: Pinned 0.4.39 source b13ddd632bde1fea7678386c345665ea5fa671af: hermesllm/src/clients/endpoints.rs accepts Chat, Responses and Messages ingress, with no Gemini, Cohere or Bedrock client API. providers/id.rs::compatible_api_for_client selects native Responses only for Responses ingress to OpenAI, Chat for Messages-to-OpenAI, native Messages for Messages-to-Anthropic, and Converse for all three ingress APIs to amazon_bedrock. Anthropic Chat/Responses ingress and Gemini provider use OpenAI-compatible upstream wire; they are not native Anthropic/Gemini translations. The normal provider mapping is retained rather than substituting a different provider for the OpenAI column. Seven supported pairs are enabled, including the documented Bedrock upstream. | — |
| gemini → openai-responses | — | — | not_declared: Pinned 0.4.39 source b13ddd632bde1fea7678386c345665ea5fa671af: hermesllm/src/clients/endpoints.rs accepts Chat, Responses and Messages ingress, with no Gemini, Cohere or Bedrock client API. providers/id.rs::compatible_api_for_client selects native Responses only for Responses ingress to OpenAI, Chat for Messages-to-OpenAI, native Messages for Messages-to-Anthropic, and Converse for all three ingress APIs to amazon_bedrock. Anthropic Chat/Responses ingress and Gemini provider use OpenAI-compatible upstream wire; they are not native Anthropic/Gemini translations. The normal provider mapping is retained rather than substituting a different provider for the OpenAI column. Seven supported pairs are enabled, including the documented Bedrock upstream. | — |
| openai → openai-responses | — | — | not_declared: Pinned 0.4.39 source b13ddd632bde1fea7678386c345665ea5fa671af: hermesllm/src/clients/endpoints.rs accepts Chat, Responses and Messages ingress, with no Gemini, Cohere or Bedrock client API. providers/id.rs::compatible_api_for_client selects native Responses only for Responses ingress to OpenAI, Chat for Messages-to-OpenAI, native Messages for Messages-to-Anthropic, and Converse for all three ingress APIs to amazon_bedrock. Anthropic Chat/Responses ingress and Gemini provider use OpenAI-compatible upstream wire; they are not native Anthropic/Gemini translations. The normal provider mapping is retained rather than substituting a different provider for the OpenAI column. Seven supported pairs are enabled, including the documented Bedrock upstream. | — |
| openai-responses → openai-responses | added_latency_p50_us | 194984 | valid; gateway_c1_samples=30; direct_c1_samples=268348 | — |
| openai-responses → openai-responses | added_latency_p99_us | 198964 | valid; gateway_c1_samples=30; direct_c1_samples=268348 | — |
| openai-responses → openai-responses | gateway_c1_p99_us | 198991 | valid; gateway_c1_samples=30 | — |
| openai-responses → openai-responses | direct_c1_p99_us | 27 | valid; direct_c1_samples=268348 | — |
| openai-responses → openai-responses | cpu_us_per_request | 177760 | valid | — |
| openai-responses → openai-responses | rps_per_cpu_second | 5.625562556255626 | valid | — |
| openai-responses → openai-responses | cost_window_conc | 8 | valid | — |
| openai-responses → openai-responses | cost_core_utilisation | 0.8678710026382068 | valid | — |
| openai-responses → openai-responses | cost_window_ok | 125 | valid | — |
| openai-responses → openai-responses | cost_window_rps | 20 | valid | — |
| openai-responses → openai-responses | cost_threads | 68 | valid | — |
| openai-responses → openai-responses | cost_nonvol_ctxt_per_request | 4.712 | valid | — |
| openai-responses → openai-responses | cost_majflt | 0 | valid | — |
| openai-responses → openai-responses | added_ttft_p50_us | untestable | untestable | — |
| openai-responses → openai-responses | added_ttft_p99_us | untestable | untestable | — |
| openai-responses → openai-responses | added_gap_p50_us | untestable | untestable | — |
| openai-responses → openai-responses | added_gap_p99_us | untestable | untestable | — |
| openai-responses → openai-responses | streams_sustained_fps | untestable | untestable | — |
| openai-responses → openai-responses | streams_sustained | untestable | untestable | — |
| openai-responses → openai-responses | idle_rss_mib | 611.9609375 | valid | — |
| openai-responses → openai-responses | steady_state_rss_mib | 1019.71484375 | valid | — |
| openai-responses → openai-responses | recovered_rss_mib | 1019.88671875 | valid | — |
| openai-responses → openai-responses | peak_rss_mib | 1019.96875 | valid | — |
| openai-responses → openai-responses | peak_rss_hwm_mib | 1019.88671875 | valid | — |
| openai-responses → openai-responses | time_to_plateau_s | 66 | valid | — |
| openai-responses → openai-responses | growth_rate_mib_per_min | -0.19858581951462687 | valid | — |
| openai-responses → openai-responses | load_s | 301 | valid | — |
| openai-responses → openai-responses | shape | not_measured | not_measured | — |
| openai-responses → openai-responses | idle_shape | not_measured | not_measured | — |
| openai-responses → openai-responses | idle_static | 1 | valid | — |
| openai-responses → openai-responses | idle_growth_rate_mib_per_min | 0.04586307382763456 | valid | — |
| openai-responses → openai-responses | throughput_rps | bound_not_met req/s | concurrency not recorded; every cleanly-served rung that reported a tail had it at or above 1ms, so this gateway carried no measurable throughput under that bound | 1 |
| openai-responses → openai-responses | throughput_rps | bound_not_met req/s | concurrency not recorded; every cleanly-served rung that reported a tail had it at or above 5ms, so this gateway carried no measurable throughput under that bound | 5 |
| openai-responses → openai-responses | throughput_rps | bound_not_met req/s | concurrency not recorded; every cleanly-served rung that reported a tail had it at or above 10ms, so this gateway carried no measurable throughput under that bound | 10 |
| openai-responses → openai-responses | throughput_rps | bound_not_met req/s | concurrency not recorded; every cleanly-served rung that reported a tail had it at or above 50ms, so this gateway carried no measurable throughput under that bound | 50 |
| openai-responses → openai-responses | throughput_rps | bound_not_met req/s | concurrency not recorded; every cleanly-served rung that reported a tail had it at or above 100ms, so this gateway carried no measurable throughput under that bound | 100 |
| openai-responses → openai-responses | throughput_rps | 21 req/s | concurrency 16; samples 127 | unbounded |
| cohere → openai-responses | — | — | not_declared: Pinned 0.4.39 source b13ddd632bde1fea7678386c345665ea5fa671af: hermesllm/src/clients/endpoints.rs accepts Chat, Responses and Messages ingress, with no Gemini, Cohere or Bedrock client API. providers/id.rs::compatible_api_for_client selects native Responses only for Responses ingress to OpenAI, Chat for Messages-to-OpenAI, native Messages for Messages-to-Anthropic, and Converse for all three ingress APIs to amazon_bedrock. Anthropic Chat/Responses ingress and Gemini provider use OpenAI-compatible upstream wire; they are not native Anthropic/Gemini translations. The normal provider mapping is retained rather than substituting a different provider for the OpenAI column. Seven supported pairs are enabled, including the documented Bedrock upstream. | — |
| bedrock → openai-responses | — | — | not_declared: Pinned 0.4.39 source b13ddd632bde1fea7678386c345665ea5fa671af: hermesllm/src/clients/endpoints.rs accepts Chat, Responses and Messages ingress, with no Gemini, Cohere or Bedrock client API. providers/id.rs::compatible_api_for_client selects native Responses only for Responses ingress to OpenAI, Chat for Messages-to-OpenAI, native Messages for Messages-to-Anthropic, and Converse for all three ingress APIs to amazon_bedrock. Anthropic Chat/Responses ingress and Gemini provider use OpenAI-compatible upstream wire; they are not native Anthropic/Gemini translations. The normal provider mapping is retained rather than substituting a different provider for the OpenAI column. Seven supported pairs are enabled, including the documented Bedrock upstream. | — |
| cohere → gemini | — | — | not_declared: Pinned 0.4.39 source b13ddd632bde1fea7678386c345665ea5fa671af: hermesllm/src/clients/endpoints.rs accepts Chat, Responses and Messages ingress, with no Gemini, Cohere or Bedrock client API. providers/id.rs::compatible_api_for_client selects native Responses only for Responses ingress to OpenAI, Chat for Messages-to-OpenAI, native Messages for Messages-to-Anthropic, and Converse for all three ingress APIs to amazon_bedrock. Anthropic Chat/Responses ingress and Gemini provider use OpenAI-compatible upstream wire; they are not native Anthropic/Gemini translations. The normal provider mapping is retained rather than substituting a different provider for the OpenAI column. Seven supported pairs are enabled, including the documented Bedrock upstream. | — |
| openai → gemini | — | — | not_declared: Pinned 0.4.39 source b13ddd632bde1fea7678386c345665ea5fa671af: hermesllm/src/clients/endpoints.rs accepts Chat, Responses and Messages ingress, with no Gemini, Cohere or Bedrock client API. providers/id.rs::compatible_api_for_client selects native Responses only for Responses ingress to OpenAI, Chat for Messages-to-OpenAI, native Messages for Messages-to-Anthropic, and Converse for all three ingress APIs to amazon_bedrock. Anthropic Chat/Responses ingress and Gemini provider use OpenAI-compatible upstream wire; they are not native Anthropic/Gemini translations. The normal provider mapping is retained rather than substituting a different provider for the OpenAI column. Seven supported pairs are enabled, including the documented Bedrock upstream. | — |
| openai-responses → gemini | — | — | not_declared: Pinned 0.4.39 source b13ddd632bde1fea7678386c345665ea5fa671af: hermesllm/src/clients/endpoints.rs accepts Chat, Responses and Messages ingress, with no Gemini, Cohere or Bedrock client API. providers/id.rs::compatible_api_for_client selects native Responses only for Responses ingress to OpenAI, Chat for Messages-to-OpenAI, native Messages for Messages-to-Anthropic, and Converse for all three ingress APIs to amazon_bedrock. Anthropic Chat/Responses ingress and Gemini provider use OpenAI-compatible upstream wire; they are not native Anthropic/Gemini translations. The normal provider mapping is retained rather than substituting a different provider for the OpenAI column. Seven supported pairs are enabled, including the documented Bedrock upstream. | — |
| anthropic → gemini | — | — | not_declared: Pinned 0.4.39 source b13ddd632bde1fea7678386c345665ea5fa671af: hermesllm/src/clients/endpoints.rs accepts Chat, Responses and Messages ingress, with no Gemini, Cohere or Bedrock client API. providers/id.rs::compatible_api_for_client selects native Responses only for Responses ingress to OpenAI, Chat for Messages-to-OpenAI, native Messages for Messages-to-Anthropic, and Converse for all three ingress APIs to amazon_bedrock. Anthropic Chat/Responses ingress and Gemini provider use OpenAI-compatible upstream wire; they are not native Anthropic/Gemini translations. The normal provider mapping is retained rather than substituting a different provider for the OpenAI column. Seven supported pairs are enabled, including the documented Bedrock upstream. | — |
| gemini → gemini | — | — | not_declared: Pinned 0.4.39 source b13ddd632bde1fea7678386c345665ea5fa671af: hermesllm/src/clients/endpoints.rs accepts Chat, Responses and Messages ingress, with no Gemini, Cohere or Bedrock client API. providers/id.rs::compatible_api_for_client selects native Responses only for Responses ingress to OpenAI, Chat for Messages-to-OpenAI, native Messages for Messages-to-Anthropic, and Converse for all three ingress APIs to amazon_bedrock. Anthropic Chat/Responses ingress and Gemini provider use OpenAI-compatible upstream wire; they are not native Anthropic/Gemini translations. The normal provider mapping is retained rather than substituting a different provider for the OpenAI column. Seven supported pairs are enabled, including the documented Bedrock upstream. | — |
| bedrock → gemini | — | — | not_declared: Pinned 0.4.39 source b13ddd632bde1fea7678386c345665ea5fa671af: hermesllm/src/clients/endpoints.rs accepts Chat, Responses and Messages ingress, with no Gemini, Cohere or Bedrock client API. providers/id.rs::compatible_api_for_client selects native Responses only for Responses ingress to OpenAI, Chat for Messages-to-OpenAI, native Messages for Messages-to-Anthropic, and Converse for all three ingress APIs to amazon_bedrock. Anthropic Chat/Responses ingress and Gemini provider use OpenAI-compatible upstream wire; they are not native Anthropic/Gemini translations. The normal provider mapping is retained rather than substituting a different provider for the OpenAI column. Seven supported pairs are enabled, including the documented Bedrock upstream. | — |
| openai-responses → cohere | — | — | not_declared: Pinned 0.4.39 source b13ddd632bde1fea7678386c345665ea5fa671af: hermesllm/src/clients/endpoints.rs accepts Chat, Responses and Messages ingress, with no Gemini, Cohere or Bedrock client API. providers/id.rs::compatible_api_for_client selects native Responses only for Responses ingress to OpenAI, Chat for Messages-to-OpenAI, native Messages for Messages-to-Anthropic, and Converse for all three ingress APIs to amazon_bedrock. Anthropic Chat/Responses ingress and Gemini provider use OpenAI-compatible upstream wire; they are not native Anthropic/Gemini translations. The normal provider mapping is retained rather than substituting a different provider for the OpenAI column. Seven supported pairs are enabled, including the documented Bedrock upstream. | — |
| cohere → cohere | — | — | not_declared: Pinned 0.4.39 source b13ddd632bde1fea7678386c345665ea5fa671af: hermesllm/src/clients/endpoints.rs accepts Chat, Responses and Messages ingress, with no Gemini, Cohere or Bedrock client API. providers/id.rs::compatible_api_for_client selects native Responses only for Responses ingress to OpenAI, Chat for Messages-to-OpenAI, native Messages for Messages-to-Anthropic, and Converse for all three ingress APIs to amazon_bedrock. Anthropic Chat/Responses ingress and Gemini provider use OpenAI-compatible upstream wire; they are not native Anthropic/Gemini translations. The normal provider mapping is retained rather than substituting a different provider for the OpenAI column. Seven supported pairs are enabled, including the documented Bedrock upstream. | — |
| openai → cohere | — | — | not_declared: Pinned 0.4.39 source b13ddd632bde1fea7678386c345665ea5fa671af: hermesllm/src/clients/endpoints.rs accepts Chat, Responses and Messages ingress, with no Gemini, Cohere or Bedrock client API. providers/id.rs::compatible_api_for_client selects native Responses only for Responses ingress to OpenAI, Chat for Messages-to-OpenAI, native Messages for Messages-to-Anthropic, and Converse for all three ingress APIs to amazon_bedrock. Anthropic Chat/Responses ingress and Gemini provider use OpenAI-compatible upstream wire; they are not native Anthropic/Gemini translations. The normal provider mapping is retained rather than substituting a different provider for the OpenAI column. Seven supported pairs are enabled, including the documented Bedrock upstream. | — |
| gemini → cohere | — | — | not_declared: Pinned 0.4.39 source b13ddd632bde1fea7678386c345665ea5fa671af: hermesllm/src/clients/endpoints.rs accepts Chat, Responses and Messages ingress, with no Gemini, Cohere or Bedrock client API. providers/id.rs::compatible_api_for_client selects native Responses only for Responses ingress to OpenAI, Chat for Messages-to-OpenAI, native Messages for Messages-to-Anthropic, and Converse for all three ingress APIs to amazon_bedrock. Anthropic Chat/Responses ingress and Gemini provider use OpenAI-compatible upstream wire; they are not native Anthropic/Gemini translations. The normal provider mapping is retained rather than substituting a different provider for the OpenAI column. Seven supported pairs are enabled, including the documented Bedrock upstream. | — |
| anthropic → cohere | — | — | not_declared: Pinned 0.4.39 source b13ddd632bde1fea7678386c345665ea5fa671af: hermesllm/src/clients/endpoints.rs accepts Chat, Responses and Messages ingress, with no Gemini, Cohere or Bedrock client API. providers/id.rs::compatible_api_for_client selects native Responses only for Responses ingress to OpenAI, Chat for Messages-to-OpenAI, native Messages for Messages-to-Anthropic, and Converse for all three ingress APIs to amazon_bedrock. Anthropic Chat/Responses ingress and Gemini provider use OpenAI-compatible upstream wire; they are not native Anthropic/Gemini translations. The normal provider mapping is retained rather than substituting a different provider for the OpenAI column. Seven supported pairs are enabled, including the documented Bedrock upstream. | — |
| bedrock → cohere | — | — | not_declared: Pinned 0.4.39 source b13ddd632bde1fea7678386c345665ea5fa671af: hermesllm/src/clients/endpoints.rs accepts Chat, Responses and Messages ingress, with no Gemini, Cohere or Bedrock client API. providers/id.rs::compatible_api_for_client selects native Responses only for Responses ingress to OpenAI, Chat for Messages-to-OpenAI, native Messages for Messages-to-Anthropic, and Converse for all three ingress APIs to amazon_bedrock. Anthropic Chat/Responses ingress and Gemini provider use OpenAI-compatible upstream wire; they are not native Anthropic/Gemini translations. The normal provider mapping is retained rather than substituting a different provider for the OpenAI column. Seven supported pairs are enabled, including the documented Bedrock upstream. | — |
| openai → openai | added_latency_p50_us | 198988 | valid; gateway_c1_samples=30; direct_c1_samples=266566 | — |
| openai → openai | added_latency_p99_us | 205966 | valid; gateway_c1_samples=30; direct_c1_samples=266566 | — |
| openai → openai | gateway_c1_p99_us | 205993 | valid; gateway_c1_samples=30 | — |
| openai → openai | direct_c1_p99_us | 27 | valid; direct_c1_samples=266566 | — |
| openai → openai | cpu_us_per_request | 182230.76923076922 | valid | — |
| openai → openai | rps_per_cpu_second | 5.487547488391726 | valid | — |
| openai → openai | cost_window_conc | 8 | valid | — |
| openai → openai | cost_core_utilisation | 0.9645138811621244 | valid | — |
| openai → openai | cost_window_ok | 130 | valid | — |
| openai → openai | cost_window_rps | 21 | valid | — |
| openai → openai | cost_threads | 68 | valid | — |
| openai → openai | cost_nonvol_ctxt_per_request | 6.276923076923077 | valid | — |
| openai → openai | cost_majflt | 0 | valid | — |
| openai → openai | added_ttft_p50_us | 158773 | valid; ttft_gw_samples=100; ttft_direct_samples=100 | — |
| openai → openai | added_ttft_p99_us | 170494 | valid; ttft_gw_samples=100; ttft_direct_samples=100 | — |
| openai → openai | added_gap_p50_us | 1 | valid; gap_gw_samples=63; gap_direct_samples=63 | — |
| openai → openai | added_gap_p99_us | 38 | valid; gap_gw_samples=63; gap_direct_samples=63 | — |
| openai → openai | streams_sustained_fps | 669.7194949393278 | valid | — |
| openai → openai | streams_sustained | 29 | valid | — |
| openai → openai | idle_rss_mib | 617.203125 | valid | — |
| openai → openai | steady_state_rss_mib | 971.84765625 | valid | — |
| openai → openai | recovered_rss_mib | 972.3203125 | valid | — |
| openai → openai | peak_rss_mib | 972.4453125 | valid | — |
| openai → openai | peak_rss_hwm_mib | 972.31640625 | valid | — |
| openai → openai | time_to_plateau_s | 61 | valid | — |
| openai → openai | growth_rate_mib_per_min | 0.12924042130805258 | valid | — |
| openai → openai | load_s | 305 | valid | — |
| openai → openai | shape | not_measured | not_measured | — |
| openai → openai | idle_shape | not_measured | not_measured | — |
| openai → openai | idle_static | 1 | valid | — |
| openai → openai | idle_growth_rate_mib_per_min | 0.052286481252150616 | valid | — |
| openai → openai | throughput_rps | bound_not_met req/s | concurrency not recorded; every cleanly-served rung that reported a tail had it at or above 1ms, so this gateway carried no measurable throughput under that bound | 1 |
| openai → openai | throughput_rps | bound_not_met req/s | concurrency not recorded; every cleanly-served rung that reported a tail had it at or above 5ms, so this gateway carried no measurable throughput under that bound | 5 |
| openai → openai | throughput_rps | bound_not_met req/s | concurrency not recorded; every cleanly-served rung that reported a tail had it at or above 10ms, so this gateway carried no measurable throughput under that bound | 10 |
| openai → openai | throughput_rps | bound_not_met req/s | concurrency not recorded; every cleanly-served rung that reported a tail had it at or above 50ms, so this gateway carried no measurable throughput under that bound | 50 |
| openai → openai | throughput_rps | bound_not_met req/s | concurrency not recorded; every cleanly-served rung that reported a tail had it at or above 100ms, so this gateway carried no measurable throughput under that bound | 100 |
| openai → openai | throughput_rps | 19 req/s | concurrency 8; samples 118 | unbounded |
| openai-responses → openai | — | — | not_declared: Pinned 0.4.39 source b13ddd632bde1fea7678386c345665ea5fa671af: hermesllm/src/clients/endpoints.rs accepts Chat, Responses and Messages ingress, with no Gemini, Cohere or Bedrock client API. providers/id.rs::compatible_api_for_client selects native Responses only for Responses ingress to OpenAI, Chat for Messages-to-OpenAI, native Messages for Messages-to-Anthropic, and Converse for all three ingress APIs to amazon_bedrock. Anthropic Chat/Responses ingress and Gemini provider use OpenAI-compatible upstream wire; they are not native Anthropic/Gemini translations. The normal provider mapping is retained rather than substituting a different provider for the OpenAI column. Seven supported pairs are enabled, including the documented Bedrock upstream. | — |
| bedrock → openai | — | — | not_declared: Pinned 0.4.39 source b13ddd632bde1fea7678386c345665ea5fa671af: hermesllm/src/clients/endpoints.rs accepts Chat, Responses and Messages ingress, with no Gemini, Cohere or Bedrock client API. providers/id.rs::compatible_api_for_client selects native Responses only for Responses ingress to OpenAI, Chat for Messages-to-OpenAI, native Messages for Messages-to-Anthropic, and Converse for all three ingress APIs to amazon_bedrock. Anthropic Chat/Responses ingress and Gemini provider use OpenAI-compatible upstream wire; they are not native Anthropic/Gemini translations. The normal provider mapping is retained rather than substituting a different provider for the OpenAI column. Seven supported pairs are enabled, including the documented Bedrock upstream. | — |
| anthropic → openai | added_latency_p50_us | 195998 | valid; gateway_c1_samples=30; direct_c1_samples=261879 | — |
| anthropic → openai | added_latency_p99_us | 198984 | valid; gateway_c1_samples=30; direct_c1_samples=261879 | — |
| anthropic → openai | gateway_c1_p99_us | 199012 | valid; gateway_c1_samples=30 | — |
| anthropic → openai | direct_c1_p99_us | 28 | valid; direct_c1_samples=261879 | — |
| anthropic → openai | cpu_us_per_request | 178977.27272727274 | valid | — |
| anthropic → openai | rps_per_cpu_second | 5.587301587301587 | valid | — |
| anthropic → openai | cost_window_conc | 8 | valid | — |
| anthropic → openai | cost_core_utilisation | 0.647250235848493 | valid | — |
| anthropic → openai | cost_window_ok | 88 | valid | — |
| anthropic → openai | cost_window_rps | 14 | valid | — |
| anthropic → openai | cost_threads | 84 | valid | — |
| anthropic → openai | cost_nonvol_ctxt_per_request | 5.840909090909091 | valid | — |
| anthropic → openai | cost_majflt | 0 | valid | — |
| anthropic → openai | added_ttft_p50_us | 156909 | valid; ttft_gw_samples=100; ttft_direct_samples=100 | — |
| anthropic → openai | added_ttft_p99_us | 168479 | valid; ttft_gw_samples=100; ttft_direct_samples=100 | — |
| anthropic → openai | added_gap_p50_us | below_resolution | below_resolution; gap_gw_samples=63; gap_direct_samples=63 | — |
| anthropic → openai | added_gap_p99_us | below_resolution | below_resolution; gap_gw_samples=63; gap_direct_samples=63 | — |
| anthropic → openai | streams_sustained_fps | 787.6218019669257 | valid | — |
| anthropic → openai | streams_sustained | 47 | valid | — |
| anthropic → openai | idle_rss_mib | 605.86328125 | valid | — |
| anthropic → openai | steady_state_rss_mib | 961.5234375 | valid | — |
| anthropic → openai | recovered_rss_mib | 961.328125 | valid | — |
| anthropic → openai | peak_rss_mib | 961.90625 | valid | — |
| anthropic → openai | peak_rss_hwm_mib | 961.73046875 | valid | — |
| anthropic → openai | time_to_plateau_s | 61 | valid | — |
| anthropic → openai | growth_rate_mib_per_min | 0.20581317972839427 | valid | — |
| anthropic → openai | load_s | 304 | valid | — |
| anthropic → openai | shape | not_measured | not_measured | — |
| anthropic → openai | idle_shape | not_measured | not_measured | — |
| anthropic → openai | idle_static | 1 | valid | — |
| anthropic → openai | idle_growth_rate_mib_per_min | 0.17242880842301658 | valid | — |
| anthropic → openai | throughput_rps | bound_not_met req/s | concurrency not recorded; every cleanly-served rung that reported a tail had it at or above 1ms, so this gateway carried no measurable throughput under that bound | 1 |
| anthropic → openai | throughput_rps | bound_not_met req/s | concurrency not recorded; every cleanly-served rung that reported a tail had it at or above 5ms, so this gateway carried no measurable throughput under that bound | 5 |
| anthropic → openai | throughput_rps | bound_not_met req/s | concurrency not recorded; every cleanly-served rung that reported a tail had it at or above 10ms, so this gateway carried no measurable throughput under that bound | 10 |
| anthropic → openai | throughput_rps | bound_not_met req/s | concurrency not recorded; every cleanly-served rung that reported a tail had it at or above 50ms, so this gateway carried no measurable throughput under that bound | 50 |
| anthropic → openai | throughput_rps | bound_not_met req/s | concurrency not recorded; every cleanly-served rung that reported a tail had it at or above 100ms, so this gateway carried no measurable throughput under that bound | 100 |
| anthropic → openai | throughput_rps | 21 req/s | concurrency 8; samples 128 | unbounded |
| cohere → openai | — | — | not_declared: Pinned 0.4.39 source b13ddd632bde1fea7678386c345665ea5fa671af: hermesllm/src/clients/endpoints.rs accepts Chat, Responses and Messages ingress, with no Gemini, Cohere or Bedrock client API. providers/id.rs::compatible_api_for_client selects native Responses only for Responses ingress to OpenAI, Chat for Messages-to-OpenAI, native Messages for Messages-to-Anthropic, and Converse for all three ingress APIs to amazon_bedrock. Anthropic Chat/Responses ingress and Gemini provider use OpenAI-compatible upstream wire; they are not native Anthropic/Gemini translations. The normal provider mapping is retained rather than substituting a different provider for the OpenAI column. Seven supported pairs are enabled, including the documented Bedrock upstream. | — |
| gemini → openai | — | — | not_declared: Pinned 0.4.39 source b13ddd632bde1fea7678386c345665ea5fa671af: hermesllm/src/clients/endpoints.rs accepts Chat, Responses and Messages ingress, with no Gemini, Cohere or Bedrock client API. providers/id.rs::compatible_api_for_client selects native Responses only for Responses ingress to OpenAI, Chat for Messages-to-OpenAI, native Messages for Messages-to-Anthropic, and Converse for all three ingress APIs to amazon_bedrock. Anthropic Chat/Responses ingress and Gemini provider use OpenAI-compatible upstream wire; they are not native Anthropic/Gemini translations. The normal provider mapping is retained rather than substituting a different provider for the OpenAI column. Seven supported pairs are enabled, including the documented Bedrock upstream. | — |

## Probe evidence and instrument provenance

Historical capability notes may reference an earlier product version. They are not a new probe or a current support claim. Full RSS samples remain in the immutable raw JSON.

| Ingress → upstream | Cell state | Probe HTTP status | Recorded reason | Recorded detail | Evidence scope | Response excerpt | Tested build |
| --- | --- | --- | --- | --- | --- | --- | --- |
| openai → bedrock | served | — | — | — | Recorded run evidence | — | katanemo/plano:0.4.39@sha256:35a84cb873ee5f16cded33eeda72736f90798962b7489d58650c0db7b546e9ac |
| cohere → bedrock | not_declared | — | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 2](https://onthebench.ai/#note-2) | — | katanemo/plano:0.4.39@sha256:35a84cb873ee5f16cded33eeda72736f90798962b7489d58650c0db7b546e9ac |
| gemini → bedrock | not_declared | — | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 2](https://onthebench.ai/#note-2) | — | katanemo/plano:0.4.39@sha256:35a84cb873ee5f16cded33eeda72736f90798962b7489d58650c0db7b546e9ac |
| openai-responses → bedrock | served | — | — | — | Recorded run evidence | — | katanemo/plano:0.4.39@sha256:35a84cb873ee5f16cded33eeda72736f90798962b7489d58650c0db7b546e9ac |
| anthropic → bedrock | served | — | — | — | Recorded run evidence | — | katanemo/plano:0.4.39@sha256:35a84cb873ee5f16cded33eeda72736f90798962b7489d58650c0db7b546e9ac |
| bedrock → bedrock | not_declared | — | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 2](https://onthebench.ai/#note-2) | — | katanemo/plano:0.4.39@sha256:35a84cb873ee5f16cded33eeda72736f90798962b7489d58650c0db7b546e9ac |
| openai → anthropic | not_declared | — | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 2](https://onthebench.ai/#note-2) | — | katanemo/plano:0.4.39@sha256:35a84cb873ee5f16cded33eeda72736f90798962b7489d58650c0db7b546e9ac |
| openai-responses → anthropic | not_declared | — | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 2](https://onthebench.ai/#note-2) | — | katanemo/plano:0.4.39@sha256:35a84cb873ee5f16cded33eeda72736f90798962b7489d58650c0db7b546e9ac |
| anthropic → anthropic | served | — | — | — | Recorded run evidence | — | katanemo/plano:0.4.39@sha256:35a84cb873ee5f16cded33eeda72736f90798962b7489d58650c0db7b546e9ac |
| cohere → anthropic | not_declared | — | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 2](https://onthebench.ai/#note-2) | — | katanemo/plano:0.4.39@sha256:35a84cb873ee5f16cded33eeda72736f90798962b7489d58650c0db7b546e9ac |
| gemini → anthropic | not_declared | — | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 2](https://onthebench.ai/#note-2) | — | katanemo/plano:0.4.39@sha256:35a84cb873ee5f16cded33eeda72736f90798962b7489d58650c0db7b546e9ac |
| bedrock → anthropic | not_declared | — | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 2](https://onthebench.ai/#note-2) | — | katanemo/plano:0.4.39@sha256:35a84cb873ee5f16cded33eeda72736f90798962b7489d58650c0db7b546e9ac |
| anthropic → openai-responses | not_declared | — | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 2](https://onthebench.ai/#note-2) | — | katanemo/plano:0.4.39@sha256:35a84cb873ee5f16cded33eeda72736f90798962b7489d58650c0db7b546e9ac |
| gemini → openai-responses | not_declared | — | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 2](https://onthebench.ai/#note-2) | — | katanemo/plano:0.4.39@sha256:35a84cb873ee5f16cded33eeda72736f90798962b7489d58650c0db7b546e9ac |
| openai → openai-responses | not_declared | — | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 2](https://onthebench.ai/#note-2) | — | katanemo/plano:0.4.39@sha256:35a84cb873ee5f16cded33eeda72736f90798962b7489d58650c0db7b546e9ac |
| openai-responses → openai-responses | served | — | — | — | Recorded run evidence | — | katanemo/plano:0.4.39@sha256:35a84cb873ee5f16cded33eeda72736f90798962b7489d58650c0db7b546e9ac |
| cohere → openai-responses | not_declared | — | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 2](https://onthebench.ai/#note-2) | — | katanemo/plano:0.4.39@sha256:35a84cb873ee5f16cded33eeda72736f90798962b7489d58650c0db7b546e9ac |
| bedrock → openai-responses | not_declared | — | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 2](https://onthebench.ai/#note-2) | — | katanemo/plano:0.4.39@sha256:35a84cb873ee5f16cded33eeda72736f90798962b7489d58650c0db7b546e9ac |
| cohere → gemini | not_declared | — | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 2](https://onthebench.ai/#note-2) | — | katanemo/plano:0.4.39@sha256:35a84cb873ee5f16cded33eeda72736f90798962b7489d58650c0db7b546e9ac |
| openai → gemini | not_declared | — | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 2](https://onthebench.ai/#note-2) | — | katanemo/plano:0.4.39@sha256:35a84cb873ee5f16cded33eeda72736f90798962b7489d58650c0db7b546e9ac |
| openai-responses → gemini | not_declared | — | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 2](https://onthebench.ai/#note-2) | — | katanemo/plano:0.4.39@sha256:35a84cb873ee5f16cded33eeda72736f90798962b7489d58650c0db7b546e9ac |
| anthropic → gemini | not_declared | — | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 2](https://onthebench.ai/#note-2) | — | katanemo/plano:0.4.39@sha256:35a84cb873ee5f16cded33eeda72736f90798962b7489d58650c0db7b546e9ac |
| gemini → gemini | not_declared | — | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 2](https://onthebench.ai/#note-2) | — | katanemo/plano:0.4.39@sha256:35a84cb873ee5f16cded33eeda72736f90798962b7489d58650c0db7b546e9ac |
| bedrock → gemini | not_declared | — | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 2](https://onthebench.ai/#note-2) | — | katanemo/plano:0.4.39@sha256:35a84cb873ee5f16cded33eeda72736f90798962b7489d58650c0db7b546e9ac |
| openai-responses → cohere | not_declared | — | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 2](https://onthebench.ai/#note-2) | — | katanemo/plano:0.4.39@sha256:35a84cb873ee5f16cded33eeda72736f90798962b7489d58650c0db7b546e9ac |
| cohere → cohere | not_declared | — | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 2](https://onthebench.ai/#note-2) | — | katanemo/plano:0.4.39@sha256:35a84cb873ee5f16cded33eeda72736f90798962b7489d58650c0db7b546e9ac |
| openai → cohere | not_declared | — | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 2](https://onthebench.ai/#note-2) | — | katanemo/plano:0.4.39@sha256:35a84cb873ee5f16cded33eeda72736f90798962b7489d58650c0db7b546e9ac |
| gemini → cohere | not_declared | — | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 2](https://onthebench.ai/#note-2) | — | katanemo/plano:0.4.39@sha256:35a84cb873ee5f16cded33eeda72736f90798962b7489d58650c0db7b546e9ac |
| anthropic → cohere | not_declared | — | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 2](https://onthebench.ai/#note-2) | — | katanemo/plano:0.4.39@sha256:35a84cb873ee5f16cded33eeda72736f90798962b7489d58650c0db7b546e9ac |
| bedrock → cohere | not_declared | — | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 2](https://onthebench.ai/#note-2) | — | katanemo/plano:0.4.39@sha256:35a84cb873ee5f16cded33eeda72736f90798962b7489d58650c0db7b546e9ac |
| openai → openai | served | — | — | — | Recorded run evidence | — | katanemo/plano:0.4.39@sha256:35a84cb873ee5f16cded33eeda72736f90798962b7489d58650c0db7b546e9ac |
| openai-responses → openai | not_declared | — | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 2](https://onthebench.ai/#note-2) | — | katanemo/plano:0.4.39@sha256:35a84cb873ee5f16cded33eeda72736f90798962b7489d58650c0db7b546e9ac |
| bedrock → openai | not_declared | — | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 2](https://onthebench.ai/#note-2) | — | katanemo/plano:0.4.39@sha256:35a84cb873ee5f16cded33eeda72736f90798962b7489d58650c0db7b546e9ac |
| anthropic → openai | served | — | — | — | Recorded run evidence | — | katanemo/plano:0.4.39@sha256:35a84cb873ee5f16cded33eeda72736f90798962b7489d58650c0db7b546e9ac |
| cohere → openai | not_declared | — | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 2](https://onthebench.ai/#note-2) | — | katanemo/plano:0.4.39@sha256:35a84cb873ee5f16cded33eeda72736f90798962b7489d58650c0db7b546e9ac |
| gemini → openai | not_declared | — | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 1](https://onthebench.ai/#note-1) | [recorded note 2](https://onthebench.ai/#note-2) | — | katanemo/plano:0.4.39@sha256:35a84cb873ee5f16cded33eeda72736f90798962b7489d58650c0db7b546e9ac |

**Harness commit**: `d240badd966933fa19eec0606b2d1f3945f18ad2`

**Mock SHA-256**: `99d01f709d8d9c1f49055aa265d5eb7475264d6b513911fe317aee74a71190f8`

**Load generator SHA-256**: `not recorded`

**somaxconn**: 65535

**tcp_max_syn_backlog**: 65535

## Stream sweep diagnostics

Per streaming-sweep concurrency, as recorded by the engine: lanes by final HTTP status, and lanes that received no response.

| Ingress → upstream | Concurrency | Lanes by HTTP status | Lanes with no response |
| --- | --- | --- | --- |
| anthropic → anthropic | 1 | {"200":1} | 0 |
| anthropic → anthropic | 2 | {"200":2} | 0 |
| anthropic → anthropic | 4 | {"200":4} | 0 |
| anthropic → anthropic | 8 | {"200":8} | 0 |
| anthropic → anthropic | 16 | {"200":16} | 0 |
| anthropic → anthropic | 32 | {"200":32} | 0 |
| anthropic → anthropic | 64 | {"200":64} | 0 |
| anthropic → anthropic | 128 | {"200":128} | 0 |
| anthropic → anthropic | 96 | {"200":96} | 0 |
| anthropic → anthropic | 80 | {"200":80} | 0 |
| anthropic → anthropic | 72 | {"200":72} | 0 |
| anthropic → anthropic | 68 | {"200":68} | 0 |
| anthropic → anthropic | 66 | {"200":66} | 0 |
| anthropic → anthropic | 65 | {"200":65} | 0 |
| anthropic → anthropic | 65 | {"200":65} | 0 |
| anthropic → anthropic | 65 | {"200":65} | 0 |
| openai → openai | 1 | {"200":1} | 0 |
| openai → openai | 2 | {"200":2} | 0 |
| openai → openai | 4 | {"200":4} | 0 |
| openai → openai | 8 | {"200":8} | 0 |
| openai → openai | 16 | {"200":16} | 0 |
| openai → openai | 32 | {"200":32} | 0 |
| openai → openai | 24 | {"200":24} | 0 |
| openai → openai | 28 | {"200":28} | 0 |
| openai → openai | 30 | {"200":30} | 0 |
| openai → openai | 29 | {"200":29} | 0 |
| openai → openai | 29 | {"200":29} | 0 |
| openai → openai | 29 | {"200":29} | 0 |
| anthropic → openai | 1 | {"200":1} | 0 |
| anthropic → openai | 2 | {"200":2} | 0 |
| anthropic → openai | 4 | {"200":4} | 0 |
| anthropic → openai | 8 | {"200":8} | 0 |
| anthropic → openai | 16 | {"200":16} | 0 |
| anthropic → openai | 32 | {"200":32} | 0 |
| anthropic → openai | 64 | {"200":64} | 0 |
| anthropic → openai | 48 | {"200":48} | 0 |
| anthropic → openai | 40 | {"200":40} | 0 |
| anthropic → openai | 44 | {"200":44} | 0 |
| anthropic → openai | 46 | {"200":46} | 0 |
| anthropic → openai | 47 | {"200":47} | 0 |
| anthropic → openai | 47 | {"200":47} | 0 |
| anthropic → openai | 47 | {"200":47} | 0 |

## Recorded notes

Text recorded with the cells above. Each note is shown once; rows refer to it by number.

- Pinned 0.4.39 source b13ddd632bde1fea7678386c345665ea5fa671af: hermesllm/src/clients/endpoints.rs accepts Chat, Responses and Messages ingress, with no Gemini, Cohere or Bedrock client API. providers/id.rs::compatible_api_for_client selects native Responses only for Responses ingress to OpenAI, Chat for Messages-to-OpenAI, native Messages for Messages-to-Anthropic, and Converse for all three ingress APIs to amazon_bedrock. Anthropic Chat/Responses ingress and Gemini provider use OpenAI-compatible upstream wire; they are not native Anthropic/Gemini translations. The normal provider mapping is retained rather than substituting a different provider for the OpenAI column. Seven supported pairs are enabled, including the documented Bedrock upstream.
- Historical capability research, not a fresh probe of the tested build. Referenced versions may differ from gateway_build; do not infer current capability.

## Evidence for the current measurements

- [run-plano-0a4ce97da36f11e7c407eef9280f69688b7ea1f007616709f0b914993cb8ba8e](https://onthebench.ai/gateways/runs/run-plano-0a4ce97da36f11e7c407eef9280f69688b7ea1f007616709f0b914993cb8ba8e)  ·  [complete raw record including RSS series](https://onthebench.ai/api/v1/runs/run-plano-0a4ce97da36f11e7c407eef9280f69688b7ea1f007616709f0b914993cb8ba8e/raw.json)

## Configuration recorded by the run

```
# Plano, configured as an LLM gateway pointed at the harness mock.
#
# `type: model` is the LLM listener; `type: agent` is the orchestration listener the project's README
# leads with, and it is NOT what this benchmark measures - an agent listener would put Plano's router
# and its agent hop inside a number the rest of the field takes without one.
#
# The listener port is 12000, not 10000. Plano always renders a prompt-gateway listener on 10000
# (utils.py convert_legacy_listeners), so an LLM listener on 10000 double-binds and envoy exits at
# boot with "'egress_traffic' has duplicate address '0.0.0.0:10000'". 12000 is Plano's own default
# for this listener.
#
# NO provider_interface key here, deliberately. When the model prefix is one Plano already knows -
# openai, anthropic and gemini all are - setting provider_interface as well is rejected by
# config_generator.py:445, which then exits and takes the container down with it. The prefix selects
# the interface on its own. (The error text reads "Please provide provider interface as part of model
# name", which is the reverse of what the check does; the condition is `provider in
# SUPPORTED_PROVIDERS and provider_interface is not None`.)
#
# base_url is what makes Plano testable at all: several entrants pin the vendor host and their
# upstream cells can only be recorded untestable. Plano's model_providers take base_url, so the mock
# stands in for every provider and the measured number is Plano's own cost.
#
# Provider prefixes select the released adapters. Capability declarations are source-backed in
# definition.json; correct ingress and upstream wire shapes are checked separately.
version: v0.3.0

listeners:
  - name: llm
    type: model
    port: 12000

model_providers:
  - model: openai/gpt-4o-mini
    base_url: 'http://127.0.0.1:8000'
    access_key: dummy
    default: true

  - model: anthropic/claude-3-5-sonnet
    base_url: 'http://127.0.0.1:8000'
    access_key: dummy

  - model: gemini/gemini-1.5-pro
    base_url: 'http://127.0.0.1:8000'
    access_key: dummy

  - model: amazon_bedrock/anthropic.claude-3-sonnet-20240229-v1:0
    base_url: 'http://127.0.0.1:8000'
    access_key: dummy

```

## Compare a shared protocol cell

- [Plano vs agentgateway](https://onthebench.ai/gateways/compare/plano-vs-agentgateway)
- [Plano vs AISIX (api7)](https://onthebench.ai/gateways/compare/plano-vs-aisix)
- [Plano vs APISIX](https://onthebench.ai/gateways/compare/plano-vs-apisix)
- [Plano vs Bifrost](https://onthebench.ai/gateways/compare/plano-vs-bifrost)
- [Plano vs Busbar](https://onthebench.ai/gateways/compare/plano-vs-busbar)
- [Plano vs GoModel](https://onthebench.ai/gateways/compare/plano-vs-gomodel)
- [Plano vs Helicone](https://onthebench.ai/gateways/compare/plano-vs-helicone)
- [Plano vs Higress](https://onthebench.ai/gateways/compare/plano-vs-higress)
- [Plano vs Kong](https://onthebench.ai/gateways/compare/plano-vs-kong)
- [Plano vs LiteLLM · Python](https://onthebench.ai/gateways/compare/plano-vs-litellm-python)
- [Plano vs LiteLLM · Rust](https://onthebench.ai/gateways/compare/plano-vs-litellm-rust)
- [Plano vs One-API](https://onthebench.ai/gateways/compare/plano-vs-one-api)
- [Plano vs Portkey](https://onthebench.ai/gateways/compare/plano-vs-portkey)
- [Plano vs TensorZero](https://onthebench.ai/gateways/compare/plano-vs-tensorzero)

## Historical measurements

- [2026-11-10T17:40:07Z — katanemo/plano:0.4.39@sha256:35a84cb873ee5f16cded33eeda72736f90798962b7489d58650c0db7b546e9ac](https://onthebench.ai/gateways/runs/run-plano-0a4ce97da36f11e7c407eef9280f69688b7ea1f007616709f0b914993cb8ba8e)
- [2026-08-26T19:08:45Z — katanemo/plano:0.4.36](https://onthebench.ai/gateways/runs/run-plano-5f9e8f61383353dae54dc52a3eece8e1db6e6b024d94a55a3687a3d96386130e)
