# Model API reliability on Router One

> Markdown mirror of https://router.one/benchmarks/model-reliability for AI assistants and crawlers. Router One is a unified, OpenAI-compatible LLM API gateway.
> Last updated: 2026-11-17

Success rate, rate-limit and server-error share, time to first token and throughput for every listed model with enough traffic to report, aggregated from real calls through Router One over the last 7 and 30 days.

These are observations of production traffic, not a controlled benchmark. Each model serves its own mix of prompt sizes, output lengths and reasoning settings, so the latency columns describe what callers of that model saw on Router One, not how one model's speed compares with another's. Each model's page under /models shows the same aggregates for that model.

Data read Nov 18, 2026, 10:59 AM UTC, refreshed within the hour

## Last 7 days

50 listed models, requests from 2026-11-11 to 2026-11-18 (UTC), ordered by request volume

| Model | Success 2xx | Rate limit 429 | Server 5xx | Avg. time to first token | Avg. latency | Throughput (tokens/s) |
| --- | --- | --- | --- | --- | --- | --- |
| [GPT-6.1 Sol](https://router.one/models/gpt-6-1-sol) `openai/gpt-6.1-sol` | 99.53% | 0.04% | 0.43% | 10.72 s | 14.24 s | 69.94 |
| [GPT-5.6 Luna](https://router.one/models/gpt-5-6-luna) `openai/gpt-5.6-luna` | 99.97% | 0.00% | 0.03% | 8.18 s | 2.32 s | 236.1 |
| [Gemini 3 Flash](https://router.one/models/gemini-3-flash) `google/gemini-3-flash` | 99.80% | 0.00% | 0.20% | 5.08 s | 4.62 s | 322.32 |
| [Gemini 3.8 Flash](https://router.one/models/gemini-3-8-flash) `google/gemini-3.8-flash` | 93.82% | 0.42% | 5.76% | 14.53 s | 19.1 s | 253.78 |
| [DeepSeek V4.1 Flash](https://router.one/models/deepseek-v4-1-flash) `deepseek-v4.1-flash` | 99.97% | 0.00% | 0.03% | 3.59 s | 7.94 s | 255.55 |
| [GPT-6 Sol](https://router.one/models/gpt-6-sol) `openai/gpt-6-sol` | 99.95% | 0.00% | 0.05% | 11.16 s | 10.04 s | 78.86 |
| [Claude Haiku 5.5](https://router.one/models/claude-haiku-5-5) `anthropic/claude-haiku-5.5` | 99.95% | 0.00% | 0.05% | 6.01 s | 7.92 s | 370.58 |
| [GPT-5.6 Terra](https://router.one/models/gpt-5-6-terra) `openai/gpt-5.6-terra` | 99.41% | 0.00% | 0.59% | 13.79 s | 19.89 s | 96.3 |
| [Claude Opus 5.5](https://router.one/models/claude-opus-5-5) `anthropic/claude-opus-5.5` | 99.98% | 0.00% | 0.02% | 13.24 s | 17.09 s | 420.17 |
| [Claude Sonnet 5.5](https://router.one/models/claude-sonnet-5-5) `anthropic/claude-sonnet-5.5` | 99.97% | 0.01% | 0.02% | 10.31 s | 12.3 s | 267.24 |
| [Gemini 4 Argon](https://router.one/models/gemini-4-argon) `google/gemini-4-argon` | 91.37% | 0.19% | 8.44% | 23.45 s | 33.79 s | 128.47 |
| [GPT-5.6 Sol](https://router.one/models/gpt-5-6-sol) `openai/gpt-5.6-sol` | 99.72% | 0.00% | 0.28% | 16.21 s | 22.4 s | 89.11 |
| [GPT-6 Astra](https://router.one/models/gpt-6-astra) `openai/gpt-6-astra` | 99.49% | 0.00% | 0.51% | 19.4 s | 26.86 s | 79.26 |
| [GPT-6.1 Terra](https://router.one/models/gpt-6-1-terra) `openai/gpt-6.1-terra` | 99.02% | 0.00% | 0.98% | 8.38 s | 14.17 s | 66.17 |
| [Claude Sonnet 5](https://router.one/models/claude-sonnet-5) `anthropic/claude-sonnet-5` | 99.62% | 0.00% | 0.38% | 14.46 s | 18.7 s | 246.35 |
| [Claude Sonnet 4.6 · AWS](https://router.one/models/aws-claude-sonnet-4-6) `aws/claude-sonnet-4.6` | 99.97% | 0.00% | 0.03% | — | 2.27 s | — |
| [Grok 4.5](https://router.one/models/grok-4-5) `grok-4.5` | 99.71% | 0.00% | 0.29% | 4.91 s | 23.93 s | 55.93 |
| [Grok 4.7](https://router.one/models/grok-4-7) `grok-4.7` | 99.56% | 0.00% | 0.44% | 5.2 s | 18.81 s | 65.94 |
| [Claude Sonnet 4.6](https://router.one/models/claude-sonnet-4-6) `anthropic/claude-sonnet-4.6` | 99.44% | 0.06% | 0.50% | 8.95 s | 15.3 s | 218.45 |
| [Gemini 3.8 Flash · Vertex](https://router.one/models/vertex-gemini-3-8-flash) `vertex/gemini-3.8-flash` | 98.40% | 0.04% | 1.56% | 23.33 s | 36.28 s | 166.24 |
| [DeepSeek V4 Flash](https://router.one/models/deepseek-v4-flash) `deepseek-v4-flash` | 99.98% | 0.00% | 0.02% | 2.8 s | 5.12 s | 274.89 |
| [Claude Fable 5.2](https://router.one/models/claude-fable-5-2) `anthropic/claude-fable-5.2` | 99.87% | 0.00% | 0.13% | 14.59 s | 26.64 s | 112.56 |
| [Claude Haiku 4.5](https://router.one/models/claude-haiku-4-5) `anthropic/claude-haiku-4.5` | 97.50% | 0.00% | 2.50% | 6.55 s | 8.79 s | 355.44 |
| [Gemini 3.7 Flash](https://router.one/models/gemini-3-7-flash) `google/gemini-3.7-flash` | 86.26% | 0.44% | 13.29% | 12.82 s | 21.14 s | 257.04 |
| [Gemini 4 Carbon](https://router.one/models/gemini-4-carbon) `google/gemini-4-carbon` | 93.04% | 0.04% | 6.92% | 26.86 s | 51.71 s | 91.34 |
| [GPT-6.2 Sol](https://router.one/models/gpt-6-2-sol) `openai/gpt-6.2-sol` | 98.69% | 0.09% | 1.22% | 8.39 s | 20.34 s | 51.14 |
| [Gemini 4 Hydrogen · Vertex](https://router.one/models/vertex-gemini-4-hydrogen) `vertex/gemini-4-hydrogen` | 99.22% | 0.00% | 0.78% | 23.36 s | 28.77 s | 314.88 |
| [Grok 4.6](https://router.one/models/grok-4-6) `grok-4.6` | 99.83% | 0.00% | 0.17% | 6.47 s | 37.48 s | 67.26 |
| [Gemini 4 Argon · Vertex](https://router.one/models/vertex-gemini-4-argon) `vertex/gemini-4-argon` | 73.23% | 0.00% | 26.77% | 71.89 s | 91.38 s | 72.16 |
| [Gemini 4 Argon · AI Studio](https://router.one/models/aistudio-gemini-4-argon) `aistudio/gemini-4-argon` | 75.91% | 0.00% | 24.09% | 41.26 s | 37.22 s | 65.12 |
| [Claude Opus 5](https://router.one/models/claude-opus-5) `anthropic/claude-opus-5` | 99.43% | 0.00% | 0.57% | 17.85 s | 25.81 s | 380.47 |
| [Gemini 4 Hydrogen](https://router.one/models/gemini-4-hydrogen) `google/gemini-4-hydrogen` | 80.33% | 0.00% | 19.67% | 10.75 s | 19.59 s | 511.65 |
| [Gemini 3.8 Flash · AI Studio](https://router.one/models/aistudio-gemini-3-8-flash) `aistudio/gemini-3.8-flash` | 95.00% | 0.73% | 4.27% | 13.86 s | 19.4 s | 177.25 |
| [Claude Opus 4.8](https://router.one/models/claude-opus-4-8) `anthropic/claude-opus-4.8` | 99.72% | 0.00% | 0.28% | 16.49 s | 23.37 s | 293.48 |
| [GPT-6.1 Sol · Azure](https://router.one/models/azure-gpt-6-1-sol) `azure/gpt-6.1-sol` | 99.30% | 0.00% | 0.70% | 7.54 s | 11.1 s | 100.96 |
| [Gemini 3.1 Flash Lite](https://router.one/models/gemini-3-1-flash-lite) `google/gemini-3.1-flash-lite` | 98.45% | 0.28% | 1.27% | 6.83 s | 9.9 s | 237.17 |
| [Gemini 3.5 Flash](https://router.one/models/gemini-3-5-flash) `google/gemini-3.5-flash` | 83.40% | 0.00% | 16.60% | 9.88 s | 9.12 s | 316.02 |
| [Gemini 3.5 Flash Lite · Vertex](https://router.one/models/vertex-gemini-3-5-flash-lite) `vertex/gemini-3.5-flash-lite` | 99.59% | 0.00% | 0.41% | 3.14 s | 5.48 s | 162.93 |
| [Gemini 3.6 Flash](https://router.one/models/gemini-3-6-flash) `google/gemini-3.6-flash` | 89.71% | 0.67% | 9.62% | 15.08 s | 23.17 s | 224.36 |
| [Gemini 3.7 Flash · Vertex](https://router.one/models/vertex-gemini-3-7-flash) `vertex/gemini-3.7-flash` | 99.29% | 0.00% | 0.71% | 11.18 s | 13.43 s | 130.89 |
| [Gemini 3.5 Flash Lite](https://router.one/models/gemini-3-5-flash-lite) `google/gemini-3.5-flash-lite` | 96.94% | 0.00% | 3.06% | 9.38 s | 9.48 s | 288.63 |
| [Gemini 3 Flash Preview](https://router.one/models/gemini-3-flash-preview) `google/gemini-3-flash-preview` | 98.37% | 0.54% | 1.09% | 11.06 s | 12.15 s | 254.32 |
| [GPT-6 Astra · Azure](https://router.one/models/azure-gpt-6-astra) `azure/gpt-6-astra` | 100.00% | 0.00% | 0.00% | 13.08 s | 17.48 s | 102.26 |
| [Gemini 3.5 Flash · Vertex](https://router.one/models/vertex-gemini-3-5-flash) `vertex/gemini-3.5-flash` | 97.47% | 0.00% | 2.53% | — | 10.44 s | — |
| [Claude Opus 4.6](https://router.one/models/claude-opus-4-6) `anthropic/claude-opus-4.6` | 99.16% | 0.00% | 0.84% | 12.99 s | 15.39 s | 380.7 |
| [Grok 4.7 Build Fast](https://router.one/models/grok-4-7-build-fast) `grok-4.7-build-fast` | 100.00% | 0.00% | 0.00% | 3.59 s | 35.55 s | 98.72 |
| [Gemini 3.1 Pro Preview · Vertex](https://router.one/models/vertex-gemini-3-1-pro-preview) `vertex/gemini-3.1-pro-preview` | 96.10% | 0.00% | 3.90% | — | 36.72 s | — |
| [GPT-6 Sol · Azure](https://router.one/models/azure-gpt-6-sol) `azure/gpt-6-sol` | 100.00% | 0.00% | 0.00% | 6.52 s | 6.48 s | 226.02 |
| [GPT-5.6 Luna · Azure](https://router.one/models/azure-gpt-5-6-luna) `azure/gpt-5.6-luna` | 96.47% | 0.00% | 3.53% | 4.48 s | 6.47 s | 196.04 |
| [Claude Sonnet 4.6 (thinking)](https://router.one/models/claude-sonnet-4-6-thinking) `anthropic/claude-sonnet-4.6-thinking` | 100.00% | 0.00% | 0.00% | 14.94 s | 24.65 s | 291.36 |

## Last 30 days

63 listed models, requests from 2026-10-19 to 2026-11-18 (UTC), ordered by request volume

| Model | Success 2xx | Rate limit 429 | Server 5xx | Avg. time to first token | Avg. latency | Throughput (tokens/s) |
| --- | --- | --- | --- | --- | --- | --- |
| [Gemini 3 Flash](https://router.one/models/gemini-3-flash) `google/gemini-3-flash` | 99.93% | 0.00% | 0.07% | 3.12 s | 3.05 s | 273.15 |
| [Gemini 3.8 Flash](https://router.one/models/gemini-3-8-flash) `google/gemini-3.8-flash` | 98.58% | 0.11% | 1.31% | 12.32 s | 15.26 s | 317.61 |
| [GPT-6.1 Sol](https://router.one/models/gpt-6-1-sol) `openai/gpt-6.1-sol` | 99.49% | 0.02% | 0.49% | 12.27 s | 17.56 s | 153.92 |
| [GPT-5.6 Luna · Azure](https://router.one/models/azure-gpt-5-6-luna) `azure/gpt-5.6-luna` | 99.91% | 0.03% | 0.06% | 5.48 s | 7.59 s | 269.37 |
| [DeepSeek V4.1 Flash](https://router.one/models/deepseek-v4-1-flash) `deepseek-v4.1-flash` | 99.97% | 0.00% | 0.03% | 3.91 s | 7.38 s | 266.2 |
| [GPT-5.6 Terra](https://router.one/models/gpt-5-6-terra) `openai/gpt-5.6-terra` | 99.23% | 0.00% | 0.77% | 15.18 s | 19.39 s | 116.53 |
| [GPT-5.6 Luna](https://router.one/models/gpt-5-6-luna) `openai/gpt-5.6-luna` | 99.94% | 0.00% | 0.06% | 6.13 s | 2.44 s | 209.34 |
| [GPT-6 Sol](https://router.one/models/gpt-6-sol) `openai/gpt-6-sol` | 99.85% | 0.00% | 0.15% | 10.33 s | 12.87 s | 185.04 |
| [Claude Sonnet 5.5](https://router.one/models/claude-sonnet-5-5) `anthropic/claude-sonnet-5.5` | 99.86% | 0.01% | 0.14% | 7.3 s | 12.24 s | 176.59 |
| [Claude Opus 5.5](https://router.one/models/claude-opus-5-5) `anthropic/claude-opus-5.5` | 99.71% | 0.02% | 0.26% | 12.8 s | 17.01 s | 410.26 |
| [Gemini 4 Argon](https://router.one/models/gemini-4-argon) `google/gemini-4-argon` | 97.27% | 0.04% | 2.69% | 18.64 s | 31.23 s | 108.23 |
| [GPT-6 Astra](https://router.one/models/gpt-6-astra) `openai/gpt-6-astra` | 99.51% | 0.00% | 0.49% | 13.63 s | 21.79 s | 131.91 |
| [Claude Haiku 5.5](https://router.one/models/claude-haiku-5-5) `anthropic/claude-haiku-5.5` | 99.40% | 0.01% | 0.58% | 11.32 s | 13.8 s | 212.31 |
| [GPT-5.6 Sol](https://router.one/models/gpt-5-6-sol) `openai/gpt-5.6-sol` | 99.56% | 0.00% | 0.44% | 15.05 s | 20.59 s | 112.35 |
| [Claude Sonnet 5](https://router.one/models/claude-sonnet-5) `anthropic/claude-sonnet-5` | 99.69% | 0.00% | 0.31% | 12.84 s | 18.76 s | 173.61 |
| [Gemini 3.7 Flash](https://router.one/models/gemini-3-7-flash) `google/gemini-3.7-flash` | 98.50% | 0.10% | 1.40% | 11.46 s | 16.75 s | 436.79 |
| [GPT-6.1 Terra](https://router.one/models/gpt-6-1-terra) `openai/gpt-6.1-terra` | 98.83% | 0.01% | 1.16% | 9.57 s | 12.93 s | 88.93 |
| [Grok 4.5](https://router.one/models/grok-4-5) `grok-4.5` | 99.06% | 0.01% | 0.92% | 4.98 s | 23.06 s | 59.38 |
| [Grok 4.7](https://router.one/models/grok-4-7) `grok-4.7` | 98.59% | 0.01% | 1.40% | 4.97 s | 20.25 s | 72.93 |
| [Claude Sonnet 4.6](https://router.one/models/claude-sonnet-4-6) `anthropic/claude-sonnet-4.6` | 99.65% | 0.02% | 0.33% | 9.67 s | 15.26 s | 179.44 |
| [Claude Sonnet 4.6 · AWS](https://router.one/models/aws-claude-sonnet-4-6) `aws/claude-sonnet-4.6` | 99.92% | 0.00% | 0.08% | — | 2.17 s | — |
| [Claude Haiku 4.5](https://router.one/models/claude-haiku-4-5) `anthropic/claude-haiku-4.5` | 99.15% | 0.00% | 0.85% | 4.64 s | 7.5 s | 225.23 |
| [Grok 4.6](https://router.one/models/grok-4-6) `grok-4.6` | 99.08% | 0.01% | 0.91% | 6.18 s | 39.92 s | 66.86 |
| [DeepSeek V4 Flash](https://router.one/models/deepseek-v4-flash) `deepseek-v4-flash` | 99.95% | 0.00% | 0.05% | 2.58 s | 4.78 s | 255.25 |
| [Gemini 4 Argon · Vertex](https://router.one/models/vertex-gemini-4-argon) `vertex/gemini-4-argon` | 88.45% | 1.66% | 9.90% | 41.59 s | 59.7 s | 75.39 |
| [Gemini 3.8 Flash · Vertex](https://router.one/models/vertex-gemini-3-8-flash) `vertex/gemini-3.8-flash` | 97.80% | 0.37% | 1.83% | 23.46 s | 38.33 s | 150.65 |
| [Gemini 3.5 Flash Lite](https://router.one/models/gemini-3-5-flash-lite) `google/gemini-3.5-flash-lite` | 99.73% | 0.00% | 0.27% | 3.31 s | 5.22 s | 266.76 |
| [Claude Opus 5](https://router.one/models/claude-opus-5) `anthropic/claude-opus-5` | 99.44% | 0.00% | 0.56% | 14.78 s | 23.3 s | 232.43 |
| [Gemini 3.1 Flash Lite](https://router.one/models/gemini-3-1-flash-lite) `google/gemini-3.1-flash-lite` | 99.59% | 0.05% | 0.36% | 3.4 s | 5.85 s | 261.87 |
| [Claude Sonnet 4.6 (thinking)](https://router.one/models/claude-sonnet-4-6-thinking) `anthropic/claude-sonnet-4.6-thinking` | 99.88% | 0.00% | 0.12% | 8.75 s | 19.69 s | 160.87 |
| [Claude Fable 5.2](https://router.one/models/claude-fable-5-2) `anthropic/claude-fable-5.2` | 99.87% | 0.00% | 0.13% | 14.6 s | 26.6 s | 112.69 |
| [Gemini 3.5 Flash](https://router.one/models/gemini-3-5-flash) `google/gemini-3.5-flash` | 97.44% | 0.00% | 2.56% | 6.89 s | 11.51 s | 264.39 |
| [Claude Fable 5.1](https://router.one/models/claude-fable-5-1) `anthropic/claude-fable-5.1` | 99.91% | 0.00% | 0.09% | 19.88 s | 26.12 s | 183.01 |
| [Gemini 4 Carbon](https://router.one/models/gemini-4-carbon) `google/gemini-4-carbon` | 93.38% | 0.03% | 6.58% | 26.87 s | 50.79 s | 91.96 |
| [Gemini 3.8 Flash · AI Studio](https://router.one/models/aistudio-gemini-3-8-flash) `aistudio/gemini-3.8-flash` | 97.03% | 0.23% | 2.75% | 26.67 s | 30.04 s | 212.61 |
| [Gemini 4 Argon · AI Studio](https://router.one/models/aistudio-gemini-4-argon) `aistudio/gemini-4-argon` | 81.16% | 0.00% | 18.84% | 31.54 s | 36.68 s | 71.68 |
| [Codex Auto Review](https://router.one/models/codex-auto-review) `codex-auto-review` | 98.89% | 0.00% | 1.11% | 8.61 s | 12.28 s | 76.8 |
| [GPT-6.2 Sol](https://router.one/models/gpt-6-2-sol) `openai/gpt-6.2-sol` | 98.69% | 0.09% | 1.22% | 8.39 s | 20.34 s | 51.14 |
| [Claude Opus 4.8](https://router.one/models/claude-opus-4-8) `anthropic/claude-opus-4.8` | 99.65% | 0.00% | 0.35% | 17.17 s | 33.81 s | 263.42 |
| [Gemini 4 Hydrogen · Vertex](https://router.one/models/vertex-gemini-4-hydrogen) `vertex/gemini-4-hydrogen` | 99.22% | 0.00% | 0.78% | 23.36 s | 28.77 s | 314.88 |
| [Claude Opus 4.6](https://router.one/models/claude-opus-4-6) `anthropic/claude-opus-4.6` | 98.90% | 0.00% | 1.10% | 9.85 s | 13.89 s | 200.32 |
| [Gemini 3.6 Flash](https://router.one/models/gemini-3-6-flash) `google/gemini-3.6-flash` | 97.07% | 0.53% | 2.40% | 12.1 s | 11.91 s | 297.76 |
| [GPT-6.1 Sol · Azure](https://router.one/models/azure-gpt-6-1-sol) `azure/gpt-6.1-sol` | 98.37% | 0.79% | 0.84% | 11.38 s | 16.07 s | 80.94 |
| [Gemini 3 Flash Preview](https://router.one/models/gemini-3-flash-preview) `google/gemini-3-flash-preview` | 99.65% | 0.12% | 0.23% | 4.78 s | 7.19 s | 258.72 |
| [Gemini 3.1 Flash Lite Preview](https://router.one/models/gemini-3-1-flash-lite-preview) `google/gemini-3.1-flash-lite-preview` | 99.37% | 0.00% | 0.63% | 3.08 s | 4.96 s | 262.59 |
| [Grok 4.7 Build Fast](https://router.one/models/grok-4-7-build-fast) `grok-4.7-build-fast` | 96.23% | 0.00% | 3.77% | 3.43 s | 17.99 s | 122.83 |
| [Gemini 4 Hydrogen](https://router.one/models/gemini-4-hydrogen) `google/gemini-4-hydrogen` | 80.33% | 0.00% | 19.67% | 10.75 s | 19.59 s | 511.65 |
| [GPT-6 Sol · Azure](https://router.one/models/azure-gpt-6-sol) `azure/gpt-6-sol` | 98.14% | 0.00% | 1.86% | 9.34 s | 10.07 s | 292.27 |
| [GPT-5.5 · Azure](https://router.one/models/azure-gpt-5-5) `azure/gpt-5.5` | 92.37% | 0.16% | 7.47% | 8.6 s | 13.54 s | 137.19 |
| [GPT-6 Astra · Azure](https://router.one/models/azure-gpt-6-astra) `azure/gpt-6-astra` | 98.75% | 0.18% | 1.07% | 12.57 s | 18.48 s | 93.55 |
| [Gemini 3.5 Flash Lite · Vertex](https://router.one/models/vertex-gemini-3-5-flash-lite) `vertex/gemini-3.5-flash-lite` | 99.59% | 0.00% | 0.41% | 3.14 s | 5.48 s | 162.93 |
| [Gemini 3.7 Flash · Vertex](https://router.one/models/vertex-gemini-3-7-flash) `vertex/gemini-3.7-flash` | 99.29% | 0.00% | 0.71% | 11.18 s | 13.43 s | 130.89 |
| [Claude Haiku 4.5 · AWS](https://router.one/models/aws-claude-haiku-4-5) `aws/claude-haiku-4.5` | 95.35% | 0.00% | 4.65% | — | 1.83 s | — |
| [Claude Fable 5](https://router.one/models/claude-fable-5) `anthropic/claude-fable-5` | 99.64% | 0.00% | 0.36% | 13.94 s | 14.35 s | 142.03 |
| [Gemini 3.5 Flash · Vertex](https://router.one/models/vertex-gemini-3-5-flash) `vertex/gemini-3.5-flash` | 97.47% | 0.00% | 2.53% | — | 10.44 s | — |
| [Claude Opus 4.6 (thinking)](https://router.one/models/claude-opus-4-6-thinking) `anthropic/claude-opus-4.6-thinking` | 75.52% | 0.00% | 24.48% | — | 9.44 s | — |
| [Claude Opus 4.7 (thinking)](https://router.one/models/claude-opus-4-7-thinking) `anthropic/claude-opus-4.7-thinking` | 97.24% | 1.38% | 1.38% | — | 18.8 s | — |
| [Gemini 3.1 Pro Preview · Vertex](https://router.one/models/vertex-gemini-3-1-pro-preview) `vertex/gemini-3.1-pro-preview` | 96.10% | 0.00% | 3.90% | — | 36.72 s | — |
| [GPT-5.6 Sol · Azure](https://router.one/models/azure-gpt-5-6-sol) `azure/gpt-5.6-sol` | 100.00% | 0.00% | 0.00% | 8.77 s | 10.45 s | 158.09 |
| [GPT-5.6 Terra · Azure](https://router.one/models/azure-gpt-5-6-terra) `azure/gpt-5.6-terra` | 98.41% | 0.00% | 1.59% | — | 17.24 s | — |
| [Claude Sonnet 5 · AWS](https://router.one/models/aws-claude-sonnet-5) `aws/claude-sonnet-5` | 83.67% | 1.36% | 14.97% | — | 12.52 s | — |
| [Claude Sonnet 4.5 · AWS](https://router.one/models/aws-claude-sonnet-4-5) `aws/claude-sonnet-4.5` | 89.58% | 3.47% | 6.94% | — | 10.51 s | — |
| [Claude Opus 4.6 · AWS](https://router.one/models/aws-claude-opus-4-6) `aws/claude-opus-4.6` | 99.17% | 0.00% | 0.83% | — | 10.8 s | — |

## Sales channels beside the default channel, last 30 days

Ids prefixed azure/, aws/, vertex/ or aistudio/ are separately priced sales channels of a base model, each with its own routing pool. The rows below put a channel id next to the default-channel id of the same model where both cleared the sample floor. The two serve different callers and workloads, so read the difference as what each channel's traffic saw, not as a like-for-like test.

| Model | Channel | Success 2xx | Rate limit 429 | Server 5xx | Avg. time to first token | Avg. latency | Throughput (tokens/s) |
| --- | --- | --- | --- | --- | --- | --- | --- |
| [Gemini 3.8 Flash](https://router.one/models/gemini-3-8-flash) `google/gemini-3.8-flash` | Default | 98.58% | 0.11% | 1.31% | 12.32 s | 15.26 s | 317.61 |
| [Gemini 3.8 Flash · Vertex](https://router.one/models/vertex-gemini-3-8-flash) `vertex/gemini-3.8-flash` | Vertex | 97.80% | 0.37% | 1.83% | 23.46 s | 38.33 s | 150.65 |
| [Gemini 3.8 Flash · AI Studio](https://router.one/models/aistudio-gemini-3-8-flash) `aistudio/gemini-3.8-flash` | AI Studio | 97.03% | 0.23% | 2.75% | 26.67 s | 30.04 s | 212.61 |
| [GPT-6.1 Sol](https://router.one/models/gpt-6-1-sol) `openai/gpt-6.1-sol` | Default | 99.49% | 0.02% | 0.49% | 12.27 s | 17.56 s | 153.92 |
| [GPT-6.1 Sol · Azure](https://router.one/models/azure-gpt-6-1-sol) `azure/gpt-6.1-sol` | Azure | 98.37% | 0.79% | 0.84% | 11.38 s | 16.07 s | 80.94 |
| [GPT-5.6 Terra](https://router.one/models/gpt-5-6-terra) `openai/gpt-5.6-terra` | Default | 99.23% | 0.00% | 0.77% | 15.18 s | 19.39 s | 116.53 |
| [GPT-5.6 Terra · Azure](https://router.one/models/azure-gpt-5-6-terra) `azure/gpt-5.6-terra` | Azure | 98.41% | 0.00% | 1.59% | — | 17.24 s | — |
| [GPT-5.6 Luna](https://router.one/models/gpt-5-6-luna) `openai/gpt-5.6-luna` | Default | 99.94% | 0.00% | 0.06% | 6.13 s | 2.44 s | 209.34 |
| [GPT-5.6 Luna · Azure](https://router.one/models/azure-gpt-5-6-luna) `azure/gpt-5.6-luna` | Azure | 99.91% | 0.03% | 0.06% | 5.48 s | 7.59 s | 269.37 |
| [GPT-6 Sol](https://router.one/models/gpt-6-sol) `openai/gpt-6-sol` | Default | 99.85% | 0.00% | 0.15% | 10.33 s | 12.87 s | 185.04 |
| [GPT-6 Sol · Azure](https://router.one/models/azure-gpt-6-sol) `azure/gpt-6-sol` | Azure | 98.14% | 0.00% | 1.86% | 9.34 s | 10.07 s | 292.27 |
| [Gemini 4 Argon](https://router.one/models/gemini-4-argon) `google/gemini-4-argon` | Default | 97.27% | 0.04% | 2.69% | 18.64 s | 31.23 s | 108.23 |
| [Gemini 4 Argon · Vertex](https://router.one/models/vertex-gemini-4-argon) `vertex/gemini-4-argon` | Vertex | 88.45% | 1.66% | 9.90% | 41.59 s | 59.7 s | 75.39 |
| [Gemini 4 Argon · AI Studio](https://router.one/models/aistudio-gemini-4-argon) `aistudio/gemini-4-argon` | AI Studio | 81.16% | 0.00% | 18.84% | 31.54 s | 36.68 s | 71.68 |
| [GPT-6 Astra](https://router.one/models/gpt-6-astra) `openai/gpt-6-astra` | Default | 99.51% | 0.00% | 0.49% | 13.63 s | 21.79 s | 131.91 |
| [GPT-6 Astra · Azure](https://router.one/models/azure-gpt-6-astra) `azure/gpt-6-astra` | Azure | 98.75% | 0.18% | 1.07% | 12.57 s | 18.48 s | 93.55 |
| [GPT-5.6 Sol](https://router.one/models/gpt-5-6-sol) `openai/gpt-5.6-sol` | Default | 99.56% | 0.00% | 0.44% | 15.05 s | 20.59 s | 112.35 |
| [GPT-5.6 Sol · Azure](https://router.one/models/azure-gpt-5-6-sol) `azure/gpt-5.6-sol` | Azure | 100.00% | 0.00% | 0.00% | 8.77 s | 10.45 s | 158.09 |
| [Claude Sonnet 5](https://router.one/models/claude-sonnet-5) `anthropic/claude-sonnet-5` | Default | 99.69% | 0.00% | 0.31% | 12.84 s | 18.76 s | 173.61 |
| [Claude Sonnet 5 · AWS](https://router.one/models/aws-claude-sonnet-5) `aws/claude-sonnet-5` | AWS | 83.67% | 1.36% | 14.97% | — | 12.52 s | — |
| [Gemini 3.7 Flash](https://router.one/models/gemini-3-7-flash) `google/gemini-3.7-flash` | Default | 98.50% | 0.10% | 1.40% | 11.46 s | 16.75 s | 436.79 |
| [Gemini 3.7 Flash · Vertex](https://router.one/models/vertex-gemini-3-7-flash) `vertex/gemini-3.7-flash` | Vertex | 99.29% | 0.00% | 0.71% | 11.18 s | 13.43 s | 130.89 |
| [Claude Sonnet 4.6](https://router.one/models/claude-sonnet-4-6) `anthropic/claude-sonnet-4.6` | Default | 99.65% | 0.02% | 0.33% | 9.67 s | 15.26 s | 179.44 |
| [Claude Sonnet 4.6 · AWS](https://router.one/models/aws-claude-sonnet-4-6) `aws/claude-sonnet-4.6` | AWS | 99.92% | 0.00% | 0.08% | — | 2.17 s | — |
| [Claude Haiku 4.5](https://router.one/models/claude-haiku-4-5) `anthropic/claude-haiku-4.5` | Default | 99.15% | 0.00% | 0.85% | 4.64 s | 7.5 s | 225.23 |
| [Claude Haiku 4.5 · AWS](https://router.one/models/aws-claude-haiku-4-5) `aws/claude-haiku-4.5` | AWS | 95.35% | 0.00% | 4.65% | — | 1.83 s | — |
| [Gemini 3.5 Flash Lite](https://router.one/models/gemini-3-5-flash-lite) `google/gemini-3.5-flash-lite` | Default | 99.73% | 0.00% | 0.27% | 3.31 s | 5.22 s | 266.76 |
| [Gemini 3.5 Flash Lite · Vertex](https://router.one/models/vertex-gemini-3-5-flash-lite) `vertex/gemini-3.5-flash-lite` | Vertex | 99.59% | 0.00% | 0.41% | 3.14 s | 5.48 s | 162.93 |
| [Gemini 3.5 Flash](https://router.one/models/gemini-3-5-flash) `google/gemini-3.5-flash` | Default | 97.44% | 0.00% | 2.56% | 6.89 s | 11.51 s | 264.39 |
| [Gemini 3.5 Flash · Vertex](https://router.one/models/vertex-gemini-3-5-flash) `vertex/gemini-3.5-flash` | Vertex | 97.47% | 0.00% | 2.53% | — | 10.44 s | — |
| [Claude Opus 4.6](https://router.one/models/claude-opus-4-6) `anthropic/claude-opus-4.6` | Default | 98.90% | 0.00% | 1.10% | 9.85 s | 13.89 s | 200.32 |
| [Claude Opus 4.6 · AWS](https://router.one/models/aws-claude-opus-4-6) `aws/claude-opus-4.6` | AWS | 99.17% | 0.00% | 0.83% | — | 10.8 s | — |
| [Gemini 4 Hydrogen](https://router.one/models/gemini-4-hydrogen) `google/gemini-4-hydrogen` | Default | 80.33% | 0.00% | 19.67% | 10.75 s | 19.59 s | 511.65 |
| [Gemini 4 Hydrogen · Vertex](https://router.one/models/vertex-gemini-4-hydrogen) `vertex/gemini-4-hydrogen` | Vertex | 99.22% | 0.00% | 0.78% | 23.36 s | 28.77 s | 314.88 |

## How to read the columns

### Success 2xx, rate limit 429, server 5xx

The share of requests whose final status was a 2xx, a 429 or a 5xx. Only requests that ended in one of those three are counted; a request refused for a malformed body or an empty balance is in no column.

### Avg. time to first token

The mean over successful streaming requests that recorded a first token. It grows with prompt size and with how long the model works before it starts to stream.

### Avg. latency

The mean time to the complete response over successful requests. A model that is asked for long outputs shows a longer average.

### Throughput

Output tokens per second of generation, over successful streaming requests that recorded both a token count and a generation time.

### Sample floor

A model appears in a window only with at least 100 eligible requests from at least 5 independent principals in that window. A dash in a cell means the window holds no request of the kind that column is computed from.

### Row order

Rows are ordered by request volume in the window. Nothing on this page ranks one model above another.

## What this page is not

### Not a speed comparison between models

The requests behind each row are whatever that model's callers sent. A model used mostly for long agentic sessions and one used for short classification calls will differ on every latency column for reasons that have nothing to do with the model.

### Not a service-level commitment

Contractual availability is documented on /sla, and current incidents are on /status. This page reports what happened, window by window.

### Not your own traffic

The aggregates cover all callers. Dashboard → Logs records the status, latency and token counts of each of your own requests.

## FAQ

### How often is this data updated?

This page re-reads the gateway's aggregates within the hour. The line under the heading shows when the page last read them, and each table states the dates its window covers.

### Why is a model I use missing from the table?

A model is listed only when it is in the current catalog and had at least 100 eligible requests from at least 5 independent principals in the window. A model below that floor in the last 7 days can still appear in the 30-day table.

### Why do the 7-day and 30-day rows for one model differ?

They cover different requests. A short incident or a change in what callers send moves the 7-day row quickly and the 30-day row slowly, so read the two together.

### Does a 429 in this table come from my own rate limit?

The 429 column counts requests whose final status was 429 across all callers. Per-key limits and budgets are set by each account, and your own requests and their statuses are in Dashboard → Logs.

## See also

- China latency benchmark: https://router.one/benchmarks/china-latency
- Smart routing: https://router.one/routing-methodology
- Availability & SLA: https://router.one/sla
- Canonical page: https://router.one/benchmarks/model-reliability
- Models and per-model token rates: https://router.one/models (markdown: https://router.one/models.md)
- Pricing: https://router.one/pricing
- API docs (markdown): https://router.one/docs.md
- Company facts: https://router.one/facts/company.md
