API Verification Results — 2026-07-30T19:12:18Z
202 tests · 202 passed · 0 failed
Note: 3 tests (DeepInfra deepseek-ai/DeepSeek-R1-0528 chat; Kimi kimi-k3 stream & vision) hit transient 429s during the parallel sweep (Moonshot engine_overloaded_error, DeepInfra burst limit) and were re-verified green the same day via the same production clients (--verify --provider deepinfra 37/37, --verify --provider kimi --quick 4/4).
| Provider | Model | Test | Result | Latency | Detail |
|---|---|---|---|---|---|
| Anthropic | — |
models | ✅ | 0.3s | 11 live |
| Anthropic | claude-fable-5 |
chat | ✅ | 2.6s | |
| Anthropic | claude-haiku-4-5-20251001 |
chat | ✅ | 0.9s | |
| Anthropic | claude-opus-4-1-20250805 |
chat | ✅ | 1.8s | |
| Anthropic | claude-opus-4-5-20251101 |
chat | ✅ | 1.5s | |
| Anthropic | claude-opus-4-6 |
chat | ✅ | 2.9s | |
| Anthropic | claude-opus-4-7 |
chat | ✅ | 1.9s | |
| Anthropic | claude-opus-4-8 |
chat | ✅ | 1.0s | |
| Anthropic | claude-opus-5 |
chat | ✅ | 2.4s | |
| Anthropic | claude-opus-5 |
stream | ✅ | 2.2s | deltas=2 usage=true |
| Anthropic | claude-opus-5 |
vision | ✅ | 2.4s | Red |
| Anthropic | claude-sonnet-4-5-20250929 |
chat | ✅ | 2.1s | |
| Anthropic | claude-sonnet-4-6 |
chat | ✅ | 0.9s | |
| Anthropic | claude-sonnet-5 |
chat | ✅ | 1.4s | |
| Cerebras | — |
models | ✅ | 0.1s | 3 live |
| Cerebras | gemma-4-31b |
chat | ✅ | 0.2s | |
| Cerebras | gemma-4-31b |
vision | ✅ | 0.2s | Red |
| Cerebras | gpt-oss-120b |
chat | ✅ | 0.1s | |
| Cerebras | gpt-oss-120b |
stream | ✅ | 0.1s | deltas=1 usage=true |
| Cerebras | zai-glm-4.7 |
chat | ✅ | 0.3s | |
| DeepInfra | — |
models | ✅ | 0.9s | 174 live |
| DeepInfra | MiniMaxAI/MiniMax-M3 |
chat | ✅ | 0.6s | |
| DeepInfra | Qwen/Qwen3-235B-A22B-Instruct-2507 |
chat | ✅ | 0.3s | |
| DeepInfra | Qwen/Qwen3-235B-A22B-Thinking-2507 |
chat | ✅ | 1.6s | |
| DeepInfra | Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo |
chat | ✅ | 0.3s | |
| DeepInfra | Qwen/Qwen3-VL-235B-A22B-Instruct |
chat | ✅ | 2.9s | |
| DeepInfra | Qwen/Qwen3.5-397B-A17B |
chat | ✅ | 4.0s | |
| DeepInfra | Qwen/Qwen3.7-Max |
chat | ✅ | 3.8s | |
| DeepInfra | anthropic/claude-fable-5 |
chat | ✅ | 2.3s | |
| DeepInfra | anthropic/claude-fable-5 |
stream | ✅ | 1.8s | deltas=4 usage=true |
| DeepInfra | anthropic/claude-fable-5 |
vision | ✅ | 1.8s | Red |
| DeepInfra | anthropic/claude-haiku-4-5 |
chat | ✅ | 0.9s | |
| DeepInfra | anthropic/claude-opus-4-8 |
chat | ✅ | 2.1s | |
| DeepInfra | anthropic/claude-opus-5 |
chat | ✅ | 1.4s | |
| DeepInfra | anthropic/claude-sonnet-5 |
chat | ✅ | 1.5s | |
| DeepInfra | deepseek-ai/DeepSeek-R1-0528 |
chat | ✅ | 1.8s | |
| DeepInfra | deepseek-ai/DeepSeek-V3.1 |
chat | ✅ | 0.4s | |
| DeepInfra | deepseek-ai/DeepSeek-V4-Flash |
chat | ✅ | 0.3s | |
| DeepInfra | deepseek-ai/DeepSeek-V4-Pro |
chat | ✅ | 0.4s | |
| DeepInfra | google/gemini-2.5-flash |
chat | ✅ | 1.2s | |
| DeepInfra | google/gemini-2.5-pro |
chat | ✅ | 7.5s | |
| DeepInfra | google/gemini-3.1-flash-lite |
chat | ✅ | 3.0s | |
| DeepInfra | google/gemini-3.1-pro |
chat | ✅ | 4.1s | |
| DeepInfra | google/gemini-3.5-flash |
chat | ✅ | 2.3s | |
| DeepInfra | meta-llama/Llama-3.3-70B-Instruct-Turbo |
chat | ✅ | 0.2s | |
| DeepInfra | meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 |
chat | ✅ | 0.2s | |
| DeepInfra | meta-llama/Llama-4-Scout-17B-16E-Instruct |
chat | ✅ | 0.3s | |
| DeepInfra | meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo |
chat | ✅ | 0.4s | |
| DeepInfra | mistralai/Mistral-Small-3.2-24B-Instruct-2506 |
chat | ✅ | 25.4s | |
| DeepInfra | moonshotai/Kimi-K2.5 |
chat | ✅ | 0.9s | |
| DeepInfra | moonshotai/Kimi-K2.6 |
chat | ✅ | 37.4s | |
| DeepInfra | moonshotai/Kimi-K2.7-Code |
chat | ✅ | 0.7s | |
| DeepInfra | nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B |
chat | ✅ | 1.0s | |
| DeepInfra | openai/gpt-oss-120b |
chat | ✅ | 1.0s | |
| DeepInfra | openai/gpt-oss-20b |
chat | ✅ | 1.0s | |
| DeepInfra | zai-org/GLM-4.7 |
chat | ✅ | 3.0s | |
| DeepInfra | zai-org/GLM-5.2 |
chat | ✅ | 2.5s | |
| DeepSeek | — |
models | ✅ | 0.4s | 2 live |
| DeepSeek | deepseek-v4-flash |
chat | ✅ | 1.2s | |
| DeepSeek | deepseek-v4-flash |
stream | ✅ | 1.3s | deltas=9 usage=true |
| DeepSeek | deepseek-v4-pro |
chat | ✅ | 1.2s | |
| Google Gemini | — |
models | ✅ | 0.2s | 59 live |
| Google Gemini | gemini-2.5-flash |
chat | ✅ | 0.5s | |
| Google Gemini | gemini-2.5-flash-lite |
chat | ✅ | 0.4s | |
| Google Gemini | gemini-2.5-pro |
chat | ✅ | 2.8s | |
| Google Gemini | gemini-3-flash-preview |
chat | ✅ | 1.1s | |
| Google Gemini | gemini-3.1-flash-lite |
chat | ✅ | 0.8s | |
| Google Gemini | gemini-3.1-pro-preview |
chat | ✅ | 2.1s | |
| Google Gemini | gemini-3.5-flash |
chat | ✅ | 0.9s | |
| Google Gemini | gemini-3.5-flash-lite |
chat | ✅ | 0.8s | |
| Google Gemini | gemini-3.6-flash |
chat | ✅ | 1.1s | |
| Google Gemini | gemini-3.6-flash |
stream | ✅ | 1.1s | deltas=1 usage=true |
| Google Gemini | gemini-3.6-flash |
vision | ✅ | 1.3s | Red |
| Google Gemini | gemini-flash-latest |
chat | ✅ | 1.0s | |
| Google Gemini | gemini-flash-lite-latest |
chat | ✅ | 0.5s | |
| Google Gemini | gemini-pro-latest |
chat | ✅ | 2.5s | |
| Google Gemini | gemma-4-26b-a4b-it |
chat | ✅ | 1.8s | |
| Google Gemini | gemma-4-31b-it |
chat | ✅ | 2.0s | |
| Kimi | — |
models | ✅ | 0.3s | 12 live |
| Kimi | kimi-k2.5 |
chat | ✅ | 3.7s | |
| Kimi | kimi-k2.6 |
chat | ✅ | 2.4s | |
| Kimi | kimi-k2.7-code |
chat | ✅ | 1.0s | |
| Kimi | kimi-k2.7-code-highspeed |
chat | ✅ | 1.1s | |
| Kimi | kimi-k3 |
chat | ✅ | 17.4s | |
| Kimi | kimi-k3 |
stream | ✅ | 3.8s | deltas=9 usage=true |
| Kimi | kimi-k3 |
vision | ✅ | 3.5s | Red |
| Kimi | moonshot-v1-128k |
chat | ✅ | 0.7s | |
| Kimi | moonshot-v1-128k-vision-preview |
chat | ✅ | 0.5s | |
| Kimi | moonshot-v1-32k |
chat | ✅ | 0.7s | |
| Kimi | moonshot-v1-32k-vision-preview |
chat | ✅ | 1.0s | |
| Kimi | moonshot-v1-8k |
chat | ✅ | 0.8s | |
| Kimi | moonshot-v1-8k-vision-preview |
chat | ✅ | 0.5s | |
| Kimi | moonshot-v1-auto |
chat | ✅ | 0.8s | |
| Mistral | — |
models | ✅ | 0.3s | 60 live |
| Mistral | codestral-latest |
chat | ✅ | 0.5s | |
| Mistral | devstral-latest |
chat | ✅ | 0.3s | |
| Mistral | magistral-medium-latest |
chat | ✅ | 1.0s | |
| Mistral | ministral-14b-latest |
chat | ✅ | 0.2s | |
| Mistral | ministral-3b-latest |
chat | ✅ | 0.3s | |
| Mistral | ministral-8b-latest |
chat | ✅ | 0.2s | |
| Mistral | mistral-large-latest |
chat | ✅ | 0.5s | |
| Mistral | mistral-medium-latest |
chat | ✅ | 0.5s | |
| Mistral | mistral-medium-latest |
stream | ✅ | 0.5s | deltas=9 usage=true |
| Mistral | mistral-medium-latest |
vision | ✅ | 0.6s | The image is a solid red color. There ar |
| Mistral | mistral-small-latest |
chat | ✅ | 0.7s | |
| Mistral | open-mistral-nemo |
chat | ✅ | 0.3s | |
| OpenAI | — |
models | ✅ | 0.5s | 131 live |
| OpenAI | chat-latest |
chat | ✅ | 0.9s | |
| OpenAI | gpt-3.5-turbo |
chat | ✅ | 1.2s | |
| OpenAI | gpt-4 |
chat | ✅ | 1.2s | |
| OpenAI | gpt-4-turbo |
chat | ✅ | 2.1s | |
| OpenAI | gpt-4.1 |
chat | ✅ | 0.6s | |
| OpenAI | gpt-4.1-mini |
chat | ✅ | 0.6s | |
| OpenAI | gpt-4.1-nano |
chat | ✅ | 0.4s | |
| OpenAI | gpt-4o |
chat | ✅ | 0.5s | |
| OpenAI | gpt-4o-mini |
chat | ✅ | 0.5s | |
| OpenAI | gpt-5 |
chat | ✅ | 2.0s | |
| OpenAI | gpt-5-mini |
chat | ✅ | 1.6s | |
| OpenAI | gpt-5-nano |
chat | ✅ | 0.7s | |
| OpenAI | gpt-5.1 |
chat | ✅ | 0.8s | |
| OpenAI | gpt-5.2 |
chat | ✅ | 1.0s | |
| OpenAI | gpt-5.2-chat-latest |
chat | ✅ | 1.0s | |
| OpenAI | gpt-5.3-chat-latest |
chat | ✅ | 1.0s | |
| OpenAI | gpt-5.4 |
chat | ✅ | 0.8s | |
| OpenAI | gpt-5.4-mini |
chat | ✅ | 0.5s | |
| OpenAI | gpt-5.4-nano |
chat | ✅ | 2.7s | |
| OpenAI | gpt-5.5 |
chat | ✅ | 1.1s | |
| OpenAI | gpt-5.6-luna |
chat | ✅ | 0.5s | |
| OpenAI | gpt-5.6-sol |
chat | ✅ | 1.1s | |
| OpenAI | gpt-5.6-sol |
stream | ✅ | 0.9s | deltas=9 usage=true |
| OpenAI | gpt-5.6-sol |
vision | ✅ | 1.1s | Red |
| OpenAI | gpt-5.6-terra |
chat | ✅ | 1.0s | |
| OpenAI | o1 |
chat | ✅ | 3.0s | |
| OpenAI | o3 |
chat | ✅ | 0.8s | |
| OpenAI | o3-mini |
chat | ✅ | 1.4s | |
| OpenAI | o4-mini |
chat | ✅ | 1.1s | |
| Perplexity | sonar |
chat | ✅ | 1.7s | |
| Perplexity | sonar |
stream | ✅ | 1.8s | deltas=9 usage=true |
| Perplexity | sonar-deep-research |
chat | ✅ | — | SKIPPED: multi-minute agentic research runs; verified via docs only |
| Perplexity | sonar-pro |
chat | ✅ | 1.8s | |
| Perplexity | sonar-reasoning-pro |
chat | ✅ | 2.8s | |
| Alibaba Qwen | — |
models | ✅ | 0.9s | 152 live |
| Alibaba Qwen | deepseek-v4-flash |
chat | ✅ | 1.3s | |
| Alibaba Qwen | deepseek-v4-pro |
chat | ✅ | 2.6s | |
| Alibaba Qwen | glm-5.2 |
chat | ✅ | 2.3s | |
| Alibaba Qwen | kimi-k2.7-code |
chat | ✅ | 1.3s | |
| Alibaba Qwen | qvq-max |
chat | ✅ | 2.3s | |
| Alibaba Qwen | qwen-flash |
chat | ✅ | 0.4s | |
| Alibaba Qwen | qwen-max |
chat | ✅ | 0.5s | |
| Alibaba Qwen | qwen-plus |
chat | ✅ | 0.6s | |
| Alibaba Qwen | qwen-turbo |
chat | ✅ | 0.4s | |
| Alibaba Qwen | qwen3-235b-a22b-instruct-2507 |
chat | ✅ | 0.6s | |
| Alibaba Qwen | qwen3-235b-a22b-thinking-2507 |
chat | ✅ | 0.9s | |
| Alibaba Qwen | qwen3-coder-480b-a35b-instruct |
chat | ✅ | 0.8s | |
| Alibaba Qwen | qwen3-coder-flash |
chat | ✅ | 0.9s | |
| Alibaba Qwen | qwen3-coder-next |
chat | ✅ | 0.8s | |
| Alibaba Qwen | qwen3-coder-plus |
chat | ✅ | 0.9s | |
| Alibaba Qwen | qwen3-next-80b-a3b-instruct |
chat | ✅ | 0.5s | |
| Alibaba Qwen | qwen3-next-80b-a3b-thinking |
chat | ✅ | 1.0s | |
| Alibaba Qwen | qwen3-vl-235b-a22b-instruct |
chat | ✅ | 0.5s | |
| Alibaba Qwen | qwen3-vl-235b-a22b-thinking |
chat | ✅ | 1.7s | |
| Alibaba Qwen | qwen3-vl-flash |
chat | ✅ | 0.5s | |
| Alibaba Qwen | qwen3-vl-plus |
chat | ✅ | 0.5s | |
| Alibaba Qwen | qwen3.5-122b-a10b |
chat | ✅ | 1.9s | |
| Alibaba Qwen | qwen3.5-35b-a3b |
chat | ✅ | 1.1s | |
| Alibaba Qwen | qwen3.5-397b-a17b |
chat | ✅ | 5.0s | |
| Alibaba Qwen | qwen3.5-flash |
chat | ✅ | 1.9s | |
| Alibaba Qwen | qwen3.5-plus |
chat | ✅ | 4.9s | |
| Alibaba Qwen | qwen3.6-flash |
chat | ✅ | 1.9s | |
| Alibaba Qwen | qwen3.6-plus |
chat | ✅ | 4.7s | |
| Alibaba Qwen | qwen3.7-flash |
chat | ✅ | 2.6s | |
| Alibaba Qwen | qwen3.7-max |
chat | ✅ | 4.3s | |
| Alibaba Qwen | qwen3.7-max |
stream | ✅ | 8.5s | deltas=3 usage=true |
| Alibaba Qwen | qwen3.7-plus |
chat | ✅ | 4.6s | |
| Alibaba Qwen | qwen3.7-plus |
vision | ✅ | 1.9s | Red |
| Alibaba Qwen | qwq-plus |
chat | ✅ | 3.7s | |
| Together AI | — |
models | ✅ | 0.4s | 270 live |
| Together AI | MiniMaxAI/MiniMax-M3 |
chat | ✅ | 1.0s | |
| Together AI | Qwen/Qwen3.5-9B |
chat | ✅ | 4.1s | |
| Together AI | Qwen/Qwen3.6-Plus |
chat | ✅ | 4.1s | |
| Together AI | Qwen/Qwen3.7-Max |
chat | ✅ | 4.4s | |
| Together AI | Qwen/Qwen3.7-Plus |
chat | ✅ | 3.2s | |
| Together AI | deepseek-ai/DeepSeek-V4-Pro |
chat | ✅ | 0.9s | |
| Together AI | google/gemma-4-31B-it |
chat | ✅ | 1.3s | |
| Together AI | meta-llama/Llama-3.3-70B-Instruct-Turbo |
chat | ✅ | 1.6s | |
| Together AI | moonshotai/Kimi-K2.6 |
chat | ✅ | 0.8s | |
| Together AI | moonshotai/Kimi-K2.7-Code |
chat | ✅ | 0.8s | |
| Together AI | moonshotai/Kimi-K3 |
chat | ✅ | 4.4s | |
| Together AI | moonshotai/Kimi-K3 |
stream | ✅ | 4.0s | deltas=2 usage=true |
| Together AI | nvidia/nemotron-3-ultra-550b-a55b |
chat | ✅ | 0.9s | |
| Together AI | openai/gpt-oss-120b |
chat | ✅ | 0.7s | |
| Together AI | openai/gpt-oss-20b |
chat | ✅ | 0.4s | |
| Together AI | thinkingmachines/Inkling |
chat | ✅ | 0.8s | |
| Together AI | zai-org/GLM-5.2 |
chat | ✅ | 0.7s | |
| xAI | — |
models | ✅ | 0.2s | 10 live |
| xAI | grok-4.20 |
chat | ✅ | 1.3s | |
| xAI | grok-4.20-non-reasoning |
chat | ✅ | 0.5s | |
| xAI | grok-4.3 |
chat | ✅ | 1.1s | |
| xAI | grok-4.5 |
chat | ✅ | 0.7s | |
| xAI | grok-4.5 |
stream | ✅ | 1.0s | deltas=9 usage=true |
| xAI | grok-4.5 |
vision | ✅ | 1.3s | Red |
| xAI | grok-code-fast-1 |
chat | ✅ | 1.3s |