{ "providers": [ { "name": "OpenAI/gpt-5.6-luna", "model": "gpt-5.6-luna", "api_key_env": "OPENAI_API_KEY", "base_url": "https://api.openai.com/v1", "protocol": "openai", "model_family": "GPT", "access_class": "closed", "max_output_field": "max_completion_tokens", "thinking_budget_tokens": 0, "pricing": { "input_per_million": 1.0, "cached_input_per_million": 0.1, "output_per_million": 6.0, "currency": "USD", "source_url": "https://openai.com/api/pricing/", "as_of": "2026-07-29", "status": "verified" } }, { "name": "Anthropic/claude-opus-4.8", "model": "claude-opus-4-8", "api_key_env": "ANTHROPIC_API_KEY", "protocol": "anthropic", "model_family": "Claude", "access_class": "closed", "thinking_budget_tokens": 1024, "pricing": { "input_per_million": 5.0, "cached_input_per_million": 0.5, "output_per_million": 25.0, "currency": "USD", "source_url": "https://platform.claude.com/docs/en/about-claude/pricing", "as_of": "2026-07-29", "status": "verified" } }, { "name": "Google/gemini-3.5-flash", "model": "gemini-3.5-flash", "api_key_env": "GEMINI_API_KEY", "protocol": "gemini", "model_family": "Gemini", "access_class": "closed", "thinking_budget_tokens": 1024, "pricing": { "input_per_million": 1.5, "cached_input_per_million": 0.15, "output_per_million": 9.0, "currency": "USD", "source_url": "https://ai.google.dev/gemini-api/docs/pricing", "as_of": "2026-07-29", "status": "verified" } }, { "name": "Moonshot/kimi-k3", "model": "kimi-k3", "api_key_env": "MOONSHOT_API_KEY", "base_url": "https://api.moonshot.cn/v1", "protocol": "openai", "model_family": "Kimi", "access_class": "open-weight", "thinking_budget_tokens": 1024, "extra_body": {"reasoning_effort": "low"}, "pricing": { "input_per_million": 20.0, "cached_input_per_million": 2.0, "output_per_million": 100.0, "currency": "CNY", "source_url": "https://platform.kimi.com/docs/pricing/chat-k3.md", "as_of": "2026-07-29", "usd_per_currency_unit": 0.1477922077922078, "fx_source_url": "https://www.ecb.europa.eu/stats/eurofxref/eurofxref-daily.xml", "fx_as_of": "2026-07-29", "status": "verified_with_fx" } }, { "name": "Ark/doubao-seed-1.6", "model": "doubao-seed-1-6-250615", "api_key_env": "ARK_API_KEY", "base_url": "https://ark.cn-beijing.volces.com/api/v3", "protocol": "openai", "model_family": "Doubao", "access_class": "closed", "thinking_budget_tokens": 0, "extra_body": {"thinking": {"type": "disabled"}}, "pricing": { "input_per_million": null, "cached_input_per_million": null, "output_per_million": null, "currency": "CNY", "source_url": "https://www.volcengine.com/docs/82379/1099320", "as_of": "2026-07-29", "status": "unresolved", "blocker": "The exact public cached-input and output price for endpoint doubao-seed-1-6-250615 has not been extracted from an authoritative model row." } }, { "name": "Ark/Qwen3-32B", "model": "qwen3-32b-20250429", "api_key_env": "ARK_API_KEY", "base_url": "https://ark.cn-beijing.volces.com/api/v3", "protocol": "openai", "model_family": "Qwen", "access_class": "open-weight", "thinking_budget_tokens": 0, "pricing": { "input_per_million": null, "cached_input_per_million": null, "output_per_million": null, "currency": "CNY", "source_url": "https://www.volcengine.com/docs/82379/1099320", "as_of": "2026-07-29", "status": "unresolved", "blocker": "The exact public price for Ark endpoint qwen3-32b-20250429 has not been matched to an authoritative model row." } }, { "name": "Ark/DeepSeek-V4-Flash", "model": "deepseek-v4-flash-260425", "api_key_env": "ARK_API_KEY", "base_url": "https://ark.cn-beijing.volces.com/api/v3", "protocol": "openai", "model_family": "DeepSeek", "access_class": "open-weight", "thinking_budget_tokens": 0, "pricing": { "input_per_million": null, "cached_input_per_million": null, "output_per_million": null, "currency": "CNY", "source_url": "https://www.volcengine.com/docs/82379/1099320", "as_of": "2026-07-29", "status": "unresolved", "blocker": "The exact public price for Ark endpoint deepseek-v4-flash-260425 has not been matched to an authoritative model row." } }, { "name": "DeepSeek official/DeepSeek-V4-Flash", "model": "deepseek-v4-flash", "api_key_env": "DEEPSEEK_API_KEY", "base_url": "https://api.deepseek.com/v1", "protocol": "openai", "model_family": "DeepSeek", "access_class": "open-weight", "thinking_budget_tokens": 0, "pricing": { "input_per_million": 0.14, "cached_input_per_million": 0.0028, "output_per_million": 0.28, "currency": "USD", "source_url": "https://api-docs.deepseek.com/quick_start/pricing", "as_of": "2026-07-29", "status": "verified" } }, { "name": "SiliconFlow/Qwen3-32B", "model": "Qwen/Qwen3-32B", "api_key_env": "SILICONFLOW_API_KEY", "base_url": "https://api.siliconflow.cn/v1", "protocol": "openai", "model_family": "Qwen", "access_class": "open-weight", "thinking_budget_tokens": 0, "pricing": { "input_per_million": null, "cached_input_per_million": null, "output_per_million": null, "currency": "CNY", "source_url": "https://siliconflow.cn/pricing", "as_of": "2026-07-29", "status": "unresolved", "blocker": "The exact Qwen/Qwen3-32B cached-input and output price has not been extracted from an authoritative public row." } }, { "name": "SiliconFlow/DeepSeek-V4-Flash", "model": "deepseek-ai/DeepSeek-V4-Flash", "api_key_env": "SILICONFLOW_API_KEY", "base_url": "https://api.siliconflow.cn/v1", "protocol": "openai", "model_family": "DeepSeek", "access_class": "open-weight", "thinking_budget_tokens": 0, "pricing": { "input_per_million": 1.0, "cached_input_per_million": 0.02, "output_per_million": 2.0, "currency": "CNY", "source_url": "https://siliconflow.cn/pricing", "as_of": "2026-07-29", "usd_per_currency_unit": 0.1477922077922078, "fx_source_url": "https://www.ecb.europa.eu/stats/eurofxref/eurofxref-daily.xml", "fx_as_of": "2026-07-29", "status": "verified_with_fx" } } ], "required_model_families": ["GPT", "Claude", "Gemini", "Doubao", "Qwen", "Kimi", "DeepSeek"], "external_benchmark_references": [], "same_model_provider_groups": [ { "logical_model": "DeepSeek-V4-Flash", "providers": [ "DeepSeek official/DeepSeek-V4-Flash", "SiliconFlow/DeepSeek-V4-Flash" ] } ], "workload": { "context_tokens": [8192, 32768, 131072], "output_tokens": [512, 2048], "requests_per_cell": 100, "concurrency": 4, "minimum_output_attainment_rate": 0.95 }, "availability": { "duration_hours": 168, "interval_seconds": 3600, "requests_per_probe": 1, "context_tokens": 1024, "output_tokens": 64 }, "rate_limit": { "concurrency_levels": [1, 2, 4, 8, 16, 32], "requests_per_level": 100, "context_tokens": 8192, "output_tokens": 512 }, "agent_cost": { "rounds": 6, "initial_context_tokens": 8192, "tokens_added_per_round": 2048, "output_tokens": 512 } }