{ "meta": { "generated_at": "2026-04-08T20:45:16.709065Z", "methodology_version": "0.2.0", "snapshot_date": "2026-04-08", "n_entries": 75, "n_providers": 20, "source": "computenav.com", "license": "CC BY 4.0" }, "entries": [ { "model_label": "Llama 3.1 8B Instruct", "model_id": "meta-llama/Meta-Llama-3.1-8B-Instruct", "model_developer": "Meta", "model_release_date": "2024-07-23", "model_parameters": "8B", "model_type": "chat", "model_source": "open", "compute_provider": "DeepInfra", "provider": "DeepInfra", "price_per_1m_input": 0.055, "price_per_1m_output": 0.055, "price_blended": 0.055, "latency_ms": 100, "throughput_tps": 300, "status": "healthy", "context_window": 131072, "openai_compatible": true, "endpoint": "https://deepinfra.com/", "api_base_url": "https://api.deepinfra.com/v1/openai", "developer_website": "https://ai.meta.com/llama/", "provider_website": "https://deepinfra.com/", "region": "us", "source_url": "https://deepinfra.com/pricing", "fetched_at": "2026-04-06T17:37:06Z", "source": "scraped", "price_snapshot_date": "2026-04-06" }, { "model_label": "Llama 3.1 8B Instant", "model_id": "llama-3.1-8b-instant", "model_developer": "Meta", "model_release_date": "2024-07-23", "model_parameters": "8B", "model_type": "chat", "model_source": "open", "compute_provider": "Groq", "provider": "Groq", "price_per_1m_input": 0.05, "price_per_1m_output": 0.08, "price_blended": 0.059, "latency_ms": 120, "throughput_tps": 241, "status": "healthy", "context_window": 128000, "openai_compatible": true, "endpoint": "https://groq.com/", "api_base_url": "https://api.groq.com/openai/v1", "developer_website": "https://ai.meta.com/llama/", "provider_website": "https://groq.com/", "region": "us", "source_url": "https://groq.com/pricing", "fetched_at": "2026-04-06T17:37:03Z", "source": "scraped", "price_snapshot_date": "2026-04-06" }, { "model_label": "Llama 3.1 8B Instruct", "model_id": "meta-llama/Meta-Llama-3.1-8B-Instruct", "model_developer": "Meta", "model_release_date": "2024-07-23", "model_parameters": "8B", "model_type": "chat", "model_source": "open", "compute_provider": "Scaleway", "provider": "Scaleway", "price_per_1m_input": 0.09, "price_per_1m_output": 0.09, "price_blended": 0.09, "latency_ms": 320, "throughput_tps": 90, "status": "healthy", "context_window": 131072, "openai_compatible": true, "endpoint": "https://www.scaleway.com/en/generative-apis/", "api_base_url": "https://api.scaleway.ai/v1", "developer_website": "https://ai.meta.com/llama/", "provider_website": "https://www.scaleway.com/", "region": "eu", "source_url": "https://www.scaleway.com/en/docs/generative-apis/", "fetched_at": "2026-04-08T15:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-08" }, { "model_label": "Llama 3.1 8B Instruct Turbo", "model_id": "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo", "model_developer": "Meta", "model_release_date": "2024-07-23", "model_parameters": "8B", "model_type": "chat", "model_source": "open", "compute_provider": "Together AI", "provider": "Together AI", "price_per_1m_input": 0.1, "price_per_1m_output": 0.1, "price_blended": 0.1, "latency_ms": 150, "throughput_tps": 185, "status": "healthy", "context_window": 131072, "openai_compatible": true, "endpoint": "https://www.together.ai/", "api_base_url": "https://api.together.xyz/v1", "developer_website": "https://ai.meta.com/llama/", "provider_website": "https://www.together.ai/", "region": "us", "source_url": "https://www.together.ai/pricing", "fetched_at": "2026-04-06T17:37:04Z", "source": "scraped", "price_snapshot_date": "2026-04-06" }, { "model_label": "Gemini Flash 1.5", "model_id": "gemini-1.5-flash", "model_developer": "Google", "model_release_date": "2024-05-14", "model_parameters": "\u2014", "model_type": "chat, vision", "model_source": "closed", "compute_provider": "Google", "provider": "Google", "price_per_1m_input": 0.075, "price_per_1m_output": 0.3, "price_blended": 0.1425, "latency_ms": 150, "throughput_tps": 200, "status": "healthy", "context_window": 1000000, "openai_compatible": false, "endpoint": "https://ai.google.dev/", "api_base_url": "https://generativelanguage.googleapis.com/v1beta", "developer_website": "https://ai.google.dev/", "provider_website": "https://ai.google.dev/", "region": "us", "source_url": "https://ai.google.dev/pricing", "fetched_at": "2026-04-06T18:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-06" }, { "model_label": "Qwen 3 32B Instruct", "model_id": "Qwen/Qwen3-32B", "model_developer": "Alibaba", "model_release_date": "2025-04-29", "model_parameters": "32B", "model_type": "chat", "model_source": "open", "compute_provider": "Together AI", "provider": "Together AI", "price_per_1m_input": 0.15, "price_per_1m_output": 0.15, "price_blended": 0.15, "latency_ms": 350, "throughput_tps": 85, "status": "healthy", "context_window": 131072, "openai_compatible": true, "endpoint": "https://www.together.ai/", "api_base_url": "https://api.together.xyz/v1", "developer_website": "https://qwenlm.github.io/", "provider_website": "https://www.together.ai/", "region": "us", "source_url": "https://www.together.ai/pricing", "fetched_at": "2026-04-08T12:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-08" }, { "model_label": "Mistral Small 3.1", "model_id": "mistral-small-2503", "model_developer": "Mistral", "model_release_date": "2025-03-17", "model_parameters": "24B", "model_type": "chat", "model_source": "closed", "compute_provider": "Fireworks AI", "provider": "Fireworks AI", "price_per_1m_input": 0.1, "price_per_1m_output": 0.3, "price_blended": 0.16, "latency_ms": 180, "throughput_tps": 140, "status": "healthy", "context_window": 131072, "openai_compatible": true, "endpoint": "https://fireworks.ai/", "api_base_url": "https://api.fireworks.ai/inference/v1", "developer_website": "https://mistral.ai/", "provider_website": "https://fireworks.ai/", "region": "us", "source_url": "https://fireworks.ai/pricing", "fetched_at": "2026-04-06T18:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-06" }, { "model_label": "Llama 4 Scout", "model_id": "meta-llama/Llama-4-Scout-17B-16E", "model_developer": "Meta", "model_release_date": "2025-04-05", "model_parameters": "17B\u00d716E (MoE)", "model_type": "chat, vision", "model_source": "open", "compute_provider": "Together AI", "provider": "Together AI", "price_per_1m_input": 0.18, "price_per_1m_output": 0.18, "price_blended": 0.18, "latency_ms": 180, "throughput_tps": 150, "status": "healthy", "context_window": 10000000, "openai_compatible": true, "endpoint": "https://www.together.ai/", "api_base_url": "https://api.together.xyz/v1", "developer_website": "https://ai.meta.com/llama/", "provider_website": "https://www.together.ai/", "region": "us", "source_url": "https://www.together.ai/pricing", "fetched_at": "2026-04-06T20:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-06" }, { "model_label": "DeepSeek V3", "model_id": "deepseek-chat", "model_developer": "DeepSeek", "model_release_date": "2024-12-26", "model_parameters": "671B (MoE)", "model_type": "chat", "model_source": "open", "compute_provider": "DeepSeek", "provider": "DeepSeek", "price_per_1m_input": 0.14, "price_per_1m_output": 0.28, "price_blended": 0.182, "latency_ms": 320, "throughput_tps": 90, "status": "healthy", "context_window": 65536, "openai_compatible": true, "endpoint": "https://www.deepseek.com/", "api_base_url": "https://api.deepseek.com/v1", "developer_website": "https://www.deepseek.com/", "provider_website": "https://www.deepseek.com/", "region": "cn", "source_url": "https://api-docs.deepseek.com/", "fetched_at": "2026-04-08T15:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-08" }, { "model_label": "Gemini Flash 2.0", "model_id": "gemini-2.0-flash", "model_developer": "Google", "model_release_date": "2024-12-11", "model_parameters": "\u2014", "model_type": "chat, vision", "model_source": "closed", "compute_provider": "Google", "provider": "Google", "price_per_1m_input": 0.1, "price_per_1m_output": 0.4, "price_blended": 0.19, "latency_ms": 130, "throughput_tps": 220, "status": "healthy", "context_window": 1048576, "openai_compatible": false, "endpoint": "https://ai.google.dev/", "api_base_url": "https://generativelanguage.googleapis.com/v1beta", "developer_website": "https://ai.google.dev/", "provider_website": "https://ai.google.dev/", "region": "us", "source_url": "https://ai.google.dev/pricing", "fetched_at": "2026-04-06T18:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-06" }, { "model_label": "Gemini Flash 2.0", "model_id": "gemini-2.0-flash", "model_developer": "Google", "model_release_date": "2024-12-11", "model_parameters": "\u2014", "model_type": "chat, vision", "model_source": "closed", "compute_provider": "Fireworks AI", "provider": "Fireworks AI", "price_per_1m_input": 0.1, "price_per_1m_output": 0.4, "price_blended": 0.19, "latency_ms": 135, "throughput_tps": 210, "status": "healthy", "context_window": 1048576, "openai_compatible": false, "endpoint": "https://fireworks.ai/", "api_base_url": "https://api.fireworks.ai/inference/v1", "developer_website": "https://ai.google.dev/", "provider_website": "https://fireworks.ai/", "region": "us", "source_url": "https://fireworks.ai/pricing", "fetched_at": "2026-04-06T18:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-06" }, { "model_label": "Llama 3.1 8B Instruct", "model_id": "accounts/fireworks/models/llama-v3p1-8b-instruct", "model_developer": "Meta", "model_release_date": "2024-07-23", "model_parameters": "8B", "model_type": "chat", "model_source": "open", "compute_provider": "Fireworks AI", "provider": "Fireworks AI", "price_per_1m_input": 0.2, "price_per_1m_output": 0.2, "price_blended": 0.2, "latency_ms": 160, "throughput_tps": 200, "status": "healthy", "context_window": 131072, "openai_compatible": true, "endpoint": "https://fireworks.ai/", "api_base_url": "https://api.fireworks.ai/inference/v1", "developer_website": "https://ai.meta.com/llama/", "provider_website": "https://fireworks.ai/", "region": "us", "source_url": "https://fireworks.ai/pricing", "fetched_at": "2026-04-06T17:37:04Z", "source": "scraped", "price_snapshot_date": "2026-04-06" }, { "model_label": "Mistral Small 3.1", "model_id": "mistralai/Mistral-Small-24B-Instruct-2501", "model_developer": "Mistral", "model_release_date": "2025-03-17", "model_parameters": "24B", "model_type": "chat", "model_source": "open", "compute_provider": "Together AI", "provider": "Together AI", "price_per_1m_input": 0.2, "price_per_1m_output": 0.2, "price_blended": 0.2, "latency_ms": 190, "throughput_tps": 135, "status": "healthy", "context_window": 32768, "openai_compatible": true, "endpoint": "https://www.together.ai/", "api_base_url": "https://api.together.xyz/v1", "developer_website": "https://mistral.ai/", "provider_website": "https://www.together.ai/", "region": "us", "source_url": "https://www.together.ai/pricing", "fetched_at": "2026-04-06T18:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-06" }, { "model_label": "Llama 4 Maverick", "model_id": "meta-llama/Llama-4-Maverick-17B-128E", "model_developer": "Meta", "model_release_date": "2025-04-05", "model_parameters": "17B\u00d7128E (MoE)", "model_type": "chat, vision", "model_source": "open", "compute_provider": "Groq", "provider": "Groq", "price_per_1m_input": 0.2, "price_per_1m_output": 0.2, "price_blended": 0.2, "latency_ms": 160, "throughput_tps": 180, "status": "healthy", "context_window": 1000000, "openai_compatible": true, "endpoint": "https://groq.com/", "api_base_url": "https://api.groq.com/openai/v1", "developer_website": "https://ai.meta.com/llama/", "provider_website": "https://groq.com/", "region": "us", "source_url": "https://groq.com/pricing", "fetched_at": "2026-04-06T20:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-06" }, { "model_label": "Qwen 2.5 72B Instruct", "model_id": "Qwen/Qwen2.5-72B-Instruct", "model_developer": "Alibaba", "model_release_date": "2024-09-19", "model_parameters": "72B", "model_type": "chat", "model_source": "open", "compute_provider": "SiliconFlow", "provider": "SiliconFlow", "price_per_1m_input": 0.22, "price_per_1m_output": 0.22, "price_blended": 0.22, "latency_ms": 320, "throughput_tps": 90, "status": "healthy", "context_window": 131072, "openai_compatible": true, "endpoint": "https://siliconflow.cn/", "api_base_url": "https://api.siliconflow.cn/v1", "developer_website": "https://qwenlm.github.io/", "provider_website": "https://siliconflow.cn/", "region": "cn", "source_url": "https://siliconflow.cn/pricing", "fetched_at": "2026-04-08T15:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-08" }, { "model_label": "Llama 4 Scout", "model_id": "meta-llama/Llama-4-Scout-17B-16E", "model_developer": "Meta", "model_release_date": "2025-04-05", "model_parameters": "17B\u00d716E (MoE)", "model_type": "chat, vision", "model_source": "open", "compute_provider": "Groq", "provider": "Groq", "price_per_1m_input": 0.11, "price_per_1m_output": 0.34, "price_blended": 0.225, "latency_ms": 140, "throughput_tps": 200, "status": "healthy", "context_window": 10000000, "openai_compatible": true, "endpoint": "https://groq.com/", "api_base_url": "https://api.groq.com/openai/v1", "developer_website": "https://ai.meta.com/llama/", "provider_website": "https://groq.com/", "region": "us", "source_url": "https://groq.com/pricing", "fetched_at": "2026-04-06T20:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-06" }, { "model_label": "Llama 4 Maverick", "model_id": "meta-llama/Llama-4-Maverick-17B-128E", "model_developer": "Meta", "model_release_date": "2025-04-05", "model_parameters": "17B\u00d7128E (MoE)", "model_type": "chat, vision", "model_source": "open", "compute_provider": "Together AI", "provider": "Together AI", "price_per_1m_input": 0.25, "price_per_1m_output": 0.25, "price_blended": 0.25, "latency_ms": 190, "throughput_tps": 140, "status": "healthy", "context_window": 1000000, "openai_compatible": true, "endpoint": "https://www.together.ai/", "api_base_url": "https://api.together.xyz/v1", "developer_website": "https://ai.meta.com/llama/", "provider_website": "https://www.together.ai/", "region": "us", "source_url": "https://www.together.ai/pricing", "fetched_at": "2026-04-06T20:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-06" }, { "model_label": "Gemini Flash-Lite 2.5", "model_id": "gemini-2.5-flash-lite-preview", "model_developer": "Google", "model_release_date": "2025-09-25", "model_parameters": "\u2014", "model_type": "chat, vision", "model_source": "closed", "compute_provider": "Google", "provider": "Google", "price_per_1m_input": 0.1, "price_per_1m_output": 0.4, "price_blended": 0.25, "latency_ms": 120, "throughput_tps": 240, "status": "healthy", "context_window": 1048576, "openai_compatible": false, "endpoint": "https://ai.google.dev/", "api_base_url": "https://generativelanguage.googleapis.com/v1beta", "developer_website": "https://ai.google.dev/", "provider_website": "https://ai.google.dev/", "region": "us", "source_url": "https://ai.google.dev/pricing", "fetched_at": "2026-04-06T20:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-06" }, { "model_label": "Llama 3.3 70B Instruct", "model_id": "meta-llama/Llama-3.3-70B-Instruct", "model_developer": "Meta", "model_release_date": "2024-12-06", "model_parameters": "70B", "model_type": "chat", "model_source": "open", "compute_provider": "DeepInfra", "provider": "DeepInfra", "price_per_1m_input": 0.23, "price_per_1m_output": 0.4, "price_blended": 0.281, "latency_ms": 220, "throughput_tps": 90, "status": "healthy", "context_window": 131072, "openai_compatible": true, "endpoint": "https://deepinfra.com/", "api_base_url": "https://api.deepinfra.com/v1/openai", "developer_website": "https://ai.meta.com/llama/", "provider_website": "https://deepinfra.com/", "region": "us", "source_url": "https://deepinfra.com/pricing", "fetched_at": "2026-04-06T18:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-06" }, { "model_label": "Qwen 2.5 72B Instruct", "model_id": "Qwen/Qwen2.5-72B-Instruct", "model_developer": "Alibaba", "model_release_date": "2024-09-19", "model_parameters": "72B", "model_type": "chat", "model_source": "open", "compute_provider": "DeepInfra", "provider": "DeepInfra", "price_per_1m_input": 0.23, "price_per_1m_output": 0.4, "price_blended": 0.281, "latency_ms": 230, "throughput_tps": 95, "status": "healthy", "context_window": 131072, "openai_compatible": true, "endpoint": "https://deepinfra.com/", "api_base_url": "https://api.deepinfra.com/v1/openai", "developer_website": "https://qwenlm.github.io/", "provider_website": "https://deepinfra.com/", "region": "us", "source_url": "https://deepinfra.com/pricing", "fetched_at": "2026-04-06T18:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-06" }, { "model_label": "GPT-4o Mini", "model_id": "gpt-4o-mini", "model_developer": "OpenAI", "model_release_date": "2024-07-18", "model_parameters": "\u2014", "model_type": "chat, vision", "model_source": "closed", "compute_provider": "OpenAI", "provider": "OpenAI", "price_per_1m_input": 0.15, "price_per_1m_output": 0.6, "price_blended": 0.285, "latency_ms": 200, "throughput_tps": 100, "status": "healthy", "context_window": 128000, "openai_compatible": true, "endpoint": "https://openai.com/", "api_base_url": "https://api.openai.com/v1", "developer_website": "https://openai.com/", "provider_website": "https://openai.com/", "region": "us", "source_url": "https://platform.openai.com/docs/pricing", "fetched_at": "2026-04-06T18:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-06" }, { "model_label": "GPT-4o Mini", "model_id": "gpt-4o-mini", "model_developer": "OpenAI", "model_release_date": "2024-07-18", "model_parameters": "\u2014", "model_type": "chat, vision", "model_source": "closed", "compute_provider": "Together AI", "provider": "Together AI", "price_per_1m_input": 0.15, "price_per_1m_output": 0.6, "price_blended": 0.285, "latency_ms": 210, "throughput_tps": 95, "status": "healthy", "context_window": 128000, "openai_compatible": true, "endpoint": "https://www.together.ai/", "api_base_url": "https://api.together.xyz/v1", "developer_website": "https://openai.com/", "provider_website": "https://www.together.ai/", "region": "us", "source_url": "https://www.together.ai/pricing", "fetched_at": "2026-04-06T18:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-06" }, { "model_label": "Command R", "model_id": "command-r-08-2024", "model_developer": "Cohere", "model_release_date": "2024-08-01", "model_parameters": "\u2014", "model_type": "chat", "model_source": "closed", "compute_provider": "Cohere", "provider": "Cohere", "price_per_1m_input": 0.15, "price_per_1m_output": 0.6, "price_blended": 0.285, "latency_ms": 200, "throughput_tps": 120, "status": "healthy", "context_window": 128000, "openai_compatible": false, "endpoint": "https://cohere.com/", "api_base_url": "https://api.cohere.ai/v1", "developer_website": "https://cohere.com/", "provider_website": "https://cohere.com/", "region": "us", "source_url": "https://cohere.com/pricing", "fetched_at": "2026-04-08T18:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-08" }, { "model_label": "Grok Fast 4.1", "model_id": "grok-4-1-fast", "model_developer": "xAI", "model_release_date": "2025-11-15", "model_parameters": "\u2014", "model_type": "chat, vision", "model_source": "closed", "compute_provider": "xAI", "provider": "xAI", "price_per_1m_input": 0.2, "price_per_1m_output": 0.5, "price_blended": 0.29, "latency_ms": 350, "throughput_tps": 85, "status": "healthy", "context_window": 2000000, "openai_compatible": true, "endpoint": "https://x.ai/", "api_base_url": "https://api.x.ai/v1", "developer_website": "https://x.ai/", "provider_website": "https://x.ai/", "region": "us", "source_url": "https://docs.x.ai/docs/models", "fetched_at": "2026-04-08T12:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-08" }, { "model_label": "Gemini Flash 2.5", "model_id": "gemini-2.5-flash", "model_developer": "Google", "model_release_date": "2025-04-17", "model_parameters": "\u2014", "model_type": "chat, vision", "model_source": "closed", "compute_provider": "Fireworks AI", "provider": "Fireworks AI", "price_per_1m_input": 0.12, "price_per_1m_output": 0.5, "price_blended": 0.31, "latency_ms": 145, "throughput_tps": 200, "status": "healthy", "context_window": 1048576, "openai_compatible": false, "endpoint": "https://fireworks.ai/", "api_base_url": "https://api.fireworks.ai/inference/v1", "developer_website": "https://ai.google.dev/", "provider_website": "https://fireworks.ai/", "region": "us", "source_url": "https://fireworks.ai/pricing", "fetched_at": "2026-04-06T20:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-06" }, { "model_label": "Qwen 3 235B Instruct", "model_id": "Qwen/Qwen3-235B-A22B", "model_developer": "Alibaba", "model_release_date": "2025-04-29", "model_parameters": "235B+A22B (MoE)", "model_type": "chat", "model_source": "open", "compute_provider": "DeepInfra", "provider": "DeepInfra", "price_per_1m_input": 0.35, "price_per_1m_output": 0.35, "price_blended": 0.35, "latency_ms": 250, "throughput_tps": 100, "status": "healthy", "context_window": 131072, "openai_compatible": true, "endpoint": "https://deepinfra.com/", "api_base_url": "https://api.deepinfra.com/v1/openai", "developer_website": "https://qwenlm.github.io/", "provider_website": "https://deepinfra.com/", "region": "us", "source_url": "https://deepinfra.com/pricing", "fetched_at": "2026-04-06T20:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-06" }, { "model_label": "Gemini Flash 2.5", "model_id": "gemini-2.5-flash", "model_developer": "Google", "model_release_date": "2025-04-17", "model_parameters": "\u2014", "model_type": "chat, vision", "model_source": "closed", "compute_provider": "Google", "provider": "Google", "price_per_1m_input": 0.15, "price_per_1m_output": 0.6, "price_blended": 0.375, "latency_ms": 140, "throughput_tps": 210, "status": "healthy", "context_window": 1048576, "openai_compatible": false, "endpoint": "https://ai.google.dev/", "api_base_url": "https://generativelanguage.googleapis.com/v1beta", "developer_website": "https://ai.google.dev/", "provider_website": "https://ai.google.dev/", "region": "us", "source_url": "https://ai.google.dev/pricing", "fetched_at": "2026-04-06T20:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-06" }, { "model_label": "Qwen 3 235B Instruct", "model_id": "Qwen/Qwen3-235B-A22B-Instruct-2507", "model_developer": "Alibaba", "model_release_date": "2025-04-29", "model_parameters": "235B+A22B (MoE)", "model_type": "chat", "model_source": "open", "compute_provider": "Together AI", "provider": "Together AI", "price_per_1m_input": 0.4, "price_per_1m_output": 0.4, "price_blended": 0.4, "latency_ms": 240, "throughput_tps": 110, "status": "healthy", "context_window": 131072, "openai_compatible": true, "endpoint": "https://www.together.ai/", "api_base_url": "https://api.together.xyz/v1", "developer_website": "https://qwenlm.github.io/", "provider_website": "https://www.together.ai/", "region": "us", "source_url": "https://www.together.ai/pricing", "fetched_at": "2026-04-06T20:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-06" }, { "model_label": "Mistral Codestral 2508", "model_id": "codestral-2508", "model_developer": "Mistral", "model_release_date": "2025-08-01", "model_parameters": "\u2014", "model_type": "chat, reasoning", "model_source": "closed", "compute_provider": "Mistral", "provider": "Mistral", "price_per_1m_input": 0.3, "price_per_1m_output": 0.9, "price_blended": 0.48, "latency_ms": 300, "throughput_tps": 100, "status": "healthy", "context_window": 256000, "openai_compatible": true, "endpoint": "https://mistral.ai/", "api_base_url": "https://api.mistral.ai/v1", "developer_website": "https://mistral.ai/", "provider_website": "https://mistral.ai/", "region": "us", "source_url": "https://mistral.ai/pricing", "fetched_at": "2026-04-08T18:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-08" }, { "model_label": "GPT-5 Nano", "model_id": "gpt-5-nano", "model_developer": "OpenAI", "model_release_date": "2025-08-07", "model_parameters": "\u2014", "model_type": "chat", "model_source": "closed", "compute_provider": "OpenAI", "provider": "OpenAI", "price_per_1m_input": 0.2, "price_per_1m_output": 1.25, "price_blended": 0.515, "latency_ms": 350, "throughput_tps": 85, "status": "healthy", "context_window": 1047576, "openai_compatible": true, "endpoint": "https://openai.com/", "api_base_url": "https://api.openai.com/v1", "developer_website": "https://openai.com/", "provider_website": "https://openai.com/", "region": "us", "source_url": "https://platform.openai.com/docs/pricing", "fetched_at": "2026-04-08T12:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-08" }, { "model_label": "Qwen 3 235B A22B", "model_id": "qwen3-235b-a22b", "model_developer": "Alibaba", "model_release_date": "2025-04-29", "model_parameters": "235B+A22B (MoE)", "model_type": "chat", "model_source": "closed", "compute_provider": "Alibaba Cloud", "provider": "Alibaba Cloud", "price_per_1m_input": 0.55, "price_per_1m_output": 0.55, "price_blended": 0.55, "latency_ms": 320, "throughput_tps": 90, "status": "healthy", "context_window": 131072, "openai_compatible": true, "endpoint": "https://www.alibabacloud.com/", "api_base_url": "https://dashscope.aliyuncs.com/compatible-mode/v1", "developer_website": "https://qwenlm.github.io/", "provider_website": "https://www.alibabacloud.com/", "region": "cn", "source_url": "https://help.aliyun.com/zh/model-studio/", "fetched_at": "2026-04-08T15:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-08" }, { "model_label": "Doubao Pro", "model_id": "doubao-pro-32k", "model_developer": "ByteDance", "model_release_date": "2025-03-15", "model_parameters": "\u2014", "model_type": "chat", "model_source": "closed", "compute_provider": "Volcengine", "provider": "Volcengine", "price_per_1m_input": 0.35, "price_per_1m_output": 1.05, "price_blended": 0.56, "latency_ms": 320, "throughput_tps": 90, "status": "healthy", "context_window": 256000, "openai_compatible": true, "endpoint": "https://www.volcengine.com/", "api_base_url": "https://ark.cn-beijing.volces.com/api/v3", "developer_website": "https://www.volcengine.com/product/doubao", "provider_website": "https://www.volcengine.com/", "region": "cn", "source_url": "https://www.volcengine.com/docs/82379/", "fetched_at": "2026-04-08T15:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-08" }, { "model_label": "Llama 3.3 70B", "model_id": "meta-llama/llama-3.3-70b-instruct", "model_developer": "Meta", "model_release_date": "2024-12-06", "model_parameters": "70B", "model_type": "chat", "model_source": "open", "compute_provider": "Groq", "provider": "Groq", "price_per_1m_input": 0.59, "price_per_1m_output": 0.79, "price_blended": 0.65, "latency_ms": 180, "throughput_tps": 140, "status": "healthy", "context_window": 128000, "openai_compatible": true, "endpoint": "https://groq.com/", "api_base_url": "https://api.groq.com/openai/v1", "developer_website": "https://ai.meta.com/llama/", "provider_website": "https://groq.com/", "region": "us", "source_url": "https://groq.com/pricing", "fetched_at": "2026-04-06T18:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-06" }, { "model_label": "Llama 3.3 70B Instruct", "model_id": "meta-llama/Llama-3.3-70B-Instruct", "model_developer": "Meta", "model_release_date": "2024-12-06", "model_parameters": "70B", "model_type": "chat", "model_source": "open", "compute_provider": "Nebius", "provider": "Nebius", "price_per_1m_input": 0.65, "price_per_1m_output": 0.65, "price_blended": 0.65, "latency_ms": 320, "throughput_tps": 90, "status": "healthy", "context_window": 131072, "openai_compatible": true, "endpoint": "https://nebius.com/", "api_base_url": "https://api.studio.nebius.ai/v1", "developer_website": "https://ai.meta.com/llama/", "provider_website": "https://nebius.com/", "region": "eu", "source_url": "https://nebius.com/pricing", "fetched_at": "2026-04-08T15:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-08" }, { "model_label": "DeepSeek R1", "model_id": "deepseek-r1", "model_developer": "DeepSeek", "model_release_date": "2025-01-20", "model_parameters": "671B (MoE)", "model_type": "reasoning", "model_source": "open", "compute_provider": "Groq", "provider": "Groq", "price_per_1m_input": 0.75, "price_per_1m_output": 0.99, "price_blended": 0.822, "latency_ms": 500, "throughput_tps": 45, "status": "healthy", "context_window": 128000, "openai_compatible": true, "endpoint": "https://groq.com/", "api_base_url": "https://api.groq.com/openai/v1", "developer_website": "https://www.deepseek.com/", "provider_website": "https://groq.com/", "region": "us", "source_url": "https://groq.com/pricing", "fetched_at": "2026-04-06T18:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-06" }, { "model_label": "Llama 3.3 70B Instruct Turbo", "model_id": "meta-llama/Llama-3.3-70B-Instruct-Turbo", "model_developer": "Meta", "model_release_date": "2024-12-06", "model_parameters": "70B", "model_type": "chat", "model_source": "open", "compute_provider": "Together AI", "provider": "Together AI", "price_per_1m_input": 0.88, "price_per_1m_output": 0.88, "price_blended": 0.88, "latency_ms": 200, "throughput_tps": 120, "status": "healthy", "context_window": 131072, "openai_compatible": true, "endpoint": "https://www.together.ai/", "api_base_url": "https://api.together.xyz/v1", "developer_website": "https://ai.meta.com/llama/", "provider_website": "https://www.together.ai/", "region": "us", "source_url": "https://www.together.ai/pricing", "fetched_at": "2026-04-06T18:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-06" }, { "model_label": "Mistral Medium 3", "model_id": "mistral-medium-3-latest", "model_developer": "Mistral", "model_release_date": "2025-05-07", "model_parameters": "\u2014", "model_type": "chat", "model_source": "closed", "compute_provider": "Mistral", "provider": "Mistral", "price_per_1m_input": 0.4, "price_per_1m_output": 2.0, "price_blended": 0.88, "latency_ms": 350, "throughput_tps": 85, "status": "healthy", "context_window": 131072, "openai_compatible": true, "endpoint": "https://mistral.ai/", "api_base_url": "https://api.mistral.ai/v1", "developer_website": "https://mistral.ai/", "provider_website": "https://mistral.ai/", "region": "us", "source_url": "https://mistral.ai/pricing", "fetched_at": "2026-04-08T12:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-08" }, { "model_label": "Llama 3.3 70B Instruct", "model_id": "accounts/fireworks/models/llama-v3p3-70b-instruct", "model_developer": "Meta", "model_release_date": "2024-12-06", "model_parameters": "70B", "model_type": "chat", "model_source": "open", "compute_provider": "Fireworks AI", "provider": "Fireworks AI", "price_per_1m_input": 0.9, "price_per_1m_output": 0.9, "price_blended": 0.9, "latency_ms": 210, "throughput_tps": 100, "status": "healthy", "context_window": 131072, "openai_compatible": true, "endpoint": "https://fireworks.ai/", "api_base_url": "https://api.fireworks.ai/inference/v1", "developer_website": "https://ai.meta.com/llama/", "provider_website": "https://fireworks.ai/", "region": "us", "source_url": "https://fireworks.ai/pricing", "fetched_at": "2026-04-06T18:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-06" }, { "model_label": "DeepSeek V3", "model_id": "deepseek/deepseek-chat", "model_developer": "DeepSeek", "model_release_date": "2024-12-26", "model_parameters": "671B (MoE)", "model_type": "chat", "model_source": "open", "compute_provider": "DeepInfra", "provider": "DeepInfra", "price_per_1m_input": 0.9, "price_per_1m_output": 0.9, "price_blended": 0.9, "latency_ms": 280, "throughput_tps": 85, "status": "healthy", "context_window": 131072, "openai_compatible": true, "endpoint": "https://deepinfra.com/", "api_base_url": "https://api.deepinfra.com/v1/openai", "developer_website": "https://www.deepseek.com/", "provider_website": "https://deepinfra.com/", "region": "us", "source_url": "https://deepinfra.com/pricing", "fetched_at": "2026-04-06T18:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-06" }, { "model_label": "GLM 4.5", "model_id": "glm-4.5", "model_developer": "Zhipu AI", "model_release_date": "2025-07-28", "model_parameters": "\u2014", "model_type": "chat", "model_source": "closed", "compute_provider": "Zhipu AI", "provider": "Zhipu AI", "price_per_1m_input": 0.5, "price_per_1m_output": 2.0, "price_blended": 0.95, "latency_ms": 320, "throughput_tps": 90, "status": "healthy", "context_window": 128000, "openai_compatible": true, "endpoint": "https://open.bigmodel.cn/", "api_base_url": "https://open.bigmodel.cn/api/paas/v4/", "developer_website": "https://www.zhipuai.cn/", "provider_website": "https://www.zhipuai.cn/", "region": "cn", "source_url": "https://open.bigmodel.cn/dev/api", "fetched_at": "2026-04-08T15:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-08" }, { "model_label": "GPT-4.1 Mini", "model_id": "gpt-4.1-mini", "model_developer": "OpenAI", "model_release_date": "2025-04-14", "model_parameters": "\u2014", "model_type": "chat, vision", "model_source": "closed", "compute_provider": "OpenAI", "provider": "OpenAI", "price_per_1m_input": 0.4, "price_per_1m_output": 1.6, "price_blended": 1.0, "latency_ms": 320, "throughput_tps": 120, "status": "healthy", "context_window": 1047576, "openai_compatible": true, "endpoint": "https://openai.com/", "api_base_url": "https://api.openai.com/v1", "developer_website": "https://openai.com/", "provider_website": "https://openai.com/", "region": "us", "source_url": "https://platform.openai.com/docs/pricing", "fetched_at": "2026-04-06T20:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-06" }, { "model_label": "Kimi K2", "model_id": "kimi-k2-0711-preview", "model_developer": "Moonshot", "model_release_date": "2025-07-11", "model_parameters": "\u2014", "model_type": "chat", "model_source": "closed", "compute_provider": "Moonshot", "provider": "Moonshot", "price_per_1m_input": 0.6, "price_per_1m_output": 2.5, "price_blended": 1.17, "latency_ms": 320, "throughput_tps": 90, "status": "healthy", "context_window": 256000, "openai_compatible": true, "endpoint": "https://www.moonshot.cn/", "api_base_url": "https://api.moonshot.cn/v1", "developer_website": "https://www.moonshot.cn/", "provider_website": "https://www.moonshot.cn/", "region": "cn", "source_url": "https://platform.moonshot.cn/docs/pricing", "fetched_at": "2026-04-08T15:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-08" }, { "model_label": "Qwen 2.5 72B Instruct Turbo", "model_id": "Qwen/Qwen2.5-72B-Instruct-Turbo", "model_developer": "Alibaba", "model_release_date": "2024-09-19", "model_parameters": "72B", "model_type": "chat", "model_source": "open", "compute_provider": "Together AI", "provider": "Together AI", "price_per_1m_input": 1.2, "price_per_1m_output": 1.2, "price_blended": 1.2, "latency_ms": 220, "throughput_tps": 100, "status": "healthy", "context_window": 131072, "openai_compatible": true, "endpoint": "https://www.together.ai/", "api_base_url": "https://api.together.xyz/v1", "developer_website": "https://qwenlm.github.io/", "provider_website": "https://www.together.ai/", "region": "us", "source_url": "https://www.together.ai/pricing", "fetched_at": "2026-04-06T18:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-06" }, { "model_label": "DeepSeek V3", "model_id": "deepseek-ai/DeepSeek-V3", "model_developer": "DeepSeek", "model_release_date": "2024-12-26", "model_parameters": "671B (MoE)", "model_type": "chat", "model_source": "open", "compute_provider": "Together AI", "provider": "Together AI", "price_per_1m_input": 1.25, "price_per_1m_output": 1.25, "price_blended": 1.25, "latency_ms": 300, "throughput_tps": 80, "status": "healthy", "context_window": 131072, "openai_compatible": true, "endpoint": "https://www.together.ai/", "api_base_url": "https://api.together.xyz/v1", "developer_website": "https://www.deepseek.com/", "provider_website": "https://www.together.ai/", "region": "us", "source_url": "https://www.together.ai/pricing", "fetched_at": "2026-04-06T18:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-06" }, { "model_label": "Claude Haiku 3.5", "model_id": "claude-3-5-haiku-20241022", "model_developer": "Anthropic", "model_release_date": "2024-10-22", "model_parameters": "\u2014", "model_type": "chat, vision", "model_source": "closed", "compute_provider": "Anthropic", "provider": "Anthropic", "price_per_1m_input": 0.8, "price_per_1m_output": 4.0, "price_blended": 1.76, "latency_ms": 250, "throughput_tps": 120, "status": "healthy", "context_window": 200000, "openai_compatible": false, "endpoint": "https://www.anthropic.com/", "api_base_url": "https://api.anthropic.com/v1", "developer_website": "https://www.anthropic.com/", "provider_website": "https://www.anthropic.com/", "region": "us", "source_url": "https://www.anthropic.com/pricing", "fetched_at": "2026-04-06T18:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-06" }, { "model_label": "Claude Haiku 3.5", "model_id": "claude-3-5-haiku-20241022", "model_developer": "Anthropic", "model_release_date": "2024-10-22", "model_parameters": "\u2014", "model_type": "chat, vision", "model_source": "closed", "compute_provider": "Together AI", "provider": "Together AI", "price_per_1m_input": 0.8, "price_per_1m_output": 4.0, "price_blended": 1.76, "latency_ms": 260, "throughput_tps": 110, "status": "healthy", "context_window": 200000, "openai_compatible": false, "endpoint": "https://www.together.ai/", "api_base_url": "https://api.together.xyz/v1", "developer_website": "https://www.anthropic.com/", "provider_website": "https://www.together.ai/", "region": "us", "source_url": "https://www.together.ai/pricing", "fetched_at": "2026-04-06T18:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-06" }, { "model_label": "GPT-5 Mini", "model_id": "gpt-5-mini", "model_developer": "OpenAI", "model_release_date": "2025-08-07", "model_parameters": "\u2014", "model_type": "chat, vision", "model_source": "closed", "compute_provider": "OpenAI", "provider": "OpenAI", "price_per_1m_input": 0.75, "price_per_1m_output": 4.5, "price_blended": 1.875, "latency_ms": 350, "throughput_tps": 85, "status": "healthy", "context_window": 400000, "openai_compatible": true, "endpoint": "https://openai.com/", "api_base_url": "https://api.openai.com/v1", "developer_website": "https://openai.com/", "provider_website": "https://openai.com/", "region": "us", "source_url": "https://platform.openai.com/docs/pricing", "fetched_at": "2026-04-08T12:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-08" }, { "model_label": "Llama 3.1 405B Instruct", "model_id": "meta-llama/Meta-Llama-3.1-405B-Instruct", "model_developer": "Meta", "model_release_date": "2024-07-23", "model_parameters": "405B", "model_type": "chat", "model_source": "open", "compute_provider": "Together AI", "provider": "Together AI", "price_per_1m_input": 2.0, "price_per_1m_output": 2.0, "price_blended": 2.0, "latency_ms": 350, "throughput_tps": 85, "status": "healthy", "context_window": 131072, "openai_compatible": true, "endpoint": "https://www.together.ai/", "api_base_url": "https://api.together.xyz/v1", "developer_website": "https://ai.meta.com/llama/", "provider_website": "https://www.together.ai/", "region": "us", "source_url": "https://www.together.ai/pricing", "fetched_at": "2026-04-08T12:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-08" }, { "model_label": "o1 Mini", "model_id": "o1-mini", "model_developer": "OpenAI", "model_release_date": "2024-09-12", "model_parameters": "\u2014", "model_type": "reasoning", "model_source": "closed", "compute_provider": "OpenAI", "provider": "OpenAI", "price_per_1m_input": 1.1, "price_per_1m_output": 4.4, "price_blended": 2.09, "latency_ms": 800, "throughput_tps": 30, "status": "healthy", "context_window": 128000, "openai_compatible": true, "endpoint": "https://openai.com/", "api_base_url": "https://api.openai.com/v1", "developer_website": "https://openai.com/", "provider_website": "https://openai.com/", "region": "us", "source_url": "https://platform.openai.com/docs/pricing", "fetched_at": "2026-04-06T18:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-06" }, { "model_label": "o3 Mini", "model_id": "o3-mini", "model_developer": "OpenAI", "model_release_date": "2025-01-31", "model_parameters": "\u2014", "model_type": "reasoning", "model_source": "closed", "compute_provider": "OpenAI", "provider": "OpenAI", "price_per_1m_input": 1.1, "price_per_1m_output": 4.4, "price_blended": 2.09, "latency_ms": 600, "throughput_tps": 50, "status": "healthy", "context_window": 200000, "openai_compatible": true, "endpoint": "https://openai.com/", "api_base_url": "https://api.openai.com/v1", "developer_website": "https://openai.com/", "provider_website": "https://openai.com/", "region": "us", "source_url": "https://platform.openai.com/docs/pricing", "fetched_at": "2026-04-06T18:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-06" }, { "model_label": "Claude Haiku 4.5", "model_id": "claude-haiku-4-5-20251001", "model_developer": "Anthropic", "model_release_date": "2025-10-01", "model_parameters": "\u2014", "model_type": "chat, vision", "model_source": "closed", "compute_provider": "Anthropic", "provider": "Anthropic", "price_per_1m_input": 1.0, "price_per_1m_output": 5.0, "price_blended": 2.2, "latency_ms": 350, "throughput_tps": 85, "status": "healthy", "context_window": 200000, "openai_compatible": false, "endpoint": "https://www.anthropic.com/", "api_base_url": "https://api.anthropic.com/v1", "developer_website": "https://www.anthropic.com/", "provider_website": "https://www.anthropic.com/", "region": "us", "source_url": "https://www.anthropic.com/pricing", "fetched_at": "2026-04-08T12:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-08" }, { "model_label": "Claude Haiku 4.5 (Bedrock)", "model_id": "anthropic.claude-haiku-4-5-20251001-v1:0", "model_developer": "Anthropic", "model_release_date": "2025-10-01", "model_parameters": "\u2014", "model_type": "chat, vision", "model_source": "closed", "compute_provider": "Amazon Bedrock", "provider": "Amazon Bedrock", "price_per_1m_input": 1.0, "price_per_1m_output": 5.0, "price_blended": 2.2, "latency_ms": 380, "throughput_tps": 75, "status": "healthy", "context_window": 200000, "openai_compatible": false, "endpoint": "https://aws.amazon.com/bedrock/", "api_base_url": "https://bedrock-runtime.us-east-1.amazonaws.com", "developer_website": "https://www.anthropic.com/", "provider_website": "https://aws.amazon.com/bedrock/", "region": "us", "source_url": "https://aws.amazon.com/bedrock/pricing/", "fetched_at": "2026-04-08T18:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-08" }, { "model_label": "Gemini Pro 1.5", "model_id": "gemini-1.5-pro", "model_developer": "Google", "model_release_date": "2024-02-15", "model_parameters": "\u2014", "model_type": "chat, vision", "model_source": "closed", "compute_provider": "Google", "provider": "Google", "price_per_1m_input": 1.25, "price_per_1m_output": 5.0, "price_blended": 2.375, "latency_ms": 250, "throughput_tps": 100, "status": "healthy", "context_window": 2000000, "openai_compatible": false, "endpoint": "https://ai.google.dev/", "api_base_url": "https://generativelanguage.googleapis.com/v1beta", "developer_website": "https://ai.google.dev/", "provider_website": "https://ai.google.dev/", "region": "us", "source_url": "https://ai.google.dev/pricing", "fetched_at": "2026-04-06T18:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-06" }, { "model_label": "o4-mini", "model_id": "o4-mini", "model_developer": "OpenAI", "model_release_date": "2025-04-16", "model_parameters": "\u2014", "model_type": "reasoning", "model_source": "closed", "compute_provider": "OpenAI", "provider": "OpenAI", "price_per_1m_input": 1.1, "price_per_1m_output": 4.4, "price_blended": 2.75, "latency_ms": 550, "throughput_tps": 55, "status": "healthy", "context_window": 200000, "openai_compatible": true, "endpoint": "https://openai.com/", "api_base_url": "https://api.openai.com/v1", "developer_website": "https://openai.com/", "provider_website": "https://openai.com/", "region": "us", "source_url": "https://platform.openai.com/docs/pricing", "fetched_at": "2026-04-06T20:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-06" }, { "model_label": "Mistral Large 2", "model_id": "mistral-large-2411", "model_developer": "Mistral", "model_release_date": "2024-11-18", "model_parameters": "\u2014", "model_type": "chat", "model_source": "closed", "compute_provider": "Mistral", "provider": "Mistral", "price_per_1m_input": 2.0, "price_per_1m_output": 6.0, "price_blended": 3.2, "latency_ms": 320, "throughput_tps": 90, "status": "healthy", "context_window": 128000, "openai_compatible": true, "endpoint": "https://mistral.ai/", "api_base_url": "https://api.mistral.ai/v1", "developer_website": "https://mistral.ai/", "provider_website": "https://mistral.ai/", "region": "eu", "source_url": "https://mistral.ai/pricing", "fetched_at": "2026-04-08T15:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-08" }, { "model_label": "Gemini Pro 2.5", "model_id": "gemini-2.5-pro-preview-03-25", "model_developer": "Google", "model_release_date": "2025-03-25", "model_parameters": "\u2014", "model_type": "chat, vision", "model_source": "closed", "compute_provider": "Google", "provider": "Google", "price_per_1m_input": 1.25, "price_per_1m_output": 10.0, "price_blended": 3.875, "latency_ms": 350, "throughput_tps": 80, "status": "healthy", "context_window": 1048576, "openai_compatible": false, "endpoint": "https://ai.google.dev/", "api_base_url": "https://generativelanguage.googleapis.com/v1beta", "developer_website": "https://ai.google.dev/", "provider_website": "https://ai.google.dev/", "region": "us", "source_url": "https://ai.google.dev/pricing", "fetched_at": "2026-04-06T18:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-06" }, { "model_label": "GPT-4.5", "model_id": "gpt-4.5-preview", "model_developer": "OpenAI", "model_release_date": "2025-02-27", "model_parameters": "\u2014", "model_type": "chat, vision", "model_source": "closed", "compute_provider": "OpenAI", "provider": "OpenAI", "price_per_1m_input": 1.5, "price_per_1m_output": 12.0, "price_blended": 4.65, "latency_ms": 380, "throughput_tps": 75, "status": "healthy", "context_window": 128000, "openai_compatible": true, "endpoint": "https://openai.com/", "api_base_url": "https://api.openai.com/v1", "developer_website": "https://openai.com/", "provider_website": "https://openai.com/", "region": "us", "source_url": "https://platform.openai.com/docs/pricing", "fetched_at": "2026-04-08T12:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-08" }, { "model_label": "GPT-4o", "model_id": "gpt-4o", "model_developer": "OpenAI", "model_release_date": "2024-05-13", "model_parameters": "\u2014", "model_type": "chat, vision", "model_source": "closed", "compute_provider": "OpenAI", "provider": "OpenAI", "price_per_1m_input": 2.5, "price_per_1m_output": 10.0, "price_blended": 4.75, "latency_ms": 350, "throughput_tps": 80, "status": "healthy", "context_window": 128000, "openai_compatible": true, "endpoint": "https://openai.com/", "api_base_url": "https://api.openai.com/v1", "developer_website": "https://openai.com/", "provider_website": "https://openai.com/", "region": "us", "source_url": "https://platform.openai.com/docs/pricing", "fetched_at": "2026-04-06T18:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-06" }, { "model_label": "Command R+", "model_id": "command-r-plus-08-2024", "model_developer": "Cohere", "model_release_date": "2024-08-01", "model_parameters": "\u2014", "model_type": "chat", "model_source": "closed", "compute_provider": "Cohere", "provider": "Cohere", "price_per_1m_input": 2.5, "price_per_1m_output": 10.0, "price_blended": 4.75, "latency_ms": 250, "throughput_tps": 100, "status": "healthy", "context_window": 128000, "openai_compatible": false, "endpoint": "https://cohere.com/", "api_base_url": "https://api.cohere.ai/v1", "developer_website": "https://cohere.com/", "provider_website": "https://cohere.com/", "region": "us", "source_url": "https://cohere.com/pricing", "fetched_at": "2026-04-08T18:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-08" }, { "model_label": "GPT-4.1", "model_id": "gpt-4.1", "model_developer": "OpenAI", "model_release_date": "2025-04-14", "model_parameters": "\u2014", "model_type": "chat, vision", "model_source": "closed", "compute_provider": "OpenAI", "provider": "OpenAI", "price_per_1m_input": 2.0, "price_per_1m_output": 8.0, "price_blended": 5.0, "latency_ms": 400, "throughput_tps": 85, "status": "healthy", "context_window": 1047576, "openai_compatible": true, "endpoint": "https://openai.com/", "api_base_url": "https://api.openai.com/v1", "developer_website": "https://openai.com/", "provider_website": "https://openai.com/", "region": "us", "source_url": "https://platform.openai.com/docs/pricing", "fetched_at": "2026-04-06T20:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-06" }, { "model_label": "DeepSeek R1 (0528)", "model_id": "deepseek-ai/DeepSeek-R1-0528", "model_developer": "DeepSeek", "model_release_date": "2025-05-28", "model_parameters": "671B (MoE)", "model_type": "reasoning", "model_source": "open", "compute_provider": "Together AI", "provider": "Together AI", "price_per_1m_input": 3.0, "price_per_1m_output": 7.0, "price_blended": 5.0, "latency_ms": 320, "throughput_tps": 50, "status": "healthy", "context_window": 163840, "openai_compatible": true, "endpoint": "https://www.together.ai/", "api_base_url": "https://api.together.xyz/v1", "developer_website": "https://www.deepseek.com/", "provider_website": "https://www.together.ai/", "region": "us", "source_url": "https://www.together.ai/pricing", "fetched_at": "2026-04-06T20:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-06" }, { "model_label": "Gemini Pro 2.5", "model_id": "gemini-2.5-pro", "model_developer": "Google", "model_release_date": "2025-06-18", "model_parameters": "\u2014", "model_type": "chat, vision", "model_source": "closed", "compute_provider": "Google", "provider": "Google", "price_per_1m_input": 1.25, "price_per_1m_output": 10.0, "price_blended": 5.625, "latency_ms": 360, "throughput_tps": 85, "status": "healthy", "context_window": 1048576, "openai_compatible": false, "endpoint": "https://ai.google.dev/", "api_base_url": "https://generativelanguage.googleapis.com/v1beta", "developer_website": "https://ai.google.dev/", "provider_website": "https://ai.google.dev/", "region": "us", "source_url": "https://ai.google.dev/pricing", "fetched_at": "2026-04-06T20:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-06" }, { "model_label": "GPT-5", "model_id": "gpt-5", "model_developer": "OpenAI", "model_release_date": "2025-08-07", "model_parameters": "\u2014", "model_type": "chat, vision", "model_source": "closed", "compute_provider": "OpenAI", "provider": "OpenAI", "price_per_1m_input": 2.5, "price_per_1m_output": 15.0, "price_blended": 6.25, "latency_ms": 350, "throughput_tps": 85, "status": "healthy", "context_window": 400000, "openai_compatible": true, "endpoint": "https://openai.com/", "api_base_url": "https://api.openai.com/v1", "developer_website": "https://openai.com/", "provider_website": "https://openai.com/", "region": "us", "source_url": "https://platform.openai.com/docs/pricing", "fetched_at": "2026-04-08T12:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-08" }, { "model_label": "Claude Sonnet 3.5", "model_id": "claude-3-5-sonnet-20241022", "model_developer": "Anthropic", "model_release_date": "2024-10-22", "model_parameters": "\u2014", "model_type": "chat, vision", "model_source": "closed", "compute_provider": "Anthropic", "provider": "Anthropic", "price_per_1m_input": 3.0, "price_per_1m_output": 15.0, "price_blended": 6.6, "latency_ms": 400, "throughput_tps": 70, "status": "healthy", "context_window": 200000, "openai_compatible": false, "endpoint": "https://www.anthropic.com/", "api_base_url": "https://api.anthropic.com/v1", "developer_website": "https://www.anthropic.com/", "provider_website": "https://www.anthropic.com/", "region": "us", "source_url": "https://www.anthropic.com/pricing", "fetched_at": "2026-04-06T18:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-06" }, { "model_label": "Claude Sonnet 3.7", "model_id": "claude-3-7-sonnet-20250219", "model_developer": "Anthropic", "model_release_date": "2025-02-19", "model_parameters": "\u2014", "model_type": "chat, vision", "model_source": "closed", "compute_provider": "Anthropic", "provider": "Anthropic", "price_per_1m_input": 3.0, "price_per_1m_output": 15.0, "price_blended": 6.6, "latency_ms": 450, "throughput_tps": 65, "status": "healthy", "context_window": 200000, "openai_compatible": false, "endpoint": "https://www.anthropic.com/", "api_base_url": "https://api.anthropic.com/v1", "developer_website": "https://www.anthropic.com/", "provider_website": "https://www.anthropic.com/", "region": "us", "source_url": "https://www.anthropic.com/pricing", "fetched_at": "2026-04-06T18:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-06" }, { "model_label": "Claude Sonnet 4", "model_id": "claude-sonnet-4-20250514", "model_developer": "Anthropic", "model_release_date": "2025-05-22", "model_parameters": "\u2014", "model_type": "chat, vision", "model_source": "closed", "compute_provider": "Anthropic", "provider": "Anthropic", "price_per_1m_input": 3.0, "price_per_1m_output": 15.0, "price_blended": 6.6, "latency_ms": 420, "throughput_tps": 75, "status": "healthy", "context_window": 200000, "openai_compatible": false, "endpoint": "https://www.anthropic.com/", "api_base_url": "https://api.anthropic.com/v1", "developer_website": "https://www.anthropic.com/", "provider_website": "https://www.anthropic.com/", "region": "us", "source_url": "https://www.anthropic.com/pricing", "fetched_at": "2026-04-06T20:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-06" }, { "model_label": "Claude Sonnet 4.5", "model_id": "claude-sonnet-4-5-20250929", "model_developer": "Anthropic", "model_release_date": "2025-09-29", "model_parameters": "\u2014", "model_type": "chat, vision", "model_source": "closed", "compute_provider": "Anthropic", "provider": "Anthropic", "price_per_1m_input": 3.0, "price_per_1m_output": 15.0, "price_blended": 6.6, "latency_ms": 350, "throughput_tps": 85, "status": "healthy", "context_window": 200000, "openai_compatible": false, "endpoint": "https://www.anthropic.com/", "api_base_url": "https://api.anthropic.com/v1", "developer_website": "https://www.anthropic.com/", "provider_website": "https://www.anthropic.com/", "region": "us", "source_url": "https://www.anthropic.com/pricing", "fetched_at": "2026-04-08T12:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-08" }, { "model_label": "Grok 4", "model_id": "grok-4", "model_developer": "xAI", "model_release_date": "2025-07-01", "model_parameters": "\u2014", "model_type": "chat, vision", "model_source": "closed", "compute_provider": "xAI", "provider": "xAI", "price_per_1m_input": 3.0, "price_per_1m_output": 15.0, "price_blended": 6.6, "latency_ms": 350, "throughput_tps": 85, "status": "healthy", "context_window": 256000, "openai_compatible": true, "endpoint": "https://x.ai/", "api_base_url": "https://api.x.ai/v1", "developer_website": "https://x.ai/", "provider_website": "https://x.ai/", "region": "us", "source_url": "https://docs.x.ai/docs/models", "fetched_at": "2026-04-08T12:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-08" }, { "model_label": "Claude Sonnet 4.6", "model_id": "claude-sonnet-4-6", "model_developer": "Anthropic", "model_release_date": "2026-02-10", "model_parameters": "\u2014", "model_type": "chat, vision", "model_source": "closed", "compute_provider": "Anthropic", "provider": "Anthropic", "price_per_1m_input": 3.0, "price_per_1m_output": 15.0, "price_blended": 6.6, "latency_ms": 400, "throughput_tps": 80, "status": "healthy", "context_window": 1000000, "openai_compatible": false, "endpoint": "https://www.anthropic.com/", "api_base_url": "https://api.anthropic.com/v1", "developer_website": "https://www.anthropic.com/", "provider_website": "https://www.anthropic.com/", "region": "us", "source_url": "https://platform.claude.com/docs/en/about-claude/pricing", "fetched_at": "2026-04-08T18:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-08" }, { "model_label": "Perplexity Sonar Pro", "model_id": "sonar-pro", "model_developer": "Perplexity", "model_release_date": "2025-01-15", "model_parameters": "\u2014", "model_type": "chat, vision", "model_source": "closed", "compute_provider": "Perplexity", "provider": "Perplexity", "price_per_1m_input": 3.0, "price_per_1m_output": 15.0, "price_blended": 6.6, "latency_ms": 400, "throughput_tps": 70, "status": "healthy", "context_window": 200000, "openai_compatible": true, "endpoint": "https://www.perplexity.ai/", "api_base_url": "https://api.perplexity.ai", "developer_website": "https://www.perplexity.ai/", "provider_website": "https://www.perplexity.ai/", "region": "us", "source_url": "https://docs.perplexity.ai/docs/getting-started/pricing", "fetched_at": "2026-04-08T18:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-08" }, { "model_label": "DeepSeek R1", "model_id": "deepseek-ai/DeepSeek-R1", "model_developer": "DeepSeek", "model_release_date": "2025-01-20", "model_parameters": "671B (MoE)", "model_type": "reasoning", "model_source": "open", "compute_provider": "Together AI", "provider": "Together AI", "price_per_1m_input": 7.0, "price_per_1m_output": 7.0, "price_blended": 7.0, "latency_ms": 800, "throughput_tps": 40, "status": "healthy", "context_window": 163840, "openai_compatible": true, "endpoint": "https://www.together.ai/", "api_base_url": "https://api.together.xyz/v1", "developer_website": "https://www.deepseek.com/", "provider_website": "https://www.together.ai/", "region": "us", "source_url": "https://www.together.ai/pricing", "fetched_at": "2026-04-06T18:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-06" }, { "model_label": "Claude Opus 4.5", "model_id": "claude-opus-4-5-20251101", "model_developer": "Anthropic", "model_release_date": "2025-11-01", "model_parameters": "\u2014", "model_type": "chat, vision", "model_source": "closed", "compute_provider": "Anthropic", "provider": "Anthropic", "price_per_1m_input": 5.0, "price_per_1m_output": 25.0, "price_blended": 11.0, "latency_ms": 350, "throughput_tps": 85, "status": "healthy", "context_window": 200000, "openai_compatible": false, "endpoint": "https://www.anthropic.com/", "api_base_url": "https://api.anthropic.com/v1", "developer_website": "https://www.anthropic.com/", "provider_website": "https://www.anthropic.com/", "region": "us", "source_url": "https://www.anthropic.com/pricing", "fetched_at": "2026-04-08T12:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-08" }, { "model_label": "Claude Opus 4.6", "model_id": "claude-opus-4-6", "model_developer": "Anthropic", "model_release_date": "2026-02-05", "model_parameters": "\u2014", "model_type": "chat, vision", "model_source": "closed", "compute_provider": "Anthropic", "provider": "Anthropic", "price_per_1m_input": 5.0, "price_per_1m_output": 25.0, "price_blended": 15.0, "latency_ms": 650, "throughput_tps": 40, "status": "healthy", "context_window": 1000000, "openai_compatible": false, "endpoint": "https://www.anthropic.com/", "api_base_url": "https://api.anthropic.com/v1", "developer_website": "https://www.anthropic.com/", "provider_website": "https://www.anthropic.com/", "region": "us", "source_url": "https://www.anthropic.com/news/claude-opus-4-6", "fetched_at": "2026-04-06T20:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-06" }, { "model_label": "o3", "model_id": "o3", "model_developer": "OpenAI", "model_release_date": "2025-04-20", "model_parameters": "\u2014", "model_type": "reasoning", "model_source": "closed", "compute_provider": "OpenAI", "provider": "OpenAI", "price_per_1m_input": 10.0, "price_per_1m_output": 40.0, "price_blended": 19.0, "latency_ms": 350, "throughput_tps": 85, "status": "healthy", "context_window": 200000, "openai_compatible": true, "endpoint": "https://openai.com/", "api_base_url": "https://api.openai.com/v1", "developer_website": "https://openai.com/", "provider_website": "https://openai.com/", "region": "us", "source_url": "https://platform.openai.com/docs/pricing", "fetched_at": "2026-04-08T12:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-08" }, { "model_label": "Claude Opus 4", "model_id": "claude-opus-4-20250514", "model_developer": "Anthropic", "model_release_date": "2025-05-22", "model_parameters": "\u2014", "model_type": "chat, vision", "model_source": "closed", "compute_provider": "Anthropic", "provider": "Anthropic", "price_per_1m_input": 15.0, "price_per_1m_output": 75.0, "price_blended": 45.0, "latency_ms": 600, "throughput_tps": 45, "status": "healthy", "context_window": 200000, "openai_compatible": false, "endpoint": "https://www.anthropic.com/", "api_base_url": "https://api.anthropic.com/v1", "developer_website": "https://www.anthropic.com/", "provider_website": "https://www.anthropic.com/", "region": "us", "source_url": "https://www.anthropic.com/pricing", "fetched_at": "2026-04-06T20:00:00Z", "source": "manual", "price_snapshot_date": "2026-04-06" } ] }