{"object":"list","data":[{"id":"anthropic/claude-fable-5","canonical_slug":"anthropic/claude-fable-5","name":"Anthropic: Claude Fable 5","description":"Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is suited for long-running, complex, and asynchronous tasks that previously required frequent human check-ins.\n\nIt is particularly strong at end-to-end work that would otherwise take a person hours, days, or weeks - taking on problems that are long-running, ambiguous, or highly multi-step. It executes well-scoped tasks with few mistakes, automatically self-correcting through verification loops, and ships with robust safeguards.","created":1792646463,"context_length":1000000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"pricing":{"prompt":"0.000008","completion":"0.00004","input_cache_read":"0.0000008","input_cache_write":"0.00001","input_cache_write_1h":"0.000016"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":128000},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/anthropic/claude-fable-5/endpoints"},"object":"model","owned_by":"surogate-router","reasoning_efforts":["low","medium","high","xhigh","max"]},{"id":"anthropic/claude-fable-5.1","canonical_slug":"anthropic/claude-fable-5.1","name":"Anthropic: Claude Fable 5.1","description":"Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual code generation, and finance and analysis tasks in particular. It also tends to be more concise than Fable 5 in its plans and summaries. We recommend testing it as a direct upgrade wherever you use Fable 5 today, and alongside Opus 5 on reasoning-heavy tasks.","created":1792646439,"context_length":1000000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"pricing":{"prompt":"0.000008","completion":"0.00004","input_cache_read":"0.0000002","input_cache_write":"0.00001","input_cache_write_1h":"0.000016"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":128000},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/anthropic/claude-fable-5.1/endpoints"},"object":"model","owned_by":"surogate-router","reasoning_efforts":["low","medium","high","xhigh","max"]},{"id":"anthropic/claude-haiku-5.5","canonical_slug":"anthropic/claude-haiku-5.5","name":"Anthropic: Claude Haiku 5.5","description":"Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and knowledge work, and accepts text and image input with a 1M-token context window.\n\nIt is the first Haiku model with adjustable effort. Thinking is adaptive and on by default, with effort as the main lever for trading off depth, latency, and cost; it can be turned off at low, medium, and high effort.","created":1792642052,"context_length":1000000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"pricing":{"prompt":"0.00000008","completion":"0.0000004","input_cache_read":"0.000000008","input_cache_write":"0.0000001","input_cache_write_1h":"0.00000016"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":128000},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/anthropic/claude-haiku-5.5/endpoints"},"object":"model","owned_by":"surogate-router","reasoning_efforts":["none","low","medium","high","xhigh","max"]},{"id":"anthropic/claude-opus-4.7","canonical_slug":"anthropic/claude-opus-4.7","name":"Anthropic: Claude Opus 4.7","description":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on complex, multi-step tasks and more reliable agentic execution across extended workflows. It is especially effective for asynchronous agent pipelines where tasks unfold over time - large codebases, multi-stage debugging, and end-to-end project orchestration.\n\nBeyond coding, Opus 4.7 brings improved knowledge work capabilities - from drafting documents and building presentations to analyzing data. It maintains coherence across very long outputs and extended sessions, making it a strong default for tasks that require persistence, judgment, and follow-through.","created":1792646466,"context_length":1000000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"pricing":{"prompt":"0.000004","completion":"0.00002","input_cache_read":"0.0000004","input_cache_write":"0.000005","input_cache_write_1h":"0.000008"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":128000},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/anthropic/claude-opus-4.7/endpoints"},"object":"model","owned_by":"surogate-router","reasoning_efforts":["none","low","medium","high","xhigh","max"]},{"id":"anthropic/claude-opus-4.8","canonical_slug":"anthropic/claude-opus-4.8","name":"Anthropic: Claude Opus 4.8","description":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context window. It is suited for highly autonomous agents, long-horizon agentic work, knowledge work, and memory-driven tasks where coherence over extended sessions matters.\n\nIt is particularly strong on multi-step reasoning, complex coding, and end-to-end project orchestration - large codebases, multi-stage debugging, and long-running asynchronous agent pipelines. Beyond coding, it handles knowledge work such as drafting documents, building presentations, and analyzing data, maintaining quality across very long outputs.","created":1792646459,"context_length":1000000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"pricing":{"prompt":"0.000004","completion":"0.00002","input_cache_read":"0.0000004","input_cache_write":"0.000005","input_cache_write_1h":"0.000008"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":128000},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/anthropic/claude-opus-4.8/endpoints"},"object":"model","owned_by":"surogate-router","reasoning_efforts":["none","low","medium","high","xhigh","max"]},{"id":"anthropic/claude-opus-5","canonical_slug":"anthropic/claude-opus-5","name":"Anthropic: Claude Opus 5","description":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis of charts and documents, complex office deliverables, and coordinating parallel subagents.\n\nThe model maintains strong instruction following and tool use across extended tasks, while remaining effective at lower effort settings for workloads that prioritize latency and token efficiency.","created":1792646452,"context_length":1000000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"pricing":{"prompt":"0.000004","completion":"0.00002","input_cache_read":"0.0000004","input_cache_write":"0.000005","input_cache_write_1h":"0.000008"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":128000},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/anthropic/claude-opus-5/endpoints"},"object":"model","owned_by":"surogate-router","reasoning_efforts":["none","low","medium","high","xhigh","max"]},{"id":"anthropic/claude-opus-5.5","canonical_slug":"anthropic/claude-opus-5.5","name":"Anthropic: Claude Opus 5.5","description":"Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code review and bug finding, financial and scientific analysis, and reading dense charts, diagrams, and screenshots, and it is more careful than its predecessor about only stating figures and citing sources it can back up.\n\nThe model completes comparable tasks in fewer steps and with fewer tokens than Opus 5, and reports on its work in plainer language, with clear updates on what it did, what it found, and what it needs from the user. Thinking is always adaptive, so effort is the main lever for trading off depth, latency, and cost, and lower effort settings remain effective for latency-sensitive workloads.","created":1792646443,"context_length":1000000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"pricing":{"prompt":"0.00000376","completion":"0.0000188","input_cache_read":"0.000000188","input_cache_write":"0.0000047","input_cache_write_1h":"0.00000752"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":128000},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/anthropic/claude-opus-5.5/endpoints"},"object":"model","owned_by":"surogate-router","reasoning_efforts":["low","medium","high","xhigh","max"]},{"id":"anthropic/claude-sonnet-5","canonical_slug":"anthropic/claude-sonnet-5","name":"Anthropic: Claude Sonnet 5","description":"Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max, and x-high), a 1M-token context window, and text, image, and file inputs. Sonnet 5 uses an updated tokenizer and includes real-time cyber safeguards that block certain high-risk dual-use activities.","created":1792646451,"context_length":1000000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"pricing":{"prompt":"0.0000016","completion":"0.000008","input_cache_read":"0.00000016","input_cache_write":"0.000002","input_cache_write_1h":"0.0000032"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":128000},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/anthropic/claude-sonnet-5/endpoints"},"object":"model","owned_by":"surogate-router","reasoning_efforts":["none","low","medium","high","xhigh","max"]},{"id":"anthropic/claude-sonnet-5.5","canonical_slug":"anthropic/claude-sonnet-5.5","name":"Anthropic: Claude Sonnet 5.5","description":"Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing polished documents, slides, and spreadsheets, and it writes and communicates more clearly than its predecessor.\n\nThinking is always on, so effort is the main lever for trading off depth, latency, and cost, and lower effort settings keep it responsive for everyday agentic loops.","created":1792646446,"context_length":1000000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"pricing":{"prompt":"0.00000162","completion":"0.0000081","input_cache_read":"0.000000081","input_cache_write":"0.000002025","input_cache_write_1h":"0.00000324"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":128000},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/anthropic/claude-sonnet-5.5/endpoints"},"object":"model","owned_by":"surogate-router","reasoning_efforts":["low","medium","high","xhigh","max"]},{"id":"deepseek/deepseek-v4-flash-0731","canonical_slug":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek: DeepSeek V4 Flash 0731","description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows. This is the GA release of DeepSeek V4 Flash.","created":1792497919,"context_length":1048576,"architecture":{"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"pricing":{"prompt":"0.0000004586","completion":"0.0000009172","input_cache_read":"0.0000000918"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":384000},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v4-flash-0731/endpoints"},"object":"model","owned_by":"surogate-router","reasoning_efforts":["none","low","high","max"]},{"id":"deepseek/deepseek-v4-flash-vision-exp","canonical_slug":"deepseek/deepseek-v4-flash-vision-exp","name":"DeepSeek: DeepSeek V4 Flash Vision Exp","description":"DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of DeepSeek V4 Flash 0731 from DeepSeek, adding image understanding while matching the base model on text capabilities including agents, reasoning, and world knowledge. It is a sparse mixture-of-experts model with 13B active parameters out of 284B total.\n\nIt is suited for document and chart understanding, visual question answering, and multimodal agent workflows that interleave text and images.","created":1792497923,"context_length":1048576,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"pricing":{"prompt":"0.00000033","completion":"0.00000099","input_cache_read":"0.0000000105"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":262144},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v4-flash-vision-exp/endpoints"},"object":"model","owned_by":"surogate-router","reasoning_efforts":["none","low","high","max"]},{"id":"deepseek/deepseek-v4-pro-0813","canonical_slug":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek: DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.","created":1792497927,"context_length":1048576,"architecture":{"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"pricing":{"prompt":"0.0000013","completion":"0.0000026","input_cache_read":"0.0000001"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":16384},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v4-pro-0813/endpoints"},"object":"model","owned_by":"surogate-router","reasoning_efforts":["none","low","high","max"]},{"id":"deepseek/deepseek-v4.1-flash","canonical_slug":"deepseek/deepseek-v4.1-flash","name":"DeepSeek: DeepSeek V4.1 Flash","description":"DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on output from a 552B-parameter backbone, an asymmetric split that keeps per-token compute low relative to the model's total size. Image understanding is native to the architecture, with visual and text embeddings trained jointly from the start of pre-training rather than added afterward as in the earlier experimental V4 Flash Vision Exp.\n\nIt is suited for coding, terminal, and computer-use agents, along with long-horizon tasks that must run to completion across many steps and long-context analysis. Compressed KV caching cuts cache memory to roughly a quarter of the previous Flash generation, significantly reducing costs on agentic workloads. DeepSeek positions it as the cost-efficient tier of the V4.1 family and reports that it exceeds V4 Pro on performance, speed, and task completion time.","created":1792497912,"context_length":1048576,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"pricing":{"prompt":"0.0000002","completion":"0.0000006","input_cache_read":"0.000000006","input_cache_write":"0.0000003"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":131072},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v4.1-flash/endpoints"},"object":"model","owned_by":"surogate-router","reasoning_efforts":["none","low","high","max"]},{"id":"deepseek/deepseek-v4.1-flash-1017","canonical_slug":"deepseek/deepseek-v4.1-flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017","description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name. V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on output from a 552B-parameter backbone, an asymmetric split that keeps per-token compute low relative to the model's total size. Image understanding is native to the architecture, with visual and text embeddings trained jointly from the start of pre-training rather than added afterward as in the earlier experimental V4 Flash Vision Exp.\n\nIt is suited for coding, terminal, and computer-use agents, along with long-horizon tasks that must run to completion across many steps and long-context analysis. Compressed KV caching cuts cache memory to roughly a quarter of the previous Flash generation, significantly reducing costs on agentic workloads. DeepSeek positions it as the cost-efficient tier of the V4.1 family and reports that it exceeds V4 Pro on performance, speed, and task completion time.","created":1792497915,"context_length":1048576,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"pricing":{"prompt":"0.000000166","completion":"0.00000066","input_cache_read":"0.00000000498","input_cache_write":"0.000000249"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":131072},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/deepseek/deepseek-v4.1-flash-1017/endpoints"},"object":"model","owned_by":"surogate-router","reasoning_efforts":["none","low","high","max"]},{"id":"google/gemma-4-26b-a4b-it","canonical_slug":"google/gemma-4-26b-a4b-it","name":"Google: Gemma 4 26B A4B","description":"Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at a fraction of the compute cost. Supports multimodal input including text, images, and video (up to 60s at 1fps). Features a 256K token context window, native function calling, configurable thinking/reasoning mode, and structured output support. Released under Apache 2.0.","created":1792497947,"context_length":262144,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"pricing":{"prompt":"0.00000013","completion":"0.0000004","input_cache_read":"0.00000013"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":16384},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/google/gemma-4-26b-a4b-it/endpoints"},"object":"model","owned_by":"surogate-router"},{"id":"google/gemma-4-31b-it","canonical_slug":"google/gemma-4-31b-it","name":"Google: Gemma 4 31B","description":"Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function calling, and multilingual support across 140+ languages. Strong on coding, reasoning, and document understanding tasks. Apache 2.0 license.","created":1792497951,"context_length":262144,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"pricing":{"prompt":"0.000000184","completion":"0.000000368","input_cache_read":"0.000000184"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":16384},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/google/gemma-4-31b-it/endpoints"},"object":"model","owned_by":"surogate-router"},{"id":"mistralai/mistral-medium-3-5","canonical_slug":"mistralai/mistral-medium-3-5","name":"Mistral: Mistral Medium 3.5","description":"Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...","created":1792574656,"context_length":180000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"pricing":{"prompt":"0.000001186524","completion":"0.00000593262","input_cache_read":"0.000001186524"},"top_provider":{"is_moderated":false,"context_length":180000,"max_completion_tokens":16384},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/mistralai/mistral-medium-3-5/endpoints"},"object":"model","owned_by":"surogate-router","reasoning_efforts":["none","high"]},{"id":"mistralai/mistral-small-3.2-24b-instruct","canonical_slug":"mistralai/mistral-small-3.2-24b-instruct","name":"Mistral: Mistral Small 3.2 24B","description":"Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on...","created":1792574659,"context_length":128000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"pricing":{"prompt":"0.000000129","completion":"0.000000300975","input_cache_read":"0.000000129"},"top_provider":{"is_moderated":false,"context_length":128000,"max_completion_tokens":32768},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/mistralai/mistral-small-3.2-24b-instruct/endpoints"},"object":"model","owned_by":"surogate-router"},{"id":"moondream/moondream3-preview","canonical_slug":"moondream/moondream3-preview","name":"Moondream: Moondream 3 Preview","description":"Moondream 3 Preview is a vision-language model from Moondream with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and visual reasoning over images, with a 32K-token context and an optional reasoning mode.","created":1792555050,"context_length":32000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"pricing":{"prompt":"0.0000003","completion":"0.0000025","input_cache_read":"0.0000003"},"top_provider":{"is_moderated":false,"context_length":32000,"max_completion_tokens":4096},"per_request_limits":null,"supported_parameters":["max_tokens","temperature"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/moondream/moondream3-preview/endpoints"},"object":"model","owned_by":"surogate-router"},{"id":"moondream/moondream3.1-9b-a2b","canonical_slug":"moondream/moondream3.1-9b-a2b","name":"Moondream: Moondream 3.1","description":"Moondream 3.1 is a vision-language model from Moondream, the successor to Moondream 3 Preview, with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and visual reasoning over images, with a 32K-token context and an optional reasoning mode.","created":1792555054,"context_length":32000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"pricing":{"prompt":"0.0000003","completion":"0.0000025","input_cache_read":"0.0000003"},"top_provider":{"is_moderated":false,"context_length":32000,"max_completion_tokens":4096},"per_request_limits":null,"supported_parameters":["max_tokens","temperature"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/moondream/moondream3.1-9b-a2b/endpoints"},"object":"model","owned_by":"surogate-router"},{"id":"moonshotai/kimi-k3","canonical_slug":"moonshotai/kimi-k3","name":"MoonshotAI: Kimi K3","description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at navigating large repositories, using tools, debugging, and iterating against images, logs, tests, and runtime feedback. Its architecture uses KDA and Attention Residuals for computational efficiency.","created":1792497938,"context_length":1048576,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"pricing":{"prompt":"0.000002565","completion":"0.000012825","input_cache_read":"0.0000002565","input_cache_write":"0.0000027","input_cache_write_1h":"0.00000513"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":943718},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/moonshotai/kimi-k3/endpoints"},"object":"model","owned_by":"surogate-router","reasoning_efforts":["none","low","high","max"]},{"id":"moonshotai/kimi-k3.1-pro","canonical_slug":"moonshotai/kimi-k3.1-pro","name":"MoonshotAI: Kimi K3.1 Pro","description":"Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D creation, financial research, and end-to-end agentic knowledge work, with native image and video understanding.","created":1792814762,"context_length":1048576,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"pricing":{"prompt":"0.00000188","completion":"0.0000094","input_cache_read":"0.000000188","input_cache_write":"0.00000188","input_cache_write_1h":"0.00000376"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":943718},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/moonshotai/kimi-k3.1-pro/endpoints"},"object":"model","owned_by":"surogate-router","reasoning_efforts":["none","low","high","max"]},{"id":"nvidia/nemotron-3-super-120b-a12b","canonical_slug":"nvidia/nemotron-3-super-120b-a12b","name":"NVIDIA: Nemotron 3 Super","description":"NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer Mixture-of-Experts architecture with multi-token prediction (MTP), it delivers over 50% higher token generation compared to leading open models.\n\nThe model features a 1M token context window for long-term agent coherence, cross-document reasoning, and multi-step task planning. Latent MoE enables calling 4 experts for the inference cost of only one, improving intelligence and generalization. Multi-environment RL training across 10+ environments delivers leading accuracy on benchmarks including AIME 2025, TerminalBench, and SWE-Bench Verified.\n\nFully open with weights, datasets, and recipes under the NVIDIA Open License, Nemotron 3 Super allows easy customization and secure deployment anywhere — from workstation to cloud.","created":1792497954,"context_length":262144,"architecture":{"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"pricing":{"prompt":"0.000000085","completion":"0.0000004","input_cache_read":"0.000000085"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":16384},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/nvidia/nemotron-3-super-120b-a12b/endpoints"},"object":"model","owned_by":"surogate-router","reasoning_efforts":["none","low","medium"]},{"id":"openai/gpt-4o-mini","canonical_slug":"openai/gpt-4o-mini","name":"OpenAI: GPT-4o-mini","description":"GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs.\n\nAs their most advanced small model, it is many multiples more affordable than other recent frontier models, and more than 60% cheaper than GPT-3.5 Turbo. It maintains SOTA intelligence, while being significantly more cost-effective.\n\nGPT-4o mini achieves an 82% score on MMLU and presently ranks higher than GPT-4 on chat preferences common leaderboards.","created":1792647851,"context_length":128000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"pricing":{"prompt":"0.00000012","completion":"0.00000048","input_cache_read":"0.00000006","input_cache_write":"0.00000012","input_cache_write_1h":"0.00000012"},"top_provider":{"is_moderated":false,"context_length":128000,"max_completion_tokens":16384},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/openai/gpt-4o-mini/endpoints"},"object":"model","owned_by":"surogate-router"},{"id":"openai/gpt-5-mini","canonical_slug":"openai/gpt-5-mini","name":"OpenAI: GPT-5 Mini","description":"GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost. GPT-5 Mini is the successor to OpenAI's o4-mini model.","created":1792647863,"context_length":400000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"pricing":{"prompt":"0.0000002025","completion":"0.00000162","input_cache_read":"0.00000002025","input_cache_write":"0.0000002025","input_cache_write_1h":"0.0000002025"},"top_provider":{"is_moderated":false,"context_length":400000,"max_completion_tokens":128000},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/openai/gpt-5-mini/endpoints"},"object":"model","owned_by":"surogate-router","reasoning_efforts":["minimal","low","medium","high"]},{"id":"openai/gpt-5-nano","canonical_slug":"openai/gpt-5-nano","name":"OpenAI: GPT-5 Nano","description":"GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger counterparts, it retains key instruction-following and safety features. It is the successor to GPT-4.1-nano and offers a lightweight option for cost-sensitive or real-time applications.","created":1792647881,"context_length":400000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"pricing":{"prompt":"0.00000004","completion":"0.00000032","input_cache_read":"0.000000004","input_cache_write":"0.00000004","input_cache_write_1h":"0.00000004"},"top_provider":{"is_moderated":false,"context_length":400000,"max_completion_tokens":128000},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/openai/gpt-5-nano/endpoints"},"object":"model","owned_by":"surogate-router","reasoning_efforts":["minimal","low","medium","high"]},{"id":"openai/gpt-5.4","canonical_slug":"openai/gpt-5.4","name":"OpenAI: GPT-5.4","description":"GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling high-context reasoning, coding, and multimodal analysis within the same workflow.\n\nThe model delivers improved performance in coding, document understanding, tool use, and instruction following. It is designed as a strong default for both general-purpose tasks and software engineering, capable of generating production-quality code, synthesizing information across multiple sources, and executing complex multi-step workflows with fewer iterations and greater token efficiency.","created":1792647866,"context_length":1050000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"pricing":{"prompt":"0.000002","completion":"0.000012","input_cache_read":"0.0000002","input_cache_write":"0.000002","input_cache_write_1h":"0.000002"},"top_provider":{"is_moderated":false,"context_length":1050000,"max_completion_tokens":128000},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/openai/gpt-5.4/endpoints"},"object":"model","owned_by":"surogate-router","reasoning_efforts":["none","low","medium","high","xhigh"]},{"id":"openai/gpt-5.4-mini","canonical_slug":"openai/gpt-5.4-mini","name":"OpenAI: GPT-5.4 Mini","description":"GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding, and tool use, while reducing latency and cost for large-scale deployments.\n\nThe model is designed for production environments that require a balance of capability and efficiency, making it well suited for chat applications, coding assistants, and agent workflows that operate at scale. GPT-5.4 mini delivers reliable instruction following, solid multi-step reasoning, and consistent performance across diverse tasks with improved cost efficiency.","created":1792647854,"context_length":400000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"pricing":{"prompt":"0.0000006","completion":"0.0000036","input_cache_read":"0.00000006","input_cache_write":"0.0000006","input_cache_write_1h":"0.0000006"},"top_provider":{"is_moderated":false,"context_length":400000,"max_completion_tokens":128000},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/openai/gpt-5.4-mini/endpoints"},"object":"model","owned_by":"surogate-router","reasoning_efforts":["none","low","medium","high","xhigh"]},{"id":"openai/gpt-5.4-nano","canonical_slug":"openai/gpt-5.4-nano","name":"OpenAI: GPT-5.4 Nano","description":"GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency use cases such as classification, data extraction, ranking, and sub-agent execution.\n\nThe model prioritizes responsiveness and efficiency over deep reasoning, making it ideal for pipelines that require fast, reliable outputs at scale. GPT-5.4 nano is well suited for background tasks, real-time systems, and distributed agent architectures where minimizing cost and latency is essential.","created":1792647856,"context_length":400000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"pricing":{"prompt":"0.00000016","completion":"0.000001","input_cache_read":"0.000000016","input_cache_write":"0.00000016","input_cache_write_1h":"0.00000016"},"top_provider":{"is_moderated":false,"context_length":400000,"max_completion_tokens":128000},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/openai/gpt-5.4-nano/endpoints"},"object":"model","owned_by":"surogate-router","reasoning_efforts":["none","low","medium","high","xhigh"]},{"id":"openai/gpt-5.5","canonical_slug":"openai/gpt-5.5","name":"OpenAI: GPT-5.5","description":"GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling large-scale reasoning, coding, and multimodal workflows within a single system.","created":1792647868,"context_length":1050000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"pricing":{"prompt":"0.000004","completion":"0.000024","input_cache_read":"0.0000004","input_cache_write":"0.000004","input_cache_write_1h":"0.000004"},"top_provider":{"is_moderated":false,"context_length":1050000,"max_completion_tokens":128000},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/openai/gpt-5.5/endpoints"},"object":"model","owned_by":"surogate-router","reasoning_efforts":["none","low","medium","high","xhigh"]},{"id":"openai/gpt-5.6-luna","canonical_slug":"openai/gpt-5.6-luna","name":"OpenAI: GPT-5.6 Luna","description":"GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for its price tier.","created":1792647538,"context_length":1050000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"pricing":{"prompt":"0.00000016","completion":"0.00000096","input_cache_read":"0.000000016","input_cache_write":"0.00000016","input_cache_write_1h":"0.00000016"},"top_provider":{"is_moderated":false,"context_length":1050000,"max_completion_tokens":128000},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/openai/gpt-5.6-luna/endpoints"},"object":"model","owned_by":"surogate-router","reasoning_efforts":["none","low","medium","high","xhigh","max"]},{"id":"openai/gpt-5.6-sol","canonical_slug":"openai/gpt-5.6-sol","name":"OpenAI: GPT-5.6 Sol","description":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks and long-horizon problem solving.","created":1792647847,"context_length":1050000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"pricing":{"prompt":"0.0000032","completion":"0.000016","input_cache_read":"0.00000032","input_cache_write":"0.0000032","input_cache_write_1h":"0.0000032"},"top_provider":{"is_moderated":false,"context_length":1050000,"max_completion_tokens":128000},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/openai/gpt-5.6-sol/endpoints"},"object":"model","owned_by":"surogate-router","reasoning_efforts":["none","low","medium","high","xhigh","max"]},{"id":"openai/gpt-5.6-terra","canonical_slug":"openai/gpt-5.6-terra","name":"OpenAI: GPT-5.6 Terra","description":"GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic tasks where capability and cost need to be balanced, offering strong performance at roughly half the cost of Sol.","created":1792647850,"context_length":1050000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"pricing":{"prompt":"0.00000184","completion":"0.00001104","input_cache_read":"0.000000184","input_cache_write":"0.00000184","input_cache_write_1h":"0.00000184"},"top_provider":{"is_moderated":false,"context_length":1050000,"max_completion_tokens":128000},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/openai/gpt-5.6-terra/endpoints"},"object":"model","owned_by":"surogate-router","reasoning_efforts":["none","low","medium","high","xhigh","max"]},{"id":"openai/gpt-6-astra","canonical_slug":"openai/gpt-6-astra","name":"OpenAI: GPT-6 Astra","description":"GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon agentic tasks that involve computer and browser use.","created":1792647847,"context_length":1050000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"pricing":{"prompt":"0.00001","completion":"0.00005","input_cache_read":"0.000001","input_cache_write":"0.00001","input_cache_write_1h":"0.00001"},"top_provider":{"is_moderated":false,"context_length":1050000,"max_completion_tokens":128000},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/openai/gpt-6-astra/endpoints"},"object":"model","owned_by":"surogate-router","reasoning_efforts":["low","medium","high","xhigh","max"]},{"id":"openai/gpt-6-luna","canonical_slug":"openai/gpt-6-luna","name":"OpenAI: GPT-6 Luna","description":"GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic tasks, and at higher reasoning effort it can take on complex software engineering and computer-use tasks that previously called for a Sol-tier model. It shares the GPT-6 family's gains in factual reliability and its clearer, more concise communication style.","created":1792647535,"context_length":1050000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"pricing":{"prompt":"0.0000001","completion":"0.0000005","input_cache_read":"0.00000001","input_cache_write":"0.0000001","input_cache_write_1h":"0.0000001"},"top_provider":{"is_moderated":false,"context_length":1050000,"max_completion_tokens":128000},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/openai/gpt-6-luna/endpoints"},"object":"model","owned_by":"surogate-router","reasoning_efforts":["none","low","medium","high","xhigh","max"]},{"id":"openai/gpt-6-sol","canonical_slug":"openai/gpt-6-sol","name":"OpenAI: GPT-6 Sol","description":"GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional work, agentic coding, business workflow automation, and computer use, and is particularly strong at long-horizon software engineering tasks in real codebases. It approaches Astra-level factual reliability at a much lower cost and shares Astra's clearer, more concise communication style in technical and coding conversations.","created":1792647839,"context_length":1050000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"pricing":{"prompt":"0.0000016","completion":"0.000008","input_cache_read":"0.00000016","input_cache_write":"0.0000016","input_cache_write_1h":"0.0000016"},"top_provider":{"is_moderated":false,"context_length":1050000,"max_completion_tokens":128000},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/openai/gpt-6-sol/endpoints"},"object":"model","owned_by":"surogate-router","reasoning_efforts":["none","low","medium","high","xhigh","max"]},{"id":"openai/gpt-6.1-sol","canonical_slug":"openai/gpt-6.1-sol","name":"OpenAI: GPT-6.1 Sol","description":"GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional work, and multi-step business workflow automation, and approaches Astra-level results on these tasks at a much lower cost. Compared with GPT-6 Sol, it makes fewer factual errors and is more reliable at respecting explicit restrictions and user intent during agentic tasks.","created":1792647839,"context_length":1050000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"pricing":{"prompt":"0.0000016","completion":"0.000008","input_cache_read":"0.00000008","input_cache_write":"0.0000016","input_cache_write_1h":"0.0000016"},"top_provider":{"is_moderated":false,"context_length":1050000,"max_completion_tokens":128000},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/openai/gpt-6.1-sol/endpoints"},"object":"model","owned_by":"surogate-router","reasoning_efforts":["low","medium","high","xhigh","max"]},{"id":"openai/gpt-6.1-terra","canonical_slug":"openai/gpt-6.1-terra","name":"OpenAI: GPT-6.1 Terra","description":"GPT-6.1 Terra is the balanced model in OpenAI's GPT-6.1 series, positioned below GPT-6.1 Sol at half its price. It is suited for computer use, everyday coding and reasoning, and agentic tasks where capability and cost need to be balanced.","created":1793095203,"context_length":1050000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"pricing":{"prompt":"0.000001","completion":"0.000005","input_cache_read":"0.00000005","input_cache_write":"0.000001","input_cache_write_1h":"0.000001"},"top_provider":{"is_moderated":false,"context_length":1050000,"max_completion_tokens":128000},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/openai/gpt-6.1-terra/endpoints"},"object":"model","owned_by":"surogate-router","reasoning_efforts":["none","low","medium","high","xhigh","max"]},{"id":"openai/gpt-oss-120b","canonical_slug":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized to run on a single H100 GPU with native MXFP4 quantization. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.","created":1792558709,"context_length":131072,"architecture":{"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"pricing":{"prompt":"0.00000005","completion":"0.00000025","input_cache_read":"0.00000005"},"top_provider":{"is_moderated":false,"context_length":131072,"max_completion_tokens":32768},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/openai/gpt-oss-120b/endpoints"},"object":"model","owned_by":"surogate-router","reasoning_efforts":["low","medium","high"]},{"id":"qwen/qwen3.6-35b-a3b","canonical_slug":"qwen/qwen3.6-35b-a3b","name":"Qwen: Qwen3.6 35B A3B","description":"Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated DeltaNet linear attention with standard gated attention layers, enabling efficient inference at a fraction of the compute cost. The model supports a 262K token native context window (extensible to 1M via YaRN) and accepts text, image, and video inputs. It includes integrated thinking mode with reasoning traces preserved across multi-turn conversations, function calling, and structured output. Released under the Apache 2.0 license.","created":1792497941,"context_length":262144,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"pricing":{"prompt":"0.0000001","completion":"0.00000095","input_cache_read":"0.0000001"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":65536},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/qwen/qwen3.6-35b-a3b/endpoints"},"object":"model","owned_by":"surogate-router"},{"id":"qwen/qwen3.8-27b","canonical_slug":"qwen/qwen3.8-27b","name":"Qwen: Qwen3.8 27B","description":"Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be enabled or disabled.","created":1792497945,"context_length":262144,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"pricing":{"prompt":"0.000000012","completion":"0.00000066","input_cache_read":"0.000000012"},"top_provider":{"is_moderated":false,"context_length":262144,"max_completion_tokens":235929},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/qwen/qwen3.8-27b/endpoints"},"object":"model","owned_by":"surogate-router","reasoning_efforts":["none","low","medium","xhigh"]},{"id":"qwen/qwen3.8-flash","canonical_slug":"qwen/qwen3.8-flash","name":"Qwen: Qwen3.8 Flash","description":"Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-video analysis.","created":1792498887,"context_length":1000000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"pricing":{"prompt":"0.00000015","completion":"0.00000047","input_cache_read":"0.000000016","input_cache_write":"0.0000002"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":131072},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/qwen/qwen3.8-flash/endpoints"},"object":"model","owned_by":"surogate-router"},{"id":"qwen/qwen3.8-max-0902","canonical_slug":"qwen/qwen3.8-max-0902","name":"Qwen: Qwen3.8 Max (0902)","description":"Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts text, image, and video input and returns text, with a 1M-token context window and reasoning enabled by default.\n\nThis snapshot is post-trained for coding and agentic work, including multi-step software projects, multi-tool orchestration, and long-horizon task execution. It also targets chart reasoning, document parsing, and multimodal understanding over long documents and extended video. Tool calling, structured outputs, and configurable reasoning effort are supported.","created":1792498884,"context_length":1000000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"pricing":{"prompt":"0.0000016","completion":"0.0000048","input_cache_read":"0.0000002","input_cache_write":"0.000002"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":131072},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/qwen/qwen3.8-max-0902/endpoints"},"object":"model","owned_by":"surogate-router","reasoning_efforts":["minimal","low","medium","high","xhigh"]},{"id":"qwen/qwen3.8-omni-flash","canonical_slug":"qwen/qwen3.8-omni-flash","name":"Qwen: Qwen3.8 Omni Flash","description":"Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding. It is suited for audio-video analysis and summarization, video editing and production workflows, audio-video dialogue, coding, knowledge work, and GUI interaction, and it is particularly strong at long-form multimedia tasks that combine speech, sound, and visual context. It also supports two-channel and four-channel spatial audio understanding.","created":1792498890,"context_length":1000000,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"pricing":{"prompt":"0.00000012","completion":"0.000000376","input_cache_read":"0.0000000128"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":131072},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/qwen/qwen3.8-omni-flash/endpoints"},"object":"model","owned_by":"surogate-router"},{"id":"surogate/surogate3.7-flash","canonical_slug":"surogate/surogate3.7-flash","name":"Surogate: Surogate 3.7 Flash","created":1792464273,"context_length":1048576,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"pricing":{"prompt":"0.00000015","completion":"0.000001","input_cache_read":"0.00000005"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":32768},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/surogate/surogate3.7-flash/endpoints"},"object":"model","owned_by":"surogate-router"},{"id":"xiaomi/mimo-v2.6-flash","canonical_slug":"xiaomi/mimo-v2.6-flash","name":"Xiaomi: MiMo-V2.6-Flash","description":"MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for greater computational efficiency. The model features a 1M-token context window and native multimodal capabilities. Optimized for agentic workflows, it delivers strong performance across coding, visual, general, and research scenarios, excelling at complex, long-horizon tasks with robust generalization across a diverse range of agent harnesses.","created":1792497909,"context_length":1048576,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"pricing":{"prompt":"0.00000014","completion":"0.00000028","input_cache_read":"0.0000000028"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":943718},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/xiaomi/mimo-v2.6-flash/endpoints"},"object":"model","owned_by":"surogate-router"},{"id":"xiaomi/mimo-v2.6-pro","canonical_slug":"xiaomi/mimo-v2.6-pro","name":"Xiaomi: MiMo-V2.6-Pro","description":"MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi. Built at a scale of over 1T parameters, it is designed to push the ceiling of capability for the most demanding workloads. The model features a 1M-token context window and native multimodal capabilities. Optimized for agentic workflows, it delivers top-tier performance across coding, visual, general, and research scenarios, excelling at complex, long-horizon tasks with robust generalization across a diverse range of agent harnesses.","created":1792497905,"context_length":1048576,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"pricing":{"prompt":"0.00000043","completion":"0.00000087","input_cache_read":"0.0000000036"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":943718},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/xiaomi/mimo-v2.6-pro/endpoints"},"object":"model","owned_by":"surogate-router"},{"id":"z-ai/glm-5.3","canonical_slug":"z-ai/glm-5.3","name":"Z.ai: GLM 5.3","description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves on GLM-5.2 in coding and in the balance between performance and token efficiency.\n\nReasoning is always on and cannot be disabled. Reasoning efforts low, high, and max are supported; max is the default.","created":1792498938,"context_length":1000000,"architecture":{"input_modalities":["text"],"output_modalities":["text"],"modality":"text->text"},"pricing":{"prompt":"0.00000098","completion":"0.00000308","input_cache_read":"0.000000182","input_cache_write":"0.00000098"},"top_provider":{"is_moderated":false,"context_length":1000000,"max_completion_tokens":131072},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/z-ai/glm-5.3/endpoints"},"object":"model","owned_by":"surogate-router","reasoning_efforts":["low","high","max"]},{"id":"z-ai/glm-5.3-flash","canonical_slug":"z-ai/glm-5.3-flash","name":"Z.ai: GLM 5.3 Flash","description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while reducing compute overhead.","created":1792497934,"context_length":1048576,"architecture":{"input_modalities":["text","image"],"output_modalities":["text"],"modality":"text+image->text"},"pricing":{"prompt":"0.00000015","completion":"0.0000005","input_cache_read":"0.00000003","input_cache_write":"0.00000015"},"top_provider":{"is_moderated":false,"context_length":1048576,"max_completion_tokens":943718},"per_request_limits":null,"supported_parameters":["max_tokens","response_format","structured_outputs","temperature","tool_choice","tools"],"default_parameters":{},"supported_voices":null,"links":{"details":"/api/v1/models/z-ai/glm-5.3-flash/endpoints"},"object":"model","owned_by":"surogate-router","reasoning_efforts":["low","high","max"]}],"total_count":49,"links":{"next":null}}