Model catalog
Compare context, capabilities, modalities, token pricing, and live managed-cloud activity across every provider available through the Everstack gateway.
OpenRouter listing date, not necessarily the original model launch. Provider-route pricing and limits verified 2026-09-29; endpoint selection can change rates. Tool, audio, and other non-text charges are not represented by these text token rates.
Adaptive thinking enabled by default; default effort high. Standard synchronous output limit; batch beta limits are separate.
OpenRouter listing date, not necessarily the original model launch. Provider-route pricing and limits verified 2026-09-29; endpoint selection can change rates. Tool, audio, and other non-text charges are not represented by these text token rates.
OpenRouter listing date, not necessarily the original model launch. Provider-route pricing and limits verified 2026-09-29; endpoint selection can change rates. Tool, audio, and other non-text charges are not represented by these text token rates.
OpenRouter listing date, not necessarily the original model launch. Provider-route pricing and limits verified 2026-09-29; endpoint selection can change rates. Tool, audio, and other non-text charges are not represented by these text token rates.
OpenRouter listing date, not necessarily the original model launch. Provider-route pricing and limits verified 2026-09-29; endpoint selection can change rates. Tool, audio, and other non-text charges are not represented by these text token rates.
OpenRouter listing date, not necessarily the original model launch. Provider-route pricing and limits verified 2026-09-29; endpoint selection can change rates. Tool, audio, and other non-text charges are not represented by these text token rates.
OpenRouter listing date, not necessarily the original model launch. Provider-route pricing and limits verified 2026-09-29; endpoint selection can change rates. Tool, audio, and other non-text charges are not represented by these text token rates.
OpenRouter listing date, not necessarily the original model launch. Provider-route pricing and limits verified 2026-09-29; endpoint selection can change rates. Tool, audio, and other non-text charges are not represented by these text token rates.
OpenRouter listing date, not necessarily the original model launch. Provider-route pricing and limits verified 2026-09-29; endpoint selection can change rates. Tool, audio, and other non-text charges are not represented by these text token rates.
Adaptive thinking always on; default effort medium. Standard synchronous output limit; batch beta limits are separate.
OpenRouter listing date, not necessarily the original model launch. Provider-route pricing and limits verified 2026-09-29; endpoint selection can change rates. Tool, audio, and other non-text charges are not represented by these text token rates.
Use Responses for reasoning with tools; Chat Completions function calling requires reasoning_effort=none. Standard global token rates; regional processing adds 10% where available.
Use Responses for reasoning with tools; Chat Completions function calling requires reasoning_effort=none. Standard global token rates; regional processing adds 10% where available.
OpenRouter listing date, not necessarily the original model launch. Provider-route pricing and limits verified 2026-09-29; endpoint selection can change rates. Tool, audio, and other non-text charges are not represented by these text token rates.
OpenRouter listing date, not necessarily the original model launch. Provider-route pricing and limits verified 2026-09-29; endpoint selection can change rates. Tool, audio, and other non-text charges are not represented by these text token rates.
OpenRouter listing date, not necessarily the original model launch. Provider-route pricing and limits verified 2026-09-29; endpoint selection can change rates. Tool, audio, and other non-text charges are not represented by these text token rates.
OpenRouter listing date, not necessarily the original model launch. Provider-route pricing and limits verified 2026-09-29; endpoint selection can change rates. Tool, audio, and other non-text charges are not represented by these text token rates.
OpenRouter listing date, not necessarily the original model launch. Provider-route pricing and limits verified 2026-09-29; endpoint selection can change rates. Tool, audio, and other non-text charges are not represented by these text token rates.
OpenRouter listing date, not necessarily the original model launch. Provider-route pricing and limits verified 2026-09-29; endpoint selection can change rates. Tool, audio, and other non-text charges are not represented by these text token rates.
OpenRouter listing date, not necessarily the original model launch. Provider-route pricing and limits verified 2026-09-29; endpoint selection can change rates. Tool, audio, and other non-text charges are not represented by these text token rates.
OpenRouter listing date, not necessarily the original model launch. Provider-route pricing and limits verified 2026-09-29; endpoint selection can change rates. Tool, audio, and other non-text charges are not represented by these text token rates.
OpenRouter listing date, not necessarily the original model launch. Provider-route pricing and limits verified 2026-09-29; endpoint selection can change rates. Tool, audio, and other non-text charges are not represented by these text token rates.
OpenRouter listing date, not necessarily the original model launch. Provider-route pricing and limits verified 2026-09-29; endpoint selection can change rates. Tool, audio, and other non-text charges are not represented by these text token rates.
OpenRouter listing date, not necessarily the original model launch. Provider-route pricing and limits verified 2026-09-29; endpoint selection can change rates. Tool, audio, and other non-text charges are not represented by these text token rates.
OpenRouter listing date, not necessarily the original model launch. Provider-route pricing and limits verified 2026-09-29; endpoint selection can change rates. Tool, audio, and other non-text charges are not represented by these text token rates.
OpenRouter listing date, not necessarily the original model launch. Provider-route pricing and limits verified 2026-09-29; endpoint selection can change rates. Tool, audio, and other non-text charges are not represented by these text token rates.
OpenRouter listing date, not necessarily the original model launch. Provider-route pricing and limits verified 2026-09-29; endpoint selection can change rates. Tool, audio, and other non-text charges are not represented by these text token rates.
OpenRouter listing date, not necessarily the original model launch. Provider-route pricing and limits verified 2026-09-29; endpoint selection can change rates. Tool, audio, and other non-text charges are not represented by these text token rates.
OpenRouter listing date, not necessarily the original model launch. Provider-route pricing and limits verified 2026-09-29; endpoint selection can change rates. Tool, audio, and other non-text charges are not represented by these text token rates.
Peak rates. Off-peak rates are 50% lower. Peak UTC hours: 01:00-04:00 and 06:00-10:00 on weekdays excluding Chinese public holidays. Native multimodal V4.1 Flash; use deepseek-flash as the API ID.
OpenRouter listing date, not necessarily the original model launch. Provider-route pricing and limits verified 2026-09-29; endpoint selection can change rates. Tool, audio, and other non-text charges are not represented by these text token rates.
OpenRouter listing date, not necessarily the original model launch. Provider-route pricing and limits verified 2026-09-29; endpoint selection can change rates. Tool, audio, and other non-text charges are not represented by these text token rates.
OpenRouter listing date, not necessarily the original model launch. Provider-route pricing and limits verified 2026-09-29; endpoint selection can change rates. Tool, audio, and other non-text charges are not represented by these text token rates.
OpenRouter listing date, not necessarily the original model launch. Provider-route pricing and limits verified 2026-09-29; endpoint selection can change rates. Tool, audio, and other non-text charges are not represented by these text token rates.
OpenRouter listing date, not necessarily the original model launch. Provider-route pricing and limits verified 2026-09-29; endpoint selection can change rates. Tool, audio, and other non-text charges are not represented by these text token rates.
OpenRouter listing date, not necessarily the original model launch. Provider-route pricing and limits verified 2026-09-29; endpoint selection can change rates. Tool, audio, and other non-text charges are not represented by these text token rates.
OpenRouter listing date, not necessarily the original model launch. Provider-route pricing and limits verified 2026-09-29; endpoint selection can change rates. Tool, audio, and other non-text charges are not represented by these text token rates.
OpenRouter listing date, not necessarily the original model launch. Provider-route pricing and limits verified 2026-09-29; endpoint selection can change rates. Tool, audio, and other non-text charges are not represented by these text token rates.
OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation; tool calling requires the Responses API
OpenRouter listing date, not necessarily the original model launch. Provider-route pricing and limits verified 2026-09-29; endpoint selection can change rates. Tool, audio, and other non-text charges are not represented by these text token rates.
Introductory standard token rates through 2026-12-31; input/output/cache-read rates double on 2027-01-01. Cache storage and grounding fees are separate. Minimal thinking is unsupported.
OpenRouter listing date, not necessarily the original model launch. Provider-route pricing and limits verified 2026-09-29; endpoint selection can change rates. Tool, audio, and other non-text charges are not represented by these text token rates.
OpenRouter listing date, not necessarily the original model launch. Provider-route pricing and limits verified 2026-09-29; endpoint selection can change rates. Tool, audio, and other non-text charges are not represented by these text token rates.
OpenRouter listing date, not necessarily the original model launch. Provider-route pricing and limits verified 2026-09-29; endpoint selection can change rates. Tool, audio, and other non-text charges are not represented by these text token rates.
Latest Claude Fable model for demanding reasoning and long-horizon agentic work with adaptive thinking always on
Retired checkpoint. Temporary compatibility alias served and billed as DeepSeek V4.1 Flash; migrate to deepseek-flash. Peak rates. Off-peak rates are 50% lower. Peak UTC hours: 01:00-04:00 and 06:00-10:00 on weekdays excluding Chinese public holidays. Native multimodal V4.1 Flash; use deepseek-flash as the API ID.
Fast DeepSeek model for efficient chat, coding help, and agent loops
Tencent Hy reasoning model for coding, instruction following, and agent tasks
Flagship GLM model for hybrid reasoning, coding, and agentic engineering
Qwen vision-language model for visual reasoning, documents, and agent tasks
High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning
Fast Gemini model balancing multimodal reasoning, tool use, and cost
High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning
Fast Gemini model balancing multimodal reasoning, tool use, and cost
Fast Gemini model balancing multimodal reasoning, tool use, and cost
DeepSeek V4 Pro is a DeepSeek model in the Deepseek V4 family built for chat, function calling, and reasoning. It is available through Everstack with up to 1M tokens of context.
DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes
Flagship DeepSeek model for coding, reasoning, and agentic work
DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes
DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes
xAI's frontier model for long-running agents, coding, knowledge work, and visual projects
Grok model for agentic tool use, reasoning, coding, and live assistance
Qwen instruction model for multilingual chat, reasoning, and tool use
Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows
Multimodal reasoning model for visual analysis, planning, and tool use
Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads
Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads
Nemotron model for efficient reasoning, coding, and specialized AI agents
Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.
Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.
Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.
Flagship model for demanding analysis, coding, and production agent workflows
Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.
2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows
2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows
Qwen vision-language model for visual reasoning, documents, and agent tasks
Pricing, context windows, and capabilities for every model in the catalog.
