23 models,one endpoint.

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...

Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...

DeepSeek R1 is here: Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass....

Doubao Seed 2.0 Mini is the lowest-cost production model currently exposed through the NextModel public gateway. It is a practical default for Chinese Q&A, classification, summarization, and lightweight multimodal tasks.

Qwen3 Coder Plus is Alibaba's proprietary version of the Open Source Qwen3 Coder 480B A35B. It is a powerful coding agent model specializing in autonomous programming via tool calling and...

DeepSeek V4 Pro is DeepSeek's flagship reasoning model, onboarded via the Volcengine Agent Plan for production-grade reasoning and coding workloads.

Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to provide responses with greater...

Qwen3-Max is an updated release built on the Qwen3 series, offering major improvements in reasoning, instruction following, multilingual support, and long-tail knowledge coverage compared to the January 2025 version. It...

Doubao Seed 2.0 Pro is Volcengine's flagship general-purpose model, onboarded through the Volcengine Agent Plan, sharing the same tiered pricing as the Code variant.

Doubao Seed 2.0 Code is Volcengine's coding-focused variant, onboarded through the Volcengine Agent Plan for agentic and long-context coding workloads.

GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...

Kimi K2.7 Code is Moonshot AI's coding-focused model, available only through the Volcengine Agent Plan (no public ARK price list); its listed price tracks the OpenRouter reference rate for the same model.

DeepSeek V4 Flash is a long-context low-cost candidate for teams that need Chinese capability and batch-friendly pricing.

DeepSeek V4 Flash is the low-cost, low-latency member of the DeepSeek V4 family, onboarded via the Volcengine Agent Plan.

Kimi K2.6 is a long-context Chinese model candidate for document-heavy teams comparing cost, context length, and domestic model coverage.

GLM-5.2 is Zhipu AI's flagship model, onboarded via the Volcengine Agent Plan alongside the Doubao family, giving a non-ByteDance model option on the same billing path.

Kimi K2.6 is Moonshot AI's general-purpose model, available only through the Volcengine Agent Plan (no public ARK price list); its listed price tracks the OpenRouter reference rate for the same model.

Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...

Doubao Seed 2.0 Lite is the low-cost long-context member of the Seed 2.0 family, onboarded through the Volcengine Agent Plan. Audio input pricing is not modeled in this catalog.

MiniMax M3 is available only through the Volcengine Agent Plan (no public ARK price list); its listed price tracks the OpenRouter reference rate for the same model.

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...

MiniMax M2.7 is available only through the Volcengine Agent Plan (no public ARK price list); its listed price tracks the OpenRouter reference rate for the same model. Unlike M3, this model has no cache-hit discount.