Text Models

Abliterated Large FlashNew$1.25 / $2.50 per 1M

Abliterated Large Flash is Abliteration AI’s unrestricted multimodal model, based on DeepSeek V4.1 Flash and further abliterated. It has 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window.

Abliterated Large V2$3.00 / $5.00 per 1M

Abliterated Large V2 is Abliteration AI’s unrestricted reasoning model, based on GLM-5.3 and further abliterated and fine-tuned. Text-only with 1M context, for harder reasoning and evaluation workloads.

Aion 3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models.

Aion 3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models.

Aion 3.5, the successor to Aion 3.0, is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models, with a longer context window.

Aion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models.

Claude Fable 5$10.00 / $50.00 per 1M

Claude Fable 5 is a model from Anthropic designed for demanding reasoning and long-horizon agentic work. It features a 1M token context window, 128K max output tokens, always-on adaptive thinking, and strong multimodal capabilities.

Claude Fable 5.1$10.00 / $50.00 per 1M

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 such as long code refactors, front-end development, and finance and analysis tasks.

Claude Fable 5.2New$8.00 / $40.00 per 1M

Claude Fable 5.2 improves on Claude Fable 5.1 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work such as long code refactors, front-end development, and finance and analysis tasks.

Claude Haiku 5.5$0.10 / $0.50 per 1M

Claude Haiku 5.5 is built for high-volume, latency-sensitive work such as classification, routing, extraction, and subagent tasks.

Claude Opus 4.5$5.00 / $25.00 per 1M

Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use.

Claude Opus 4.6$5.00 / $25.00 per 1M

Claude Opus 4.6 is a reasoning model from Anthropic, building on Opus 4.5 with enhanced performance across complex software engineering, agentic workflows, and long-horizon tasks.

Claude Opus 4.7$5.00 / $25.00 per 1M

Claude Opus 4.7 is a model from Anthropic for complex reasoning and agentic coding. It features a 1M token context window, 128K max output tokens, adaptive thinking, and strong multimodal capabilities.

Claude Opus 4.8$5.00 / $25.00 per 1M

Claude Opus 4.8 is the successor to Opus 4.7 in Anthropic’s Opus family. It supports long-horizon agentic work, complex multi-step coding, and memory-driven tasks where coherence over extended sessions matters.

Claude Opus 5$5.00 / $25.00 per 1M

Claude Opus 5, the successor to Opus 4.8, delivers major gains in agentic coding, professional knowledge work, and long-horizon reasoning, with a 1M token context window, 128K max output tokens, adaptive thinking, and strong multimodal…

Claude Opus 5.5$4.00 / $20.00 per 1M

Claude Opus 5.5 is a step-change improvement over Opus 5, with the biggest gains in agentic coding, long-running agentic tasks, and knowledge work.

Claude Sonnet 4.6$3.00 / $15.00 per 1M

Claude Sonnet 4.6 is Anthropic’s best combination of speed and intelligence, offering strong performance on coding, reasoning, and general tasks with excellent speed and cost efficiency.

Claude Sonnet 5$2.00 / $10.00 per 1M

Claude Sonnet 5 follows Sonnet 4.6, substantially improving on it in coding and agentic work and reaching near-Opus quality on many tasks.

Claude Sonnet 5.5$2.00 / $10.00 per 1M

Claude Sonnet 5.5 is a step-change improvement over Sonnet 5. It performs great with well-scoped everyday tasks like building features, fixing bugs, and creating polished documents, slides, and spreadsheets.

DeepSeek V3.2$0.33 / $0.48 per 1M

DeepSeek-V3.2 is an efficient large language model with DeepSeek Sparse Attention (DSA) for long contexts. It features strong reasoning and tool-use skills, achieving top results on the 2025 IMO and IOI.

DeepSeek V4 Flash 0423$0.138 / $0.275 per 1M

DeepSeek V4 Flash is an efficiency-optimized 284B-parameter Mixture-of-Experts model with 13B active parameters and a 1M-token context window.

DeepSeek V4 Flash 0731$0.13 / $0.26 per 1M

DeepSeek V4 Flash 0731 follows the 0423 release of DeepSeek V4 Flash, an efficiency-optimized 284B-parameter Mixture-of-Experts model with 13B active parameters and a 1M-token context window.

DeepSeek V4 Pro$1.65 / $3.30 per 1M

DeepSeek V4 Pro is a 1.6T-parameter Mixture-of-Experts model with 49B active parameters and a 1M-token context window.

DeepSeek V4 Pro 0813$1.65 / $4.95 per 1M

DeepSeek V4 Pro is a 1.6T-parameter Mixture-of-Experts model with 49B active parameters and a 1M-token context window.

DeepSeek V4.1 Flash$0.30 / $1.20 per 1M

DeepSeek V4.1 Flash is a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window.

DeepSeek v4.1 Flash (1017)New$0.30 / $1.20 per 1M

DeepSeek V4.1 Flash is a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window.

DeepSeek V4.1 Flash 1017 AbliteratedNew$0.375 / $1.50 per 1M

DeepSeek V4.1 Flash 1017 Abliterated running in a Trusted Execution Environment (TEE). A text-only reasoning and coding model with refusal behavior removed and a 1M-token context window.

DeepSeek V4.1 Flash 1017 UltrafastNew$3.00 / $12.00 per 1M

DeepSeek V4.1 Flash is a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window.

DeepSeek V4.1 Flash 1017 UncensoredNew$0.33 / $1.32 per 1M

DeepSeek V4.1 Flash 1017 Uncensored is an abliterated, uncensored variant of DeepSeek V4.1 Flash 1017, a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window.

DeepSeek V4.1 Flash UncensoredNew$0.33 / $1.32 per 1M

DeepSeek V4.1 Flash Uncensored is an abliterated, uncensored variant of DeepSeek V4.1 Flash, a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window.

Gemini 3 Flash Preview$0.70 / $3.75 per 1M

Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi-turn chat, and coding assistance. It delivers near Pro level reasoning with substantially lower latency.

Gemini 3.1 Pro Preview$2.50 / $15.00 per 1M

Gemini 3.1 Pro is an evolution of Google’s flagship frontier model with 1M context, advancing high-precision multimodal reasoning across text, image, and code.

Gemini 3.5 Flash$1.55 / $9.45 per 1M

Gemini 3.5 Flash is a high speed, high value thinking model with 1M context, designed for agentic workflows, multi-turn chat, and coding assistance. It delivers near Pro level reasoning with substantially lower latency.

Gemini 3.5 Flash-Lite$0.375 / $3.13 per 1M

Gemini 3.5 Flash-Lite is the fastest, most cost-efficient Gemini 3.5 model with 1M context, ideal for everyday questions, summarization, and lightweight coding tasks.

Gemini 3.6 Flash$0.9375 / $4.69 per 1M

Gemini 3.6 Flash, the successor to Gemini 3.5 Flash, is a high speed, high value thinking model with 1M context, designed for agentic workflows, multi-turn chat, and coding assistance.

Gemini 3.7 Flash$0.9375 / $4.69 per 1M

Gemini 3.7 Flash, the successor to Gemini 3.6 Flash, is built for complex coding, agentic workflows, and reliable multi-step execution, with 1M context and tunable thinking.

Gemini 3.8 Flash$0.9375 / $4.69 per 1M

Gemini 3.8 Flash, the successor to Gemini 3.7 Flash, is built for complex coding, agentic workflows, and reliable multi-step execution, with 1M context and tunable thinking.

Gemini 4 Argon$2.50 / $12.50 per 1M

Gemini 4 Argon is Google’s frontier model for complex workflows across software engineering, enterprise knowledge work, and cybersecurity defense, with a unified 1M token context window and tunable thinking.

Gemini 4 CarbonNew$2.50 / $12.50 per 1M

Gemini 4 Carbon is Google’s frontier model for long-horizon agentic work across software engineering, scientific reasoning, and cybersecurity defense, with a unified 1M token context window and deeper tunable thinking than Gemini 4 Argon.

Gemini 4 HydrogenNew$1.88 / $9.38 per 1M

Gemini 4 Hydrogen is Google’s fast, efficient model for coding and agentic work, with a unified 1M token context window and tunable thinking.

Gemma 4 26B A4B Uncensored$0.19 / $0.88 per 1M

Gemma 4 26B A4B Uncensored running in a Trusted Execution Environment (TEE).

Gemma 4 UncensoredDeprecated$0.1625 / $0.50 per 1M

Gemma 4 Uncensored is an uncensored variant of Google Gemma 4 26B, a Mixture-of-Experts model with 26B total parameters and only 4B active per token.

GLM-4.6 is a large language model developed by Z.ai, featuring strong reasoning capabilities and support for multiple languages. Supports a large context window for processing extensive text and detailed analysis.

GLM-4.7, the successor to GLM-4.6, is a large language model developed by Z.ai, featuring strong reasoning capabilities and support for multiple languages. Supports a large context window for processing extensive text and detailed analysis.

GLM-4.7-Flash-Heretic is an uncensored experimental variant of GLM-4.7-Flash, optimized for creative freedom and unfiltered dialogue with fast inference speed.

GLM-5, the successor to GLM-4.7, is a large language model developed by Z.ai, featuring significantly enhanced reasoning capabilities, improved instruction following, and support for multiple languages.

GLM-5 Turbo is a fast inference model from Z.ai tuned for strong performance in agent-driven environments and production coding workflows.

GLM-5.1, the successor to GLM-5, is a large language model developed by Z.ai, featuring significantly enhanced reasoning capabilities, improved instruction following, and support for multiple languages.

GLM-5.2, the successor to GLM-5.1, is a large language model developed by Z.ai, featuring significantly enhanced reasoning capabilities, improved instruction following, and support for multiple languages.

GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks.

GLM-5.3 Flash is a reasoning model designed for coding, sustained agentic work, and production workloads. It is suited for long-horizon software engineering, complex reasoning, and workflows that combine text with visual context.

GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks with image and text inputs.

Google Gemma 3 27B Instruct$0.12 / $0.20 per 1M

Gemma 3 introduces multimodality, supporting vision-language input and text outputs.

Google Gemma 4 26B A4B Instruct$0.13 / $0.40 per 1M

Gemma 4 26B A4B is a Mixture-of-Experts model from Google DeepMind with 26B total parameters and only 4B active per token, offering fast inference at high quality.

Google Gemma 4 31B Instruct$0.12 / $0.36 per 1M

Gemma 4 31B is a dense model from Google DeepMind with 31B parameters, delivering frontier-level reasoning performance. It handles text, image, and video input, supports 256K context, function calling, and configurable thinking modes.

OpenAI’s multimodal model with vision capabilities, strong reasoning, and broad knowledge. Popular for its balanced performance across tasks. Version: 2024-11-20.

OpenAI’s cost-efficient small model that delivers GPT-4 level intelligence at a fraction of the cost. Ideal for high-volume applications requiring strong reasoning. Version: 2024-07-18.

GPT-5.2 is a frontier-grade model in the GPT-5 series, offering stronger agentic and long context performance compared to GPT-5.1.

GPT-5.3 Codex, the successor to GPT-5.2 Codex, is OpenAI’s specialized coding model, optimized for advanced software development, code generation, and technical problem-solving.

GPT-5.4, the successor to GPT-5.2, is a frontier model in the GPT-5 series with a 1M+ context window, offering improved agentic and long context performance. It uses adaptive reasoning to dynamically allocate computation across tasks.