ChatUNCENSORED
Abliterated Large Flash
abliteration-abliterated-model-large-flashAbliterated 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. It natively processes images and text, with strong reasoning, coding, and agentic performance and no content-filtering guardrails.
- Context
- 1,000,000 tokens
Input$2.50 / 1M tokens
Output$5.00 / 1M tokens
Cache read$0.25 / 1M tokens
ChatUNCENSORED
Abliterated Large V2
abliteration-abliterated-model-large-v2Abliterated 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. Always reasons; depth can be set to low, high, or max.
- Context
- 1,000,000 tokens
Input$6.00 / 1M tokens
Output$10.00 / 1M tokens
Cache read$0.60 / 1M tokens
ChatUNCENSORED
Aion 3.0
aion-labs-aion-3-0Aion 3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. Multiple specialized models collaborate on each response to produce stronger narrative structure and more compelling tension and conflict. It handles mature and darker themes with nuance and supports tool calling for richer interactive fiction.
- Context
- 128,000 tokens
Input$7.50 / 1M tokens
Output$15.00 / 1M tokens
Cache read$1.875 / 1M tokens
ChatUNCENSORED
Aion 3.0 Mini
aion-labs-aion-3-0-miniAion 3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. Multiple specialized models collaborate on each response to produce stronger narrative structure and more compelling tension and conflict at lower cost. It handles mature and darker themes with nuance and supports tool calling for richer interactive fiction.
- Context
- 128,000 tokens
Input$1.75 / 1M tokens
Output$3.50 / 1M tokens
Cache read$0.45 / 1M tokens
ChatUNCENSORED
Aion 3.5
aion-labs-aion-3-5Aion 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. Multiple specialized models collaborate on each response to produce stronger narrative structure and more compelling tension and conflict. It handles mature and darker themes with nuance and supports tool calling for richer interactive fiction.
- Context
- 262,144 tokens
Input$7.50 / 1M tokens
Output$15.00 / 1M tokens
Cache read$1.875 / 1M tokens
ChatUNCENSORED
Aion 3.5 Mini
aion-labs-aion-3-5-miniAion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. Multiple specialized models collaborate on each response to produce stronger narrative structure and more compelling tension and conflict at lower cost. It handles mature and darker themes with nuance and supports tool calling for richer interactive fiction.
- Context
- 262,144 tokens
Input$1.75 / 1M tokens
Output$3.50 / 1M tokens
Cache read$0.45 / 1M tokens
Embeddings
BGE-EN-ICL
text-embedding-bge-en-iclBGE-EN-ICL is BAAI's English embedding model, which can take a few examples in the query to adapt to a task, an approach BAAI calls in-context learning. It returns 4,096-dimensional vectors for inputs of up to 8,192 tokens, for English retrieval and classification.
- Context
- 8,192 tokens
Input$0.025 / 1M tokens
Output$0.025 / 1M tokens
Embeddings
BGE-M3
text-embedding-bge-m3BGE-M3 is BAAI's open-weight multilingual embedding model, covering more than 100 languages. It turns inputs of up to 8,192 tokens into 1,024-dimensional vectors for semantic search, retrieval and clustering across languages.
- Context
- 8,192 tokens
Input$0.30 / 1M tokens
Output$1.20 / 1M tokens
Chat
Claude Fable 5
claude-fable-5Claude 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.
- Context
- 1,000,000 tokens
- Reasoning
- low / medium / high / xhigh / max
Input$20.00 / 1M tokens
Output$100.00 / 1M tokens
Cache read$2.00 / 1M tokens
All billing units (4)
Cache write$25.00 / 1M tokens
Chat
Claude Fable 5.1
claude-fable-5-1Claude 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. It features a 1M token context window, 128K max output tokens, always-on adaptive thinking, and strong multimodal capabilities, and tends to be more concise in its plans and summaries.
- Context
- 1,000,000 tokens
- Reasoning
- low / medium / high / xhigh / max
Input$20.00 / 1M tokens
Output$100.00 / 1M tokens
Cache read$0.50 / 1M tokens
All billing units (4)
Cache write$25.00 / 1M tokens
Chat
Claude Fable 5.2
claude-fable-5-2Claude 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. It features a 1M token context window, 128K max output tokens, always-on adaptive thinking, and strong multimodal capabilities, and tends to be more concise in its plans and summaries.
- Context
- 1,000,000 tokens
- Reasoning
- low / medium / high / xhigh / max
Input$16.00 / 1M tokens
Output$80.00 / 1M tokens
Cache read$0.40 / 1M tokens
All billing units (4)
Cache write$20.00 / 1M tokens
Chat
Claude Haiku 5.5
claude-haiku-5-5Claude Haiku 5.5 is built for high-volume, latency-sensitive work such as classification, routing, extraction, and subagent tasks. It features a 1M token context window, 128K max output tokens, adaptive thinking, and strong document and vision understanding.
- Context
- 1,000,000 tokens
- Reasoning
- none / low / medium / high / xhigh / max
Input$0.20 / 1M tokens
Output$1.00 / 1M tokens
Cache read$0.02 / 1M tokens
All billing units (8)
Cache write$0.25 / 1M tokens
Input · context > 100000 tokens$1.00 / 1M tokens
Output · context > 100000 tokens$5.00 / 1M tokens
Cache read · context > 100000 tokens$0.10 / 1M tokens
Cache write · context > 100000 tokens$1.25 / 1M tokens
Chat
Claude Opus 4.5
claude-opus-4-5Claude Opus 4.5 is Anthropic's frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and reasoning benchmarks, and improved robustness to prompt injection.
- Context
- 198,000 tokens
Input$10.00 / 1M tokens
Output$50.00 / 1M tokens
Cache read$1.00 / 1M tokens
All billing units (4)
Cache write$12.50 / 1M tokens
Chat
Claude Opus 4.6
claude-opus-4-6Claude 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. It features a 1M token context window, improved multimodal capabilities, and stronger robustness to prompt injection.
- Context
- 1,000,000 tokens
- Reasoning
- low / medium / high / max
Input$10.00 / 1M tokens
Output$50.00 / 1M tokens
Cache read$1.00 / 1M tokens
All billing units (4)
Cache write$12.50 / 1M tokens
Chat
Claude Opus 4.7
claude-opus-4-7Claude 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.
- Context
- 1,000,000 tokens
- Reasoning
- low / medium / high / xhigh / max
Input$10.00 / 1M tokens
Output$50.00 / 1M tokens
Cache read$1.00 / 1M tokens
All billing units (4)
Cache write$12.50 / 1M tokens
Chat
Claude Opus 4.8
claude-opus-4-8Claude 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. It features a 1M token context window, 128K max output tokens, adaptive thinking, and strong multimodal capabilities.
- Context
- 1,000,000 tokens
- Reasoning
- low / medium / high / xhigh / max
Input$10.00 / 1M tokens
Output$50.00 / 1M tokens
Cache read$1.00 / 1M tokens
All billing units (4)
Cache write$12.50 / 1M tokens
Chat
Claude Opus 4.8 Fast
claude-opus-4-8-fastClaude Opus 4.8 (Fast) is a speed-optimized variant of Claude Opus 4.8, offering the same 1M token context window and strong performance across long-horizon agentic work and complex coding — with lower latency.
- Context
- 1,000,000 tokens
- Reasoning
- low / medium / high / xhigh / max
Input$20.00 / 1M tokens
Output$100.00 / 1M tokens
Cache read$2.00 / 1M tokens
All billing units (4)
Cache write$25.00 / 1M tokens
Chat
Claude Opus 5
claude-opus-5Claude 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 capabilities.
- Context
- 1,000,000 tokens
- Reasoning
- low / medium / high / xhigh / max
Input$10.00 / 1M tokens
Output$50.00 / 1M tokens
Cache read$1.00 / 1M tokens
All billing units (4)
Cache write$12.50 / 1M tokens
Chat
Claude Opus 5 Fast
claude-opus-5-fastClaude Opus 5 (Fast) is a speed-optimized variant of Claude Opus 5, offering the same 1M token context window and strong performance across agentic coding, professional knowledge work, and long-horizon reasoning — with lower latency.
- Context
- 1,000,000 tokens
- Reasoning
- low / medium / high / xhigh / max
Input$20.00 / 1M tokens
Output$100.00 / 1M tokens
Cache read$2.00 / 1M tokens
All billing units (4)
Cache write$25.00 / 1M tokens
Chat
Claude Opus 5.5
claude-opus-5-5Claude 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. It is also a much better collaborator on long-running work, with a 1M token context window, 128K max output tokens, adaptive thinking, and strong multimodal capabilities.
- Context
- 1,000,000 tokens
- Reasoning
- low / medium / high / xhigh / max
Input$8.00 / 1M tokens
Output$40.00 / 1M tokens
Cache read$0.40 / 1M tokens
All billing units (4)
Cache write$10.00 / 1M tokens
Chat
Claude Opus 5.5 Fast
claude-opus-5-5-fastClaude Opus 5.5 Fast serves the same Opus 5.5 model with faster output generation, a 1M token context window, up to 128K output tokens, adaptive thinking, vision, and tool calling.
- Context
- 1,000,000 tokens
- Reasoning
- low / medium / high / xhigh / max
Input$16.00 / 1M tokens
Output$80.00 / 1M tokens
Cache read$0.80 / 1M tokens
All billing units (4)
Cache write$20.00 / 1M tokens
Chat
Claude Sonnet 4.6
claude-sonnet-4-6Claude 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. It features a 1M token context window and 64K max output tokens.
- Context
- 1,000,000 tokens
- Reasoning
- low / medium / high / max
Input$6.00 / 1M tokens
Output$30.00 / 1M tokens
Cache read$0.60 / 1M tokens
All billing units (4)
Cache write$7.50 / 1M tokens
Chat
Claude Sonnet 5
claude-sonnet-5Claude Sonnet 5 follows Sonnet 4.6, substantially improving on it in coding and agentic work and reaching near-Opus quality on many tasks. It features a 1M token context window, adaptive thinking, and strong document and vision understanding.
- Context
- 1,000,000 tokens
- Reasoning
- low / medium / high / xhigh / max
Input$4.00 / 1M tokens
Output$20.00 / 1M tokens
Cache read$0.40 / 1M tokens
All billing units (4)
Cache write$5.00 / 1M tokens
Chat
Claude Sonnet 5.5
claude-sonnet-5-5Claude 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. Sonnet 5.5 also improves on communication and writes more clearly than Sonnet 5. It features a 1M token context window, 128K max output tokens, adaptive thinking, and strong document and vision understanding.
- Context
- 1,000,000 tokens
- Reasoning
- low / medium / high / xhigh / max
Input$4.00 / 1M tokens
Output$20.00 / 1M tokens
Cache read$0.20 / 1M tokens
All billing units (4)
Cache write$5.00 / 1M tokens
Classification
Clef (System One)
clef-apiClef (System One) is Cloudflare's decision model. Like Jev, it answers typed questions about a passage with structured judgments rather than prose: probabilities, choices or rubric scores. It reads up to 32,768 tokens of context.
- Context
- 32,768 tokens
Input$0.10 / 1M tokens
Output$0.10 / 1M tokens
Chat
DeepSeek V3.2
deepseek-v3.2DeepSeek-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.
- Context
- 160,000 tokens
- Reasoning
- none / low / medium / high
Input$0.66 / 1M tokens
Output$0.96 / 1M tokens
Cache read$0.32 / 1M tokens
Chat
DeepSeek V4 Flash
e2ee-deepseek-v4-flashDeepSeek V4 Flash running in a Trusted Execution Environment (TEE). Hardware attestation evidence is available for independent verification of enclave identity and configuration.
- Context
- 1,000,000 tokens
Input$0.364 / 1M tokens
Output$0.746 / 1M tokens
Cache read$0.076 / 1M tokens
Chat
DeepSeek V4 Flash 0423
deepseek-v4-flashDeepSeek V4 Flash is an efficiency-optimized 284B-parameter Mixture-of-Experts model with 13B active parameters and a 1M-token context window. Tuned for fast inference and high-throughput workloads while maintaining strong reasoning and coding performance.
- Context
- 1,000,000 tokens
- Reasoning
- none / low / medium / high
Input$0.276 / 1M tokens
Output$0.55 / 1M tokens
Cache read$0.056 / 1M tokens
Chat
DeepSeek V4 Flash 0731
deepseek-v4-flash-0731DeepSeek 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. Tuned for fast inference and high-throughput workloads while maintaining strong reasoning and coding performance.
- Context
- 1,000,000 tokens
- Reasoning
- none / low / high / max
Input$0.26 / 1M tokens
Output$0.52 / 1M tokens
Cache read$0.056 / 1M tokens
Chat
DeepSeek V4 Flash 0731 Fast
deepseek-v4-flash-0731-fastDeepSeek 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. Tuned for fast inference and high-throughput workloads while maintaining strong reasoning and coding performance.
- Context
- 1,000,000 tokens
- Reasoning
- none / low / high / max
Input$0.70 / 1M tokens
Output$1.40 / 1M tokens
Cache read$0.175 / 1M tokens
Chat
DeepSeek V4 Pro
deepseek-v4-proDeepSeek V4 Pro is a 1.6T-parameter Mixture-of-Experts model with 49B active parameters and a 1M-token context window. Built for advanced reasoning, coding, and long-horizon agentic workflows with a hybrid attention system for efficient long-context processing.
- Context
- 1,000,000 tokens
- Reasoning
- none / low / medium / high
Input$3.30 / 1M tokens
Output$6.602 / 1M tokens
Cache read$0.66 / 1M tokens
Chat
DeepSeek V4 Pro 0813
deepseek-v4-pro-0813DeepSeek V4 Pro is a 1.6T-parameter Mixture-of-Experts model with 49B active parameters and a 1M-token context window. Built for advanced reasoning, coding, and long-horizon agentic workflows with a hybrid attention system for efficient long-context processing.
- Context
- 1,000,000 tokens
- Reasoning
- none / low / high / max
Input$3.30 / 1M tokens
Output$9.90 / 1M tokens
Cache read$0.33 / 1M tokens
Chat
DeepSeek V4.1 Flash
deepseek-v4-1-flashDeepSeek 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. It natively processes images and text, with strong reasoning, coding, and agentic performance.
- Context
- 1,000,000 tokens
- Reasoning
- none / low / high / max
Input$0.60 / 1M tokens
Output$2.40 / 1M tokens
Cache read$0.015 / 1M tokens
Chat
DeepSeek v4.1 Flash (1017)
deepseek-v4-1-flash-1017DeepSeek 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. It natively processes images and text, with strong reasoning, coding, and agentic performance.
- Context
- 1,000,000 tokens
- Reasoning
- none / low / high / max
Input$0.60 / 1M tokens
Output$2.40 / 1M tokens
Cache read$0.015 / 1M tokens
ChatUNCENSORED
DeepSeek V4.1 Flash 1017 Abliterated
e2ee-deepseek-v4-1-flash-1017-abliteratedDeepSeek 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. Hardware attestation evidence is available for independent verification of enclave identity and configuration.
- Context
- 1,000,000 tokens
Input$0.75 / 1M tokens
Output$3.00 / 1M tokens
Cache read$0.015 / 1M tokens
Chat
DeepSeek V4.1 Flash 1017 Ultrafast
deepseek-v4-1-flash-1017-ultrafastDeepSeek 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. It natively processes images and text, with strong reasoning, coding, and agentic performance.
- Context
- 1,000,000 tokens
- Reasoning
- none / low / high / max
Input$6.00 / 1M tokens
Output$24.00 / 1M tokens
Cache read$0.12 / 1M tokens
ChatUNCENSORED
DeepSeek V4.1 Flash 1017 Uncensored
deepseek-v4-1-flash-1017-uncensoredDeepSeek 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. It natively processes images and text, with strong reasoning, coding, and agentic performance and no content-filtering guardrails.
- Context
- 1,000,000 tokens
- Reasoning
- none / low / high / max
Input$0.66 / 1M tokens
Output$2.64 / 1M tokens
Cache read$0.0165 / 1M tokens
ChatUNCENSORED
DeepSeek V4.1 Flash Uncensored
deepseek-v4-1-flash-uncensoredDeepSeek 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. It natively processes images and text, with strong reasoning, coding, and agentic performance and no content-filtering guardrails.
- Context
- 1,000,000 tokens
- Reasoning
- none / low / high / max
Input$0.66 / 1M tokens
Output$2.64 / 1M tokens
Cache read$0.0165 / 1M tokens
Chat
Gemini 3 Flash Preview
gemini-3-flash-previewGemini 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.
- Context
- 256,000 tokens
- Reasoning
- none / low / medium / high
Input$1.40 / 1M tokens
Output$7.50 / 1M tokens
Cache read$0.14 / 1M tokens
Chat
Gemini 3.1 Pro Preview
gemini-3-1-pro-previewGemini 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.
- Context
- 1,000,000 tokens
- Reasoning
- low / medium / high
Input$5.00 / 1M tokens
Output$30.00 / 1M tokens
Cache read$1.00 / 1M tokens
All billing units (8)
Cache write$1.00 / 1M tokens
Input · context > 200000 tokens$10.00 / 1M tokens
Output · context > 200000 tokens$45.00 / 1M tokens
Cache read · context > 200000 tokens$1.00 / 1M tokens
Cache write · context > 200000 tokens$1.00 / 1M tokens
Chat
Gemini 3.5 Flash
gemini-3-5-flashGemini 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.
- Context
- 1,000,000 tokens
- Reasoning
- low / medium / high
Input$3.10 / 1M tokens
Output$18.90 / 1M tokens
Cache read$0.31 / 1M tokens
All billing units (4)
Cache write$0.172 / 1M tokens
Chat
Gemini 3.5 Flash-Lite
gemini-3-5-flash-liteGemini 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.
- Context
- 1,000,000 tokens
Input$0.75 / 1M tokens
Output$6.25 / 1M tokens
Cache read$0.075 / 1M tokens
Chat
Gemini 3.6 Flash
gemini-3-6-flashGemini 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. It delivers near Pro level reasoning with substantially lower latency.
- Context
- 1,000,000 tokens
Input$1.875 / 1M tokens
Output$9.375 / 1M tokens
Cache read$0.1875 / 1M tokens
Chat
Gemini 3.7 Flash
gemini-3-7-flashGemini 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.
- Context
- 1,000,000 tokens
Input$1.875 / 1M tokens
Output$9.375 / 1M tokens
Cache read$0.1875 / 1M tokens
Chat
Gemini 3.8 Flash
gemini-3-8-flashGemini 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.
- Context
- 1,000,000 tokens
Input$1.875 / 1M tokens
Output$9.375 / 1M tokens
Cache read$0.1875 / 1M tokens
Chat
Gemini 4 Argon
gemini-4-argonGemini 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.
- Context
- 1,000,000 tokens
Input$5.00 / 1M tokens
Output$25.00 / 1M tokens
Cache read$0.25 / 1M tokens
Embeddings
Gemini Embedding 2 Preview
gemini-embedding-2-previewGemini Embedding 2 Preview is a preview of Google's Gemini-based embedding model, returning 3,072-dimensional vectors for inputs of up to 2,048 tokens. It's built for semantic search, retrieval and classification.
- Context
- 2,048 tokens
Input$0.50 / 1M tokens
Output$0.50 / 1M tokens
ChatUNCENSORED
Gemma 4 26B A4B Uncensored
e2ee-gemma-4-26b-a4b-uncensored-pGemma 4 26B A4B Uncensored running in a Trusted Execution Environment (TEE). An uncensored variant of Google's Gemma 4 MoE model with 25.2B total / 3.8B active parameters, with hardware attestation evidence available for independent verification.
- Context
- 64,000 tokens
Input$0.38 / 1M tokens
Output$1.76 / 1M tokens
ChatUNCENSORED
Gemma 4 Uncensored
gemma-4-uncensoredGemma 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. Fine-tuned for uncensored chat without content filtering, it supports 256K context, coding, and general-purpose conversation.
- Context
- 256,000 tokens
Input$0.325 / 1M tokens
Output$1.00 / 1M tokens
Chat
GLM 4.6
zai-org-glm-4.6GLM-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.
- Context
- 198,000 tokens
- Reasoning
- low / medium / high
Input$0.86 / 1M tokens
Output$3.50 / 1M tokens
Cache read$0.16 / 1M tokens
Chat
GLM 4.7
zai-org-glm-4.7GLM-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.
- Context
- 198,000 tokens
- Reasoning
- low / medium / high
Input$1.10 / 1M tokens
Output$5.30 / 1M tokens
Cache read$0.22 / 1M tokens
ChatUNCENSORED
GLM 4.7 Flash Heretic
olafangensan-glm-4.7-flash-hereticGLM-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.
- Context
- 200,000 tokens
- Reasoning
- none / low / medium / high
Input$0.14 / 1M tokens
Output$0.80 / 1M tokens
Cache read$0.07 / 1M tokens
Chat
GLM 5
zai-org-glm-5GLM-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. Supports large context windows for processing extensive text and detailed analysis.
- Context
- 198,000 tokens
- Reasoning
- none / low / medium / high
Input$2.00 / 1M tokens
Output$6.40 / 1M tokens
Cache read$0.40 / 1M tokens
Chat
GLM 5 Turbo
z-ai-glm-5-turboGLM-5 Turbo is a fast inference model from Z.ai tuned for strong performance in agent-driven environments and production coding workflows.
- Context
- 200,000 tokens
- Reasoning
- none / low / medium / high
Input$2.40 / 1M tokens
Output$8.00 / 1M tokens
Cache read$0.48 / 1M tokens
Chat
GLM 5.1
zai-org-glm-5-1GLM-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. Supports large context windows for processing extensive text and detailed analysis with fast inference speed.
- Context
- 200,000 tokens
- Reasoning
- none / low / medium / high
Input$3.08 / 1M tokens
Output$9.68 / 1M tokens
Cache read$0.572 / 1M tokens
Chat
GLM 5.2
e2ee-glm-5-2-pGLM 5.2 running in a Trusted Execution Environment (TEE). A Z.AI model for long-horizon tasks with enhanced reasoning and project-level engineering context, with hardware attestation evidence available for independent verification.
- Context
- 524,288 tokens
- Reasoning
- none / low / medium / high
Input$3.50 / 1M tokens
Output$11.50 / 1M tokens
Cache read$0.60 / 1M tokens
Chat
GLM 5.2
zai-org-glm-5-2GLM-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. Supports a longer context window than GLM-5.1 for processing extensive text and detailed analysis with fast inference speed.
- Context
- 1,000,000 tokens
- Reasoning
- none / high / max
Input$2.80 / 1M tokens
Output$8.80 / 1M tokens
Cache read$0.52 / 1M tokens
Chat
GLM 5.3
e2ee-glm-5-3-pGLM 5.3 running in a Trusted Execution Environment (TEE). Z.ai's flagship model with 1M context. Hardware attestation evidence is available for independent verification of enclave identity and configuration.
- Context
- 1,000,000 tokens
- Reasoning
- none / low / medium / high
Input$3.50 / 1M tokens
Output$11.00 / 1M tokens
Cache read$0.65 / 1M tokens
Chat
GLM 5.3
z-ai-glm-5-3GLM-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.
- Context
- 1,000,000 tokens
Input$3.50 / 1M tokens
Output$11.00 / 1M tokens
Cache read$0.65 / 1M tokens
Chat
GLM 5.3 Flash
e2ee-glm-5-3-flashGLM 5.3 Flash running in a Trusted Execution Environment (TEE). A fast, low-cost multimodal model with 1M context. Hardware attestation evidence is available for independent verification of enclave identity and configuration.
- Context
- 1,000,000 tokens
Input$0.32 / 1M tokens
Output$1.08 / 1M tokens
Cache read$0.076 / 1M tokens
Chat
GLM 5.3 Flash
z-ai-glm-5-3-flashGLM-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.
- Context
- 1,048,576 tokens
Input$0.30 / 1M tokens
Output$1.00 / 1M tokens
Cache read$0.06 / 1M tokens
Chat
GLM 5V Turbo
z-ai-glm-5v-turboGLM-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.
- Context
- 200,000 tokens
- Reasoning
- none / low / medium / high
Input$3.00 / 1M tokens
Output$10.00 / 1M tokens
Cache read$0.60 / 1M tokens
Chat
Google Gemma 3 27B Instruct
google-gemma-3-27b-itGemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 27B is Google's open source model, successor to Gemma 2.
- Context
- 198,000 tokens
Input$0.24 / 1M tokens
Output$0.40 / 1M tokens
Chat
Google Gemma 4 26B A4B Instruct
google-gemma-4-26b-a4b-itGemma 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. It handles text, image, and video input, supports 256K context, function calling, and reasoning with configurable thinking modes.
- Context
- 256,000 tokens
- Reasoning
- none / low / medium / high
Input$0.26 / 1M tokens
Output$0.80 / 1M tokens
Cache read$0.10 / 1M tokens
Chat
Google Gemma 4 31B Instruct
google-gemma-4-31b-itGemma 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.
- Context
- 256,000 tokens
- Reasoning
- none / low / medium / high
Input$0.24 / 1M tokens
Output$0.72 / 1M tokens
Cache read$0.18 / 1M tokens
Chat
GPT OSS 120B
e2ee-gpt-oss-120b-pGPT OSS 120B running in a Trusted Execution Environment (TEE). OpenAI's open-weight 117B-parameter MoE model with configurable reasoning depth and native tool use, with hardware attestation evidence available for independent verification.
- Context
- 128,000 tokens
- Reasoning
- low / medium / high
Input$0.26 / 1M tokens
Output$1.30 / 1M tokens
Chat
GPT-4o
openai-gpt-4o-2024-11-20OpenAI's multimodal model with vision capabilities, strong reasoning, and broad knowledge. Popular for its balanced performance across tasks. Version: 2024-11-20.
- Context
- 128,000 tokens
Input$5.00 / 1M tokens
Output$20.00 / 1M tokens
Cache read$2.50 / 1M tokens
Chat
GPT-4o Mini
openai-gpt-4o-mini-2024-07-18OpenAI'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.
- Context
- 128,000 tokens
Input$0.30 / 1M tokens
Output$1.20 / 1M tokens
Cache read$0.15 / 1M tokens
Chat
GPT-5.2
openai-gpt-52GPT-5.2 is a frontier-grade model in the GPT-5 series, offering stronger agentic and long context performance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly to simple queries while spending more depth on complex tasks.
- Context
- 256,000 tokens
- Reasoning
- none / low / medium / high / xhigh
Input$3.50 / 1M tokens
Output$28.00 / 1M tokens
Cache read$0.35 / 1M tokens
Chat
GPT-5.3 Codex
openai-gpt-53-codexGPT-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. It supports a longer context window and longer outputs than GPT-5.2 Codex.
- Context
- 400,000 tokens
- Reasoning
- none / low / medium / high / xhigh
Input$3.50 / 1M tokens
Output$28.00 / 1M tokens
Cache read$0.35 / 1M tokens
Chat
GPT-5.4
openai-gpt-54GPT-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.
- Context
- 1,000,000 tokens
- Reasoning
- none / low / medium / high / xhigh
Input$5.00 / 1M tokens
Output$30.00 / 1M tokens
Cache read$0.50 / 1M tokens
All billing units (6)
Input · context > 272000 tokens$10.00 / 1M tokens
Output · context > 272000 tokens$45.00 / 1M tokens
Cache read · context > 272000 tokens$1.00 / 1M tokens
Chat
GPT-5.4 Mini
openai-gpt-54-miniGPT-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.
- Context
- 400,000 tokens
- Reasoning
- none / low / medium / high / xhigh
Input$1.50 / 1M tokens
Output$9.00 / 1M tokens
Cache read$0.15 / 1M tokens
Chat
GPT-5.4 Pro
openai-gpt-54-proGPT-5.4 Pro builds on GPT-5.4's unified architecture with enhanced reasoning for complex, high-stakes tasks. It provides a 1M+ token context window (922K input, 128K output) and supports text and image inputs.
- Context
- 1,000,000 tokens
- Reasoning
- none / medium / high / xhigh
Input$60.00 / 1M tokens
Output$360.00 / 1M tokens
Input · context > 272000 tokens$120.00 / 1M tokens
All billing units (4)
Output · context > 272000 tokens$540.00 / 1M tokens
Chat
GPT-5.5
openai-gpt-55GPT-5.5, the successor to GPT-5.4, 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.
- Context
- 1,000,000 tokens
- Reasoning
- none / low / medium / high / xhigh
Input$10.00 / 1M tokens
Output$60.00 / 1M tokens
Cache read$1.00 / 1M tokens
All billing units (6)
Input · context > 272000 tokens$20.00 / 1M tokens
Output · context > 272000 tokens$90.00 / 1M tokens
Cache read · context > 272000 tokens$2.00 / 1M tokens
Chat
GPT-5.5 Pro
openai-gpt-55-proGPT-5.5 Pro, the successor to GPT-5.4 Pro, builds on GPT-5.5's unified architecture with enhanced reasoning for complex, high-stakes tasks. It provides a 1M+ token context window (922K input, 128K output) and supports text and image inputs.
- Context
- 1,000,000 tokens
- Reasoning
- medium / high / xhigh
Input$60.00 / 1M tokens
Output$360.00 / 1M tokens
Input · context > 272000 tokens$120.00 / 1M tokens
All billing units (4)
Output · context > 272000 tokens$540.00 / 1M tokens
Chat
GPT-5.6 Luna
openai-gpt-56-lunaGPT-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.
- Context
- 1,000,000 tokens
- Reasoning
- none / low / medium / high / xhigh / max
Input$0.40 / 1M tokens
Output$2.40 / 1M tokens
Cache read$0.04 / 1M tokens
All billing units (8)
Cache write$0.50 / 1M tokens
Input · context > 272000 tokens$0.80 / 1M tokens
Output · context > 272000 tokens$3.60 / 1M tokens
Cache read · context > 272000 tokens$0.08 / 1M tokens
Cache write · context > 272000 tokens$1.00 / 1M tokens
Chat
GPT-5.6 Luna Pro
openai-gpt-56-luna-proGPT-5.6 Luna Pro is the same underlying model as GPT-5.6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks.
- Context
- 1,000,000 tokens
- Reasoning
- low / medium / high / xhigh / max
Input$0.40 / 1M tokens
Output$2.40 / 1M tokens
Cache read$0.04 / 1M tokens
All billing units (8)
Cache write$0.50 / 1M tokens
Input · context > 272000 tokens$0.80 / 1M tokens
Output · context > 272000 tokens$3.60 / 1M tokens
Cache read · context > 272000 tokens$0.08 / 1M tokens
Cache write · context > 272000 tokens$1.00 / 1M tokens
Chat
GPT-5.6 Sol
openai-gpt-56-solGPT-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.
- Context
- 1,000,000 tokens
- Reasoning
- none / low / medium / high / xhigh / max
Input$8.00 / 1M tokens
Output$40.00 / 1M tokens
Cache read$0.80 / 1M tokens
All billing units (8)
Cache write$10.00 / 1M tokens
Input · context > 272000 tokens$16.00 / 1M tokens
Output · context > 272000 tokens$60.00 / 1M tokens
Cache read · context > 272000 tokens$1.60 / 1M tokens
Cache write · context > 272000 tokens$20.00 / 1M tokens
Chat
GPT-5.6 Sol Pro
openai-gpt-56-sol-proGPT-5.6 Sol Pro is the same underlying model as GPT-5.6 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks.
- Context
- 1,000,000 tokens
- Reasoning
- none / low / medium / high / xhigh / max
Input$8.00 / 1M tokens
Output$40.00 / 1M tokens
Cache read$0.80 / 1M tokens
All billing units (8)
Cache write$10.00 / 1M tokens
Input · context > 272000 tokens$16.00 / 1M tokens
Output · context > 272000 tokens$60.00 / 1M tokens
Cache read · context > 272000 tokens$1.60 / 1M tokens
Cache write · context > 272000 tokens$20.00 / 1M tokens
Chat
GPT-5.6 Terra
openai-gpt-56-terraGPT-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.
- Context
- 1,000,000 tokens
- Reasoning
- none / low / medium / high / xhigh / max
Input$4.00 / 1M tokens
Output$24.00 / 1M tokens
Cache read$0.40 / 1M tokens
All billing units (8)
Cache write$5.00 / 1M tokens
Input · context > 272000 tokens$8.00 / 1M tokens
Output · context > 272000 tokens$36.00 / 1M tokens
Cache read · context > 272000 tokens$0.80 / 1M tokens
Cache write · context > 272000 tokens$10.00 / 1M tokens
Chat
GPT-5.6 Terra Pro
openai-gpt-56-terra-proGPT-5.6 Terra Pro is the same underlying model as GPT-5.6 Terra, served with reasoning.mode set to pro for higher-quality responses on complex tasks.
- Context
- 1,000,000 tokens
- Reasoning
- low / medium / high / xhigh / max
Input$4.00 / 1M tokens
Output$24.00 / 1M tokens
Cache read$0.40 / 1M tokens
All billing units (8)
Cache write$5.00 / 1M tokens
Input · context > 272000 tokens$8.00 / 1M tokens
Output · context > 272000 tokens$36.00 / 1M tokens
Cache read · context > 272000 tokens$0.80 / 1M tokens
Cache write · context > 272000 tokens$10.00 / 1M tokens
Chat
GPT-6 Astra
openai-gpt-6-astraGPT-6 Astra is OpenAI's most capable model, built for the hardest end-to-end work. It is suited for complex reasoning, coding, computer use, research, and document creation, with a 1.05M token context window (922K input, 128K output) and support for text and image inputs.
- Context
- 1,050,000 tokens
- Reasoning
- low / medium / high / xhigh / max
Input$20.00 / 1M tokens
Output$100.00 / 1M tokens
Cache read$2.00 / 1M tokens
All billing units (8)
Cache write$25.00 / 1M tokens
Input · context > 272000 tokens$40.00 / 1M tokens
Output · context > 272000 tokens$150.00 / 1M tokens
Cache read · context > 272000 tokens$4.00 / 1M tokens
Cache write · context > 272000 tokens$50.00 / 1M tokens
Chat
GPT-6 Astra Pro
openai-gpt-6-astra-proGPT-6 Astra with pro reasoning mode for difficult tasks that benefit from more model work. Supports text and image inputs with a 1.05M token context window. Pro mode can use more tokens and take longer than standard Astra.
- Context
- 1,050,000 tokens
- Reasoning
- low / medium / high / xhigh / max
Input$20.00 / 1M tokens
Output$100.00 / 1M tokens
Cache read$2.00 / 1M tokens
All billing units (8)
Cache write$25.00 / 1M tokens
Input · context > 272000 tokens$40.00 / 1M tokens
Output · context > 272000 tokens$150.00 / 1M tokens
Cache read · context > 272000 tokens$4.00 / 1M tokens
Cache write · context > 272000 tokens$50.00 / 1M tokens
Chat
GPT-6 Luna
openai-gpt-6-lunaGPT-6 Luna is OpenAI's most efficient GPT-6 model for focused, high-volume tasks. It is suited for chat, classification, and lightweight agentic workflows, with a 1.05M token context window (922K input, 128K output), text and image inputs, and capable reasoning for its price tier.
- Context
- 1,050,000 tokens
- Reasoning
- none / low / medium / high / xhigh / max
Input$0.20 / 1M tokens
Output$1.00 / 1M tokens
Cache read$0.02 / 1M tokens
All billing units (8)
Cache write$0.25 / 1M tokens
Input · context > 272000 tokens$0.40 / 1M tokens
Output · context > 272000 tokens$1.50 / 1M tokens
Cache read · context > 272000 tokens$0.04 / 1M tokens
Cache write · context > 272000 tokens$0.50 / 1M tokens
Chat
GPT-6 Sol
openai-gpt-6-solGPT-6 Sol is built for complex coding and agentic workflows. It is OpenAI's GPT-6 coding and agent model, with a 1.05M token context window (922K input, 128K output), support for text and image inputs, and reasoning effort from none through max.
- Context
- 1,050,000 tokens
- Reasoning
- none / low / medium / high / xhigh / max
Input$4.00 / 1M tokens
Output$20.00 / 1M tokens
Cache read$0.40 / 1M tokens
All billing units (8)
Cache write$5.00 / 1M tokens
Input · context > 272000 tokens$8.00 / 1M tokens
Output · context > 272000 tokens$30.00 / 1M tokens
Cache read · context > 272000 tokens$0.80 / 1M tokens
Cache write · context > 272000 tokens$10.00 / 1M tokens
Chat
GPT-6.1 Sol
openai-gpt-61-solGPT-6.1 Sol delivers near-Astra performance at a lower cost for complex coding, computer use, and professional work. It has a 1.05M token context window (922K input, 128K output), support for text and image inputs, and reasoning effort from low through max.
- Context
- 1,050,000 tokens
- Reasoning
- low / medium / high / xhigh / max
Input$4.00 / 1M tokens
Output$20.00 / 1M tokens
Cache read$0.20 / 1M tokens
All billing units (8)
Cache write$5.00 / 1M tokens
Input · context > 272000 tokens$8.00 / 1M tokens
Output · context > 272000 tokens$30.00 / 1M tokens
Cache read · context > 272000 tokens$0.40 / 1M tokens
Cache write · context > 272000 tokens$10.00 / 1M tokens
Chat
GPT-6.1 Sol Ultrafast
openai-gpt-61-sol-ultrafastGPT-6.1 Sol Ultrafast is the same model served in OpenAI's Ultrafast mode, up to 8x faster. It has a 1.05M token context window (922K input, 128K output), support for text and image inputs, and reasoning effort from low through max.
- Context
- 1,050,000 tokens
- Reasoning
- low / medium / high / xhigh / max
Input$24.00 / 1M tokens
Output$120.00 / 1M tokens
Cache read$1.20 / 1M tokens
All billing units (8)
Cache write$30.00 / 1M tokens
Input · context > 272000 tokens$48.00 / 1M tokens
Output · context > 272000 tokens$180.00 / 1M tokens
Cache read · context > 272000 tokens$2.40 / 1M tokens
Cache write · context > 272000 tokens$60.00 / 1M tokens
Chat
GPT-6.1 Terra
openai-gpt-61-terraGPT-6.1 Terra is a fast, efficient model for visual reasoning, precise computer use, and clear, natural writing. It has a 1.05M token context window (922K input, 128K output), support for text and image inputs, and reasoning effort from none through max.
- Context
- 1,050,000 tokens
- Reasoning
- none / low / medium / high / xhigh / max
Input$2.00 / 1M tokens
Output$10.00 / 1M tokens
Cache read$0.10 / 1M tokens
All billing units (8)
Cache write$2.50 / 1M tokens
Input · context > 272000 tokens$4.00 / 1M tokens
Output · context > 272000 tokens$15.00 / 1M tokens
Cache read · context > 272000 tokens$0.20 / 1M tokens
Cache write · context > 272000 tokens$5.00 / 1M tokens
Chat
Grok 4.20
grok-4-20Grok 4.20 is xAI's multimodal reasoning model with strong tool use, structured output support, and a 2M-token context window.
- Context
- 2,000,000 tokens
Input$2.84 / 1M tokens
Output$5.66 / 1M tokens
Cache read$0.46 / 1M tokens
All billing units (6)
Input · context > 200000 tokens$5.66 / 1M tokens
Output · context > 200000 tokens$11.34 / 1M tokens
Cache read · context > 200000 tokens$0.90 / 1M tokens
Chat
Grok 4.20 Multi-Agent
grok-4-20-multi-agentGrok 4.20 Multi-Agent is a variant of xAI Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information across complex tasks.
- Context
- 2,000,000 tokens
Input$2.84 / 1M tokens
Output$5.66 / 1M tokens
Cache read$0.46 / 1M tokens
All billing units (6)
Input · context > 200000 tokens$5.66 / 1M tokens
Output · context > 200000 tokens$11.34 / 1M tokens
Cache read · context > 200000 tokens$0.90 / 1M tokens
Chat
Grok 4.3
grok-4-3Grok 4.3 is a reasoning model from xAI with function calling, structured outputs, and a 1M-token context window. Suited for agentic workflows, instruction-following tasks, and applications requiring high factual accuracy.
- Context
- 1,000,000 tokens
- Reasoning
- none / low / medium / high
Input$2.84 / 1M tokens
Output$5.66 / 1M tokens
Cache read$0.46 / 1M tokens
All billing units (6)
Input · context > 200000 tokens$5.66 / 1M tokens
Output · context > 200000 tokens$11.34 / 1M tokens
Cache read · context > 200000 tokens$0.90 / 1M tokens
Chat
Grok 4.5
grok-4-5Grok 4.5 is xAI's intelligent coding model for agentic software engineering and workflow tasks, with function calling, structured outputs, and a 500K-token context window.
- Context
- 500,000 tokens
- Reasoning
- low / medium / high
Input$4.54 / 1M tokens
Output$13.60 / 1M tokens
Cache read$0.68 / 1M tokens
All billing units (6)
Input · context > 200000 tokens$9.06 / 1M tokens
Output · context > 200000 tokens$27.20 / 1M tokens
Cache read · context > 200000 tokens$1.36 / 1M tokens
Chat
Grok 4.6
grok-4-6Grok 4.6 is xAI's multimodal chat and reasoning model with function calling, structured outputs, adjustable reasoning effort (low/medium/high/xhigh), and a 500K-token context window.
- Context
- 500,000 tokens
- Reasoning
- low / medium / high / xhigh
Input$4.54 / 1M tokens
Output$13.60 / 1M tokens
Cache read$1.14 / 1M tokens
All billing units (6)
Input · context > 200000 tokens$9.06 / 1M tokens
Output · context > 200000 tokens$27.20 / 1M tokens
Cache read · context > 200000 tokens$2.26 / 1M tokens
Chat
Grok 4.7
grok-4-7Grok 4.7, the successor to Grok 4.6, is xAI's multimodal chat and reasoning model with function calling, structured outputs, adjustable reasoning effort (low/medium/high/xhigh), and a 500K-token context window.
- Context
- 500,000 tokens
- Reasoning
- low / medium / high / xhigh
Input$4.54 / 1M tokens
Output$13.60 / 1M tokens
Cache read$1.14 / 1M tokens
All billing units (6)
Input · context > 200000 tokens$9.06 / 1M tokens
Output · context > 200000 tokens$27.20 / 1M tokens
Cache read · context > 200000 tokens$2.26 / 1M tokens
Chat
Grok Build 0.1
grok-build-0-1xAI's fast coding model trained specifically for agentic coding, currently in early access.
- Context
- 256,000 tokens
Input$2.00 / 1M tokens
Output$4.00 / 1M tokens
Cache read$0.40 / 1M tokens
All billing units (6)
Input · context > 200000 tokens$4.00 / 1M tokens
Output · context > 200000 tokens$8.00 / 1M tokens
Cache read · context > 200000 tokens$0.80 / 1M tokens
Chat
Hy4 Preview
hy4-previewHy4 Preview is a 770B-parameter Mixture-of-Experts flagship model from the Tencent Hy team, with 49B parameters active per token and a 1M-token context window. It is post-trained for software engineering, office and data analysis, game development, and scientific research, with strong long-horizon reasoning, tool use, and agentic performance.
- Context
- 1,048,576 tokens
- Reasoning
- none / low / high
Input$2.085 / 1M tokens
Output$6.2525 / 1M tokens
Cache read$0.105 / 1M tokens
Classification
Jev (System One)
jev-latestJev (System One) is TypeSafe AI's decision model. Instead of writing text, it answers typed questions about a passage with structured judgments: yes-or-no probabilities, choices with confidence, or scores on a rubric. It reads up to 32,000 tokens of context, with up to 64,000 tokens across context and questions.
- Context
- 64,000 tokens
Input$0.084 / 1M tokens
Output$0.00 / 1M tokens
Chat
Kimi K2.5
kimi-k2-5Kimi K2.5 is an open reasoning model from Moonshot AI, featuring trillion-parameter Mixture-of-Experts architecture with 32B active parameters and a 256K-token context window.
- Context
- 256,000 tokens
- Reasoning
- none / low / medium / high
Input$1.12 / 1M tokens
Output$7.00 / 1M tokens
Cache read$0.44 / 1M tokens
Chat
Kimi K2.6
e2ee-kimi-k2-6Kimi K2.6 running in a Trusted Execution Environment (TEE). MoonshotAI's multimodal model with 262K context. Hardware attestation evidence is available for independent verification of enclave identity and configuration.
- Context
- 262,144 tokens
Input$1.74 / 1M tokens
Output$8.24 / 1M tokens
Cache read$0.88 / 1M tokens
Chat
Kimi K2.6
kimi-k2-6Kimi K2.6 is an open-source, native multimodal agentic model from Moonshot AI with 1T total parameters and 32B active parameters. It excels at long-horizon coding, coding-driven design, agent swarm orchestration, and proactive autonomous execution with a 256K-token context window.
- Context
- 256,000 tokens
- Reasoning
- none / low / medium / high
Input$1.50 / 1M tokens
Output$7.00 / 1M tokens
Cache read$0.32 / 1M tokens
Chat
Kimi K2.7 Code
kimi-k2-7-codeKimi K2.7 Code is Moonshot AI's coding-focused agentic model built on Kimi K2.6, with 1T total parameters and 32B active parameters. It always operates in thinking mode, supports text and image input, and targets long-horizon software engineering, agentic task decomposition, and multi-turn coding workflows with 256K context.
- Context
- 256,000 tokens
- Reasoning
- low / medium / high
Input$1.50 / 1M tokens
Output$7.00 / 1M tokens
Cache read$0.32 / 1M tokens
Chat
Kimi K3
e2ee-kimi-k3-pKimi 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.
- Context
- 1,000,000 tokens
- Reasoning
- none / max
Input$7.50 / 1M tokens
Output$37.50 / 1M tokens
Cache read$0.75 / 1M tokens
Chat
Kimi K3
kimi-k3Kimi K3 is an ultra-large-scale, 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.
- Context
- 1,000,000 tokens
- Reasoning
- none / low / high / max
Input$7.50 / 1M tokens
Output$37.50 / 1M tokens
Cache read$0.75 / 1M tokens
Chat
Kimi K3 Fast
kimi-k3-fast-apiKimi K3 is an ultra-large-scale, 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.
- Context
- 1,000,000 tokens
- Reasoning
- none / low / high / max
Input$9.00 / 1M tokens
Output$45.00 / 1M tokens
Cache read$0.90 / 1M tokens
Chat
Kimi K3.1 Pro
kimi-k3-1-proKimi K3.1 Pro is Moonshot AI's flagship multimodal reasoning model and the post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, agentic workflows, financial research, and 3D modeling through CAD code.
- Context
- 1,000,000 tokens
- Reasoning
- none / low / high / max
Input$4.00 / 1M tokens
Output$20.00 / 1M tokens
Cache read$0.40 / 1M tokens
Chat
Kimi K3.1 Pro Highspeed
kimi-k3-1-pro-highspeedKimi K3.1 Pro Highspeed is the faster variant of Kimi K3.1 Pro, Moonshot AI's flagship multimodal reasoning model. It offers the same quality and 1M-token context window with substantially higher output speed for latency-sensitive coding and agentic workflows.
- Context
- 1,000,000 tokens
- Reasoning
- none / low / high / max
Input$10.00 / 1M tokens
Output$50.00 / 1M tokens
Cache read$0.75 / 1M tokens
Chat
Llama 3.2 3B
llama-3.2-3bLlama 3.2 3B is a lightweight model from Meta's Llama 3.2 family, sized for fast, low-cost tasks such as summarization, classification and rewriting. It supports text input and output with a 128K-token context window and handles several languages.
- Context
- 128,000 tokens
Input$0.30 / 1M tokens
Output$1.20 / 1M tokens
Chat
Llama 3.3 70B
llama-3.3-70bLlama 3.3 70B is Meta's instruction-tuned 70-billion-parameter Llama model, which Meta reports performs close to its much larger Llama 3.1 405B on many tasks. It supports text input and output with a 128K-token context window, for chat, writing and code.
- Context
- 128,000 tokens
Input$1.40 / 1M tokens
Output$5.60 / 1M tokens
Chat
MiMo-V2.5
xiaomi-mimo-v2-5MiMo-V2.5 is Xiaomi's native omnimodal model with strong agentic capabilities, supporting text, image, video, and audio understanding in a unified architecture. Built on a sparse Mixture-of-Experts backbone with 310B total and 15B active parameters, it delivers long-context reasoning up to 1M tokens, function calling, and multimodal perception.
- Context
- 1,000,000 tokens
- Reasoning
- none / low / medium / high
Input$0.80 / 1M tokens
Output$4.00 / 1M tokens
Cache read$0.16 / 1M tokens
Chat
MiMo-V2.6-Flash
xiaomi-mimo-v2-6-flashMiMo-V2.6-Flash is Xiaomi's efficiency-balanced omnimodal model: a sparse Mixture-of-Experts with 309B total and 15B activated parameters, natively understanding text, image, video, and audio with a 1M-token context window. Trained with mixed reinforcement learning across coding, general agents, visual, and cybersecurity tasks, it is built for long-horizon coding, tool use, and computer use.
- Context
- 1,000,000 tokens
- Reasoning
- none / low / medium / high
Input$0.35 / 1M tokens
Output$0.70 / 1M tokens
Cache read$0.0075 / 1M tokens
Chat
MiniMax M2.5
minimax-m25MiniMax-M2.5 is a large language model optimized for coding, agentic workflows, and modern application development with enhanced reasoning capabilities.
- Context
- 198,000 tokens
- Reasoning
- low / medium / high
Input$0.54 / 1M tokens
Output$1.90 / 1M tokens
Cache read$0.06 / 1M tokens
Chat
MiniMax M2.7
minimax-m27MiniMax-M2.7 is a large language model designed for autonomous, real-world productivity with advanced agentic capabilities through multi-agent collaboration.
- Context
- 198,000 tokens
- Reasoning
- none / low / medium / high
Input$0.75 / 1M tokens
Output$3.00 / 1M tokens
Cache read$0.1375 / 1M tokens
Chat
MiniMax M3 Preview
minimax-m3-previewMiniMax-M3 preview is a 1.4T-parameter frontier model from MiniMax for coding, agentic workflows, and complex reasoning, served at fp8 with a 512K context window.
- Context
- 524,288 tokens
Input$0.60 / 1M tokens
Output$2.40 / 1M tokens
Cache read$0.12 / 1M tokens
Chat
MiniMax M3.1 Flash
minimax-m3-1-flashMiniMax M3.1 Flash is a frontier model for coding, agentic workflows, and complex reasoning, with a 1M-token context window, text, image, and video input, and tunable thinking depth from low to max (max by default).
- Context
- 1,000,000 tokens
Input$0.375 / 1M tokens
Output$1.50 / 1M tokens
Cache read$0.0375 / 1M tokens
Chat
Mistral Small 3.2 24B Instruct
mistral-small-3-2-24b-instructMistral Small 3.2 is a 24B parameter model optimized for efficiency and performance. Ideal for general-purpose tasks with balanced speed and capability.
- Context
- 256,000 tokens
Input$0.1875 / 1M tokens
Output$0.50 / 1M tokens
Embeddings
Multilingual E5 Large Instruct
text-embedding-multilingual-e5-large-instructMultilingual E5 Large Instruct is an open-weight embedding model from Microsoft's E5 family, covering about 100 languages. Queries start with a one-line task instruction, and inputs of up to 512 tokens become 1,024-dimensional vectors, which suits short passages and queries.
- Context
- 512 tokens
Input$0.025 / 1M tokens
Output$0.025 / 1M tokens
Chat
Muse Spark Open
muse-spark-openMuse Spark Open is an open-weight reasoning model from Meta for coding and agentic workflows. It supports tool calling and native image understanding in a single checkpoint, using a sparse Mixture-of-Experts architecture with 816B total / 42B active parameters and a 1M-token context window.
- Context
- 1,048,576 tokens
- Reasoning
- low / medium / high / xhigh
Input$3.125 / 1M tokens
Output$10.625 / 1M tokens
Cache read$0.375 / 1M tokens
Chat
Muse Wonder
muse-wonderMuse Wonder is a frontier reasoning model from Meta for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with a 1M-token context window. The model plans, delegates to sub-agents, calls tools in parallel, and recovers from errors so long-horizon work can run to completion without step-by-step direction.
- Context
- 1,048,576 tokens
- Reasoning
- none / low / medium / high / max
Input$10.00 / 1M tokens
Output$50.00 / 1M tokens
Cache read$0.50 / 1M tokens
Embeddings
Nemotron Embed VL 1B v2
text-embedding-nemotron-embed-vl-1b-v2Nemotron Embed VL 1B v2 is NVIDIA's open-weight embedding model from its Llama Nemotron family, trained for retrieval over visually rich documents such as reports, slides and scanned pages. Through the API it embeds text into 2,048-dimensional vectors.
- Context
- 32,768 tokens
Input$0.025 / 1M tokens
Output$0.025 / 1M tokens
Chat
NVIDIA Nemotron 3 Nano 30B
nvidia-nemotron-3-nano-30b-a3bNVIDIA Nemotron 3 Nano 30B is a compact and efficient language model from NVIDIA, optimized for fast inference while maintaining strong performance across diverse tasks.
- Context
- 128,000 tokens
Input$0.15 / 1M tokens
Output$0.60 / 1M tokens
Chat
NVIDIA Nemotron 3 Ultra
nvidia-nemotron-3-ultra-550b-a55bNVIDIA Nemotron 3 Ultra is built for frontier reasoning, orchestration, coding agents, deep research, and complex enterprise workflows. It delivers up to 5x faster inference and up to 30% lower cost for agentic workloads.
- Context
- 256,000 tokens
- Reasoning
- none / low / medium / high
Input$1.25 / 1M tokens
Output$6.25 / 1M tokens
Cache read$0.375 / 1M tokens
Chat
NVIDIA Nemotron 3.5 Super VL 120B
nvidia-nemotron-3-5-super-vl-120b-a12bNVIDIA Nemotron 3.5 Super VL is an open multimodal vision-language model for specialized agents. Its 120B-parameter Mixture-of-Experts design (12B active) understands text, images, documents, GUIs, and video, combining reasoning, instruction following, and tool use for long-running agentic workflows.
- Context
- 262,144 tokens
Input$0.40 / 1M tokens
Output$1.00 / 1M tokens
Cache read$0.08 / 1M tokens
Chat
OpenAI GPT OSS 120B
openai-gpt-oss-120bgpt-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. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation
- Context
- 128,000 tokens
- Reasoning
- none / low / medium / high
Input$0.14 / 1M tokens
Output$0.60 / 1M tokens
Chat
Qwen 2.5 7B
e2ee-qwen-2-5-7b-pQwen 2.5 7B Instruct running in a Trusted Execution Environment (TEE). A compact model with strong coding, math, and multilingual capabilities supporting 29+ languages, with hardware attestation evidence available for independent verification.
- Context
- 32,000 tokens
Input$0.10 / 1M tokens
Output$0.26 / 1M tokens
Chat
Qwen 3 235B A22B Instruct 2507
qwen3-235b-a22b-instruct-2507Answers directly, without a reasoning step. Built for in-depth research and handling long, complex documents. Ideal for technical work and high-precision tasks.
- Context
- 128,000 tokens
Input$0.30 / 1M tokens
Output$1.50 / 1M tokens
Chat
Qwen 3 235B A22B Thinking 2507
qwen3-235b-a22b-thinking-2507Reasons step by step before it answers. Built for in-depth research and handling long, complex documents. Ideal for technical work and high-precision tasks.
- Context
- 128,000 tokens
- Reasoning
- low / medium / high
Input$0.90 / 1M tokens
Output$7.00 / 1M tokens
Chat
Qwen 3 Coder 480B Turbo
qwen3-coder-480b-a35b-instruct-turboTurbo variant of Qwen3 Coder 480B, optimized for faster inference on code tasks.
- Context
- 256,000 tokens
Input$0.70 / 1M tokens
Output$3.00 / 1M tokens
Cache read$0.08 / 1M tokens
Chat
Qwen 3 Next 80b
qwen3-next-80bOptimized for speed and efficiency.
- Context
- 256,000 tokens
Input$0.70 / 1M tokens
Output$3.80 / 1M tokens
Chat
Qwen 3.5 35B A3B
qwen3-5-35b-a3bQwen 3.5 35B A3B is a highly efficient MoE model with 35B total parameters and only 3B active parameters. It surpasses the larger Qwen3-235B-A22B while being 6.7x smaller, excelling at reasoning, coding, and general knowledge tasks.
- Context
- 256,000 tokens
- Reasoning
- none / low / medium / high
Input$0.30 / 1M tokens
Output$2.00 / 1M tokens
Cache read$0.10 / 1M tokens
Chat
Qwen 3.5 397B
qwen3-5-397b-a17bQwen 3.5 is a reasoning model from Alibaba featuring a 397B parameter Mixture-of-Experts architecture with 17B active parameters. It excels at complex reasoning, coding, and general knowledge tasks.
- Context
- 128,000 tokens
- Reasoning
- none / low / medium / high
Input$1.50 / 1M tokens
Output$9.00 / 1M tokens
Chat
Qwen 3.6 27B
qwen3-6-27bThe Qwen 3.6 27B native vision-language dense model builds upon the 3.5-27B version, with key improvements in agentic coding capabilities and enhanced STEM reasoning and inference skills. In the vision modality, it demonstrates significant advances in spatial intelligence, object localization, and detection, while video understanding, document OCR, and visual agent capabilities continue to improve steadily.
- Context
- 256,000 tokens
- Reasoning
- none / low / medium / high
Input$0.65 / 1M tokens
Output$6.50 / 1M tokens
Chat
Qwen 3.6 35B A3B
qwen3-6-35b-a3bQwen 3.6 35B A3B is a fast mixture-of-experts model with 35B total parameters and ~3B active per token. Strong at agentic coding, STEM reasoning, and tool use, with a native 256K context window.
- Context
- 256,000 tokens
Input$0.20 / 1M tokens
Output$2.00 / 1M tokens
Chat
Qwen 3.6 35B A3B FP8
e2ee-qwen3-6-35b-a3bQwen 3.6 35B A3B FP8 running in a Trusted Execution Environment (TEE). A fast mixture-of-experts model with ~3B active parameters per token. Hardware attestation evidence is available for independent verification of enclave identity and configuration.
- Context
- 32,000 tokens
Input$0.364 / 1M tokens
Output$2.36 / 1M tokens
Cache read$0.12 / 1M tokens
ChatUNCENSORED
Qwen 3.6 Plus Uncensored
qwen-3-6-plusQwen 3.6 Plus Uncensored is an uncensored variant of Alibaba's Qwen 3.6 Plus, a reasoning model with exceptional performance across coding, reasoning, and general knowledge tasks. Features mixed reasoning, function calling, and multimodal input support.
- Context
- 1,000,000 tokens
Input$1.25 / 1M tokens
Output$7.50 / 1M tokens
Cache read$0.125 / 1M tokens
All billing units (8)
Cache write$1.56 / 1M tokens
Input · context > 256000 tokens$5.00 / 1M tokens
Output · context > 256000 tokens$15.00 / 1M tokens
Cache read · context > 256000 tokens$0.125 / 1M tokens
Cache write · context > 256000 tokens$1.56 / 1M tokens
Chat
Qwen 3.7 Max
qwen-3-7-maxQwen 3.7 Max is the largest model in the Qwen 3.7 series, with deep thinking, function calling, prompt caching, and multimodal input support for images and video. It excels at programming, office and productivity tasks, and long-running autonomous agent workflows.
- Context
- 1,000,000 tokens
Input$5.40 / 1M tokens
Output$16.10 / 1M tokens
Cache read$0.54 / 1M tokens
All billing units (4)
Cache write$6.70 / 1M tokens
Chat
Qwen 3.7 Plus
qwen-3-7-plusQwen 3.7 Plus, the successor to Qwen 3.6 Plus, is a reasoning model from Alibaba with exceptional performance across coding, reasoning, and general knowledge tasks. Features mixed reasoning, function calling, and multimodal input support.
- Context
- 1,000,000 tokens
Input$1.00 / 1M tokens
Output$4.00 / 1M tokens
Cache read$0.10 / 1M tokens
All billing units (8)
Cache write$1.25 / 1M tokens
Input · context > 256000 tokens$3.00 / 1M tokens
Output · context > 256000 tokens$12.00 / 1M tokens
Cache read · context > 256000 tokens$0.30 / 1M tokens
Cache write · context > 256000 tokens$3.75 / 1M tokens
Chat
Qwen 3.8 2.4T
qwen-3-8-2-4t-a95bQwen 3.8 2.4T is Alibaba's open-weight 2.4-trillion-parameter MoE model (95B active), with major gains in software engineering, research, and long-horizon agentic tasks. It is text-only, requires thinking mode, and supports a 262K-token context window.
- Context
- 262,144 tokens
Input$5.00 / 1M tokens
Output$15.00 / 1M tokens
Cache read$0.625 / 1M tokens
Chat
Qwen 3.8 27B
e2ee-qwen3-8-27bQwen 3.8 27B running in a Trusted Execution Environment (TEE). A multimodal model with 262K context supporting text and image input. Hardware attestation evidence is available for independent verification of enclave identity and configuration.
- Context
- 262,144 tokens
Input$0.94 / 1M tokens
Output$7.06 / 1M tokens
Cache read$0.094 / 1M tokens
ChatUNCENSORED
Qwen 3.8 27B
qwen-3-8-27bQwen 3.8 27B is a native vision-language dense model with 27B parameters. It improves coding, professional work, research, and long-horizon agentic tasks, with flexible thinking control and image and video understanding. It supports a native 262K-token context window.
- Context
- 262,144 tokens
- Reasoning
- none / low / medium / xhigh
Input$0.90 / 1M tokens
Output$6.40 / 1M tokens
Chat
Qwen 3.8 Flash
qwen-3-8-flashQwen 3.8 Flash is a multimodal model in the Qwen family, pairing strong reasoning and generation with remarkable speed. It natively supports a 1M-token context window, so it can process long documents, entire codebases, and complex conversations in a single pass. It excels at coding assistance, agentic workflows, and visual understanding, accepting text, image, and video input, and its thinking mode can be turned on or off per request.
- Context
- 1,000,000 tokens
Input$0.28 / 1M tokens
Output$0.98 / 1M tokens
Cache read$0.028 / 1M tokens
Chat
Qwen 3.8 Max
qwen-3-8-maxQwen 3.8 Max is Alibaba's flagship 2.4-trillion-parameter MoE model, with major gains over Qwen 3.7 Max in software engineering and office-productivity workflows and strong long-horizon, multi-agent performance. It accepts both text and vision-language input (images and video), operates in thinking mode only, and supports a 1M-token context window.
- Context
- 1,000,000 tokens
Input$5.00 / 1M tokens
Output$15.00 / 1M tokens
Cache read$0.625 / 1M tokens
All billing units (4)
Cache write$6.25 / 1M tokens
Embeddings
Qwen3 Embedding 0.6B
text-embedding-qwen3-0-6bQwen3 Embedding 0.6B is the smallest model in Alibaba's open-weight Qwen3 Embedding series, a fast, low-cost choice for multilingual and code retrieval. It returns 1,024-dimensional vectors.
- Context
- 32,768 tokens
Input$0.025 / 1M tokens
Output$0.025 / 1M tokens
Embeddings
Qwen3 Embedding 8B
text-embedding-qwen3-8bQwen3 Embedding 8B is the largest model in Alibaba's open-weight Qwen3 Embedding series, built on Qwen3 and trained for more than 100 languages, including programming languages. It returns 4,096-dimensional vectors for multilingual and code retrieval.
- Context
- 32,768 tokens
Input$0.025 / 1M tokens
Output$0.025 / 1M tokens
Chat
Qwen3 VL 235B
qwen3-vl-235b-a22bQwen3-VL 235B vision-language model with MoE architecture. The largest model in the Qwen3-VL series, with superior visual perception, OCR, and multimodal reasoning.
- Context
- 128,000 tokens
Input$0.42 / 1M tokens
Output$3.80 / 1M tokens
Cache read$0.20 / 1M tokens
Chat
Qwen3 VL 30B A3B
e2ee-qwen3-vl-30b-a3b-pQwen3 VL 30B A3B running in a Trusted Execution Environment (TEE). A multimodal model unifying text generation with visual understanding for images, with hardware attestation evidence available for independent verification.
- Context
- 128,000 tokens
Input$0.50 / 1M tokens
Output$1.80 / 1M tokens
ChatUNCENSORED
Role Play Uncensored
uncensored-role-playOptimized for creative roleplay scenarios with maximum freedom. Designed for immersive storytelling, character interactions, and open-ended creative writing.
- Context
- 128,000 tokens
Input$1.00 / 1M tokens
Output$4.00 / 1M tokens
Chat
Seed 2.1 Turbo
seed-2-1-turboSeed 2.1 Turbo (Dola-Seed-2.1) is ByteDance’s next-generation multimodal model for the coding and agent era, with engineering-grade code delivery, long-horizon agent execution, and upgraded GUI and video understanding. Supports text, image, and video inputs with a 256K context window.
- Context
- 256,000 tokens
Input$1.25 / 1M tokens
Output$6.25 / 1M tokens
Cache read$0.25 / 1M tokens
Embeddings
Text Embedding 3 Large
text-embedding-3-largeText Embedding 3 Large is OpenAI's larger embedding model, returning 3,072-dimensional vectors for inputs of up to 8,191 tokens. It suits retrieval where accuracy matters more than cost, and its vectors can be shortened with the dimensions parameter.
- Context
- 8,191 tokens
Input$0.325 / 1M tokens
Output$0.325 / 1M tokens
Embeddings
Text Embedding 3 Small
text-embedding-3-smallText Embedding 3 Small is OpenAI's efficient embedding model, returning 1,536-dimensional vectors for inputs of up to 8,191 tokens. It's a low-cost default for semantic search, clustering and classification, and its vectors can be shortened with the dimensions parameter.
- Context
- 8,191 tokens
Input$0.05 / 1M tokens
Output$0.05 / 1M tokens
ChatUNCENSORED
Uncensored 1.2
uncensored-1-2Uncensored 1.2 is designed for maximum creative freedom and authentic interaction. Built for open-ended exploration, roleplay, and unfiltered dialogue with improved capabilities over 1.1.
- Context
- 128,000 tokens
Input$0.40 / 1M tokens
Output$1.80 / 1M tokens