Discounted AI models on Infron

Provider discounts, all in one place.

Explore models with active public discounts from one or more inference providers. Each model shows the best available Standard tier provider discount, with current pricing compared against the provider's list price.

AI models with provider discounts

Upstage: Solar Pro 4

Text generation

Upstage's flagship text model for agentic, coding, document, and business workflows.

524.3K context

90% off

  • $0.03 $0.30 /M input tokens
  • $0.12 $1.20 /M output tokens

DeepSeek: Deepseek V4.1 Flash (Batch)

Batch

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the cost-efficient tier of the V4.1 family. DeepSeek reports that it exceeds V4 Pro on performance, speed, and task completion time, so it sits ahead of the previous flagship rather than beneath it. It is suited for coding, reasoning, and agentic workflows, and is particularly strong at long-horizon tasks that must run to completion across many steps.

1M context

80% off

  • $0.06 $0.30 /M input tokens
  • $0.24 $1.20 /M output tokens

DeepSeek: Deepseek V4 Flash 0731

Text generation

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows. This is the GA release of DeepSeek V4 Flash.

1M context

60% off

  • $0.17 $0.424 /M input tokens
  • $0.509 $1.272 /M output tokens

DeepSeek: Deepseek V4 Pro 0813

Text generation

1.6T total / 49B active params. Performance rivaling the world's top closed-source models.

1M context

60% off

  • $0.509 $1.272 /M input tokens
  • $1.526 $3.816 /M output tokens

DeepSeek: Deepseek V4.1 Flash

Text generation

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the cost-efficient tier of the V4.1 family. DeepSeek reports that it exceeds V4 Pro on performance, speed, and task completion time, so it sits ahead of the previous flagship rather than beneath it. It is suited for coding, reasoning, and agentic workflows, and is particularly strong at long-horizon tasks that must run to completion across many steps.

1M context

60% off

  • $0.113 $0.283 /M input tokens
  • $0.452 $1.131 /M output tokens

DeepSeek: Deepseek V4 Flash

Text generation

284B total / 13B active params. Your fast, efficient, and economical choice.

1M context

50% off

  • $0.069 $0.138 /M input tokens
  • $0.138 $0.275 /M output tokens

DeepSeek: Deepseek V4 Pro

Text generation

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding, and long-horizon agent workflows, with strong performance across knowledge, math, and software engineering benchmarks.

1M context

50% off

  • $0.825 $1.65 /M input tokens
  • $1.651 $3.301 /M output tokens

Mistral: Mistral Large 4

Text generation

Mistral Large 4 is a general-purpose multimodal model released by Mistral AI in public preview on October 6, 2026. Its granular mixture-of-experts architecture has a reported 1.05T total parameters, 52B active parameters and a 1.6B vision encoder. It targets multimodal understanding, document question answering and tool-assisted workflows. The official model page advertises a 1M context window, while this account catalog reports 524288 tokens; this configuration follows the live catalog limit.

524.3K context

50% off

  • $0.68 $1.36 /M input tokens
  • $2.09 $4.18 /M output tokens

Moonshot: Kimi K2.7 Code

Text generation

MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts architecture that accepts text, image and video input, and it always operates in a thinking mode, preserving full reasoning content across multi-turn conversations. With a 256K-token context window, it targets long-horizon coding, agentic task decomposition, and multi-turn dialogue. The model activates 32B parameters out of roughly 1T total.

256K context

50% off

  • $0.447 $0.894 /M input tokens
  • $1.857 $3.713 /M output tokens

Qwen: Qwen 3.5 Flash

Text generation

The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the 3 series, these models deliver a leap forward in performance for both pure text and multimodal tasks, offering fast response times while balancing inference speed and overall performance.

1M context

50% off

  • $0.05 $0.10 /M input tokens
  • $0.20 $0.40 /M output tokens

Qwen: Qwen 3.5 Plus

Text generation

The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of task evaluations, the 3.5 series consistently demonstrates performance on par with state-of-the-art leading models. Compared to the 3 series, these models show a leap forward in both pure-text and multimodal capabilities.

1M context

50% off

  • $0.058 $0.115 /M input tokens
  • $0.344 $0.688 /M output tokens

Qwen: Qwen 3.6 Flash

Text generation

The Qwen3.6 native vision-language Flash model series delivers a significant performance boost over the 3.5-Flash version. This model particularly excels in agentic coding capabilities, substantially outperforming its predecessor on multiple code-agent benchmarks, as well as in mathematical and code reasoning. In terms of vision, it features markedly improved spatial intelligence, with especially notable enhancements in object localization and object detection.

1M context

50% off

  • $0.083 $0.165 /M input tokens
  • $0.495 $0.99 /M output tokens

Qwen: Qwen 3.6 Plus

Text generation

The Qwen 3.6 Native Vision-Language Series Plus models demonstrate exceptional performance comparable to today's cutting-edge models, marking a significant improvement in effectiveness compared to the 3.5 series. These models feature substantial enhancements across various capabilities, including coding skills—such as Agentic coding, front-end programming, and Vibe coding—as well as multimodal object recognition, OCR, and object localization.

1M context

50% off

  • $0.138 $0.276 /M input tokens
  • $0.826 $1.651 /M output tokens

Qwen: Qwen 3.7 Flash

Text generation

Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world visual perception.

1M context

50% off

  • $0.014 $0.028 /M input tokens
  • $0.055 $0.11 /M output tokens

Qwen: Qwen Flash

Text generation

The Qwen3 series Flash models effectively blend thinking and non-thinking modes, allowing switching between modes during dialogue. They exhibit excellent performance on complex reasoning tasks, with significantly improved instruction following and text understanding capabilities. Support for 1MB context lengths is provided, with tiered billing based on context length.

1M context

50% off

  • $0.025 $0.05 /M input tokens
  • $0.20 $0.40 /M output tokens

Qwen: Qwen Mt Lite

Text generation

Based on the fully upgraded Qwen3 basic text translation model, it supports mutual translation between 32 languages. The model performance and translation effect have been fully upgraded, and it provides more stable terminology customization, format restoration accuracy and domain suggestion capabilities, making the translation more accurate and natural.

16K context

50% off

  • $0.06 $0.12 /M input tokens
  • $0.18 $0.36 /M output tokens

Qwen: Qwen Plus

Text generation

The enhanced version of the Qianwen ultra-large-scale language model supports input in different languages, including Chinese and English. Compared to previous versions, its Chinese and English coding capabilities, logical reasoning capabilities, and multilingual capabilities have been significantly improved. The response style has been greatly adjusted to cater to human preferences, and the level of detail and clarity of the model's responses has been significantly enhanced. Targeted improvements have been made to its capabilities in creative writing, JSON format compliance, and role-playing.

1M context

50% off

  • $0.20 $0.40 /M input tokens
  • $0.60 $1.20 /M output tokens

Qwen: Qwen Plus Character

Text generation

The Thousand Questions series of role-playing models is a dynamically updated version. Model updates will be announced in advance. It is suitable for anthropomorphic role-playing and has optimized the ability to follow limited character instructions, advance topics, listen and empathize, etc., supporting in-depth reproduction of personalized characters.

32K context

50% off

  • $0.25 $0.50 /M input tokens
  • $0.70 $1.40 /M output tokens

Qwen: Qwen3 14B

Text generation

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support.

131.1K context

50% off

  • $0.175 $0.35 /M input tokens
  • $0.70 $1.40 /M output tokens

Qwen: Qwen3 235B A22B

Text generation

Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a "thinking" mode for complex reasoning, math, and code tasks, and a "non-thinking" mode for general conversational efficiency. The model demonstrates strong reasoning ability, multilingual support (100+ languages and dialects), advanced instruction-following, and agent tool-calling capabilities. It natively handles a 32K token context window and extends up to 131K tokens using YaRN-based scaling.

131.1K context

50% off

  • $0.35 $0.70 /M input tokens
  • $1.40 $2.80 /M output tokens

Qwen: Qwen3 235B A22B Instruct 2507

Text generation

Qwen3-235B-A22B-Instruct-2507 has the following features: Type: Causal Language Models Training Stage: Pretraining & Post-training Number of Parameters: 235B in total and 22B activated Number of Paramaters (Non-Embedding): 234B Number of Layers: 94 Number of Attention Heads (GQA): 64 for Q and 4 for KV Number of Experts: 128 Number of Activated Experts: 8 Context Length: 262,144 natively and extendable up to 1,010,000 tokens NOTE: This model supports only non-thinking mode and does not generate <think></think> blocks in its output. Meanwhile, specifying enable_thinking=False is no longer required.

131.1K context

50% off

  • $0.115 $0.23 /M input tokens
  • $0.46 $0.92 /M output tokens

Qwen: Qwen3 235B A22B Thinking 2507

Text generation

Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144 tokens of context. This "thinking-only" variant enhances structured logical reasoning, mathematics, science, and long-form generation, showing strong benchmark performance across AIME, SuperGPQA, LiveCodeBench, and MMLU-Redux. It enforces a special reasoning mode (</think>) and is designed for high-token outputs (up to 81,920 tokens) in challenging domains. The model is instruction-tuned and excels at step-by-step reasoning, tool use, agentic workflows, and multilingual tasks. This release represents the most capable open-source variant in the Qwen3-235B series, surpassing many closed models in structured reasoning use cases.

131.1K context

50% off

  • $0.115 $0.23 /M input tokens
  • $1.15 $2.30 /M output tokens

Qwen: Qwen3 30B A3B

Text generation

Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique ability to switch seamlessly between a thinking mode for complex reasoning and a non-thinking mode for efficient dialogue ensures versatile, high-quality performance. Significantly outperforming prior models like QwQ and Qwen2.5, Qwen3 delivers superior mathematics, coding, commonsense reasoning, creative writing, and interactive dialogue capabilities. The Qwen3-30B-A3B variant includes 30.5 billion parameters (3.3 billion activated), 48 layers, 128 experts (8 activated per task), and supports up to 131K token contexts with YaRN, setting a new standard among open-source models.

131.1K context

50% off

  • $0.10 $0.20 /M input tokens
  • $0.40 $0.80 /M output tokens

Qwen: Qwen3 30B A3B Instruct 2507

Text generation

Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and agentic tool use. Post-trained on instruction data, it demonstrates competitive performance across reasoning (AIME, ZebraLogic), coding (MultiPL-E, LiveCodeBench), and alignment (IFEval, WritingBench) benchmarks. It outperforms its non-instruct variant on subjective and open-ended tasks while retaining strong factual and coding performance.

131.1K context

50% off

  • $0.10 $0.20 /M input tokens
  • $0.40 $0.80 /M output tokens

Qwen: Qwen3 30B A3B Thinking 2507

Text generation

Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated from final answers. Compared to earlier Qwen3-30B releases, this version improves performance across logical reasoning, mathematics, science, coding, and multilingual benchmarks. It also demonstrates stronger instruction following, tool use, and alignment with human preferences. With higher reasoning efficiency and extended output budgets, it is best suited for advanced research, competitive problem solving, and agentic applications requiring structured long-context reasoning.

131.1K context

50% off

  • $0.10 $0.20 /M input tokens
  • $1.20 $2.40 /M output tokens

Qwen: Qwen3 32B

Text generation

Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for tasks like math, coding, and logical inference, and a "non-thinking" mode for faster, general-purpose conversation. The model demonstrates strong performance in instruction-following, agent tool use, creative writing, and multilingual tasks across 100+ languages and dialects. It natively handles 32K token contexts and can extend to 131K tokens using YaRN-based scaling.

131.1K context

50% off

  • $0.08 $0.16 /M input tokens
  • $0.32 $0.64 /M output tokens

Qwen: Qwen3 8B

Text generation

Qwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both reasoning-heavy tasks and efficient dialogue. It supports seamless switching between "thinking" mode for math, coding, and logical inference, and "non-thinking" mode for general conversation. The model is fine-tuned for instruction-following, agent integration, creative writing, and multilingual use across 100+ languages and dialects. It natively supports a 32K token context window and can extend to 131K tokens with YaRN scaling.

131.1K context

50% off

  • $0.09 $0.18 /M input tokens
  • $0.35 $0.70 /M output tokens

Qwen: Qwen3 Coder Flash

Text generation

Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing in autonomous programming via tool calling and environment interaction, combining coding proficiency with versatile general-purpose abilities.

131.1K context

50% off

  • $0.15 $0.30 /M input tokens
  • $0.75 $1.50 /M output tokens

Qwen: Qwen3 Coder Plus

Text generation

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 environment interaction, combining coding proficiency with versatile general-purpose abilities.

131.1K context

50% off

  • $0.50 $1.00 /M input tokens
  • $2.50 $5.00 /M output tokens

Qwen: Qwen3 Max

Text generation

Qwen/qwen3-max, Enhanced with specialized upgrades in agent programming and tool calling. This official release achieves domain SOTA performance, supporting more complex agent scenarios.

262.1K context

50% off

  • $0.60 $1.20 /M input tokens
  • $3.00 $6.00 /M output tokens

Qwen: Qwen3 Next 80B A3B Instruct

Text generation

Qwen3-Next-80B-A3B-Instruct is an 80B parameter model with only 3B activated per token that excels at handling ultra-long contexts up to 256K tokens natively while maintaining strong performance across reasoning, coding, and knowledge tasks with exceptional inference efficiency.

128K context

50% off

  • $0.072 $0.144 /M input tokens
  • $0.287 $0.574 /M output tokens

Qwen: Qwen3 Next 80B A3B Thinking

Text generation

Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agentic planning, and reports strong results across knowledge, reasoning, coding, alignment, and multilingual evaluations. Compared with prior Qwen3 variants, it emphasizes stability under long chains of thought and efficient scaling during inference, and it is tuned to follow complex instructions while reducing repetitive or off-task behavior. The model is suitable for agent frameworks and tool use (function calling), retrieval-heavy workflows, and standardized benchmarking where step-by-step solutions are required. It supports long, detailed completions and leverages throughput-oriented techniques (e.g., multi-token prediction) for faster generation. Note that it operates in thinking-only mode.

131.1K context

50% off

  • $0.075 $0.15 /M input tokens
  • $0.60 $1.20 /M output tokens

Qwen: Qwen3-VL-Flash

Text generation

The Qwen3 series of small-sized visual understanding models effectively integrates thinking and non-thinking modes, outperforming the open-source version Qwen3-VL-30B-A3B with faster response times. It features a comprehensive upgrade in image/video understanding, supporting extended contextual information such as long videos and documents, spatial awareness, and object recognition; it also possesses visual 2D/3D localization capabilities, making it competent for complex real-world tasks.

256K context

50% off

  • $0.025 $0.05 /M input tokens
  • $0.20 $0.40 /M output tokens

Qwen: Qwen3-VL-Plus

Text generation

The Qwen3 series of visual understanding models effectively integrates thinking and non-thinking modes, achieving world-class performance on public benchmark datasets such as OS World. This version features comprehensive upgrades in visual coding, spatial perception, and multimodal thinking; visual perception and recognition capabilities have been significantly improved, supporting ultra-long video understanding.

256K context

50% off

  • $0.10 $0.20 /M input tokens
  • $0.80 $1.60 /M output tokens

Qwen: Qwen3.5-122B-A10B

Text generation

The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of overall performance, this model is second only to Qwen3.5-397B-A17B. Its text capabilities significantly outperform those of Qwen3-235B-2507, and its visual capabilities surpass those of Qwen3-VL-235B.

262.1K context

50% off

  • $0.20 $0.40 /M input tokens
  • $1.60 $3.20 /M output tokens

Qwen: Qwen3.5-27B

Text generation

The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to those of the Qwen3.5-122B-A10B.

256K context

50% off

  • $0.043 $0.086 /M input tokens
  • $0.344 $0.688 /M output tokens

Qwen: Qwen3.5-35B-A3B

Text generation

The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall performance is comparable to that of the Qwen3.5-27B.

256K context

50% off

  • $0.029 $0.057 /M input tokens
  • $0.23 $0.459 /M output tokens

Qwen: Qwen3.5-397B-A17B

Text generation

The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers state-of-the-art performance comparable to leading-edge models across a wide range of tasks, including language understanding, logical reasoning, code generation, agent-based tasks, image understanding, video understanding, and graphical user interface (GUI) interactions. With its robust code-generation and agent capabilities, the model exhibits strong generalization across diverse agent.

256K context

50% off

  • $0.086 $0.172 /M input tokens
  • $0.516 $1.032 /M output tokens

Qwen: Qwen3.6 Max Preview

Text generation

The Max model, the largest and most capable variant in the Qwen3.6 series, is now available in a preview version. At present, only its plain-text capabilities are open for experimentation. Compared with the previously released Qwen3-Max and Qwen3.6-Plus, this model features enhanced vibe coding abilities, more efficient coding agent execution, and significantly improved front-end development skills. Additionally, its long-tail knowledge retention has been further upgraded.

256K context

50% off

  • $0.65 $1.30 /M input tokens
  • $3.90 $7.80 /M output tokens

Qwen: Qwen3.6-27B

Text generation

The Qwen3.6 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.

256K context

50% off

  • $0.30 $0.60 /M input tokens
  • $1.80 $3.60 /M output tokens

Qwen: Qwen3.6-35B-A3B

Text generation

The Qwen3.6 35B-A3B native vision-language model is built on a hybrid architecture that integrates linear attention mechanisms with a sparse mixture-of-experts framework, achieving higher inference efficiency. Compared with the 3.5-35B-A3B, this model demonstrates significantly improved agentic coding capabilities, mathematical and code reasoning abilities, spatial intelligence, as well as object localization and object detection performance.

256K context

50% off

  • $0.124 $0.248 /M input tokens
  • $0.743 $1.485 /M output tokens

Qwen: Qwen3.7 Max

Text generation

Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks, and long-horizon autonomous execution. The model offers notable gains in coding and agentic performance over prior Qwen generations and supports explicit prompt caching for efficient repeated context use.

1M context

50% off

  • $0.825 $1.65 /M input tokens
  • $2.475 $4.951 /M output tokens

Qwen: Qwen3.7 Plus

Text generation

Among the Qwen3.7 series, the cost-effective Plus model builds on its robust text capabilities while delivering a comprehensive upgrade to its vision‑language abilities, all while preserving its full‑stack agent‑level intelligence for coding, tool use, and productivity workflows. Its key distinguishing feature is multi‑modal interactive hybrid agent capabilities, enabling it to perceive real‑world scenes, read screens and interact with GUIs, generate code based on visual references, and perform end‑to‑end navigation within mobile apps.

1M context

50% off

  • $0.138 $0.276 /M input tokens
  • $0.55 $1.101 /M output tokens

Qwen: Qwen3.8 2.4T A95B

Text generation

Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of Qwen3.8 Max, with 95 billion active parameters out of 2.4 trillion total. It is suited for coding, research, complex reasoning, and agentic workflows.

1M context

50% off

  • $1.00 $2.00 /M input tokens
  • $3.00 $6.00 /M output tokens

Qwen: Qwen3.8 27B

Text generation

Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be enabled or disabled.

1M context

50% off

  • $0.25 $0.50 /M input tokens
  • $1.50 $3.00 /M output tokens

Qwen: Qwen3.8 Flash

Text generation

Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-video analysis.

1M context

50% off

  • $0.075 $0.15 /M input tokens
  • $0.235 $0.47 /M output tokens

Qwen: Qwen3.8 Max

Text generation

2.4-trillion-parameter MoE flagship delivering a comprehensive leap in coding and professional work. Autonomously codes and delivers complete projects spanning 10+ days. Handles hundreds of specialized tasks across legal, financial, design, and other professional domains, producing production-grade results end-to-end in a single conversation. Native visual understanding runs through the full cycle of planning, execution, and verification, enabling deep semantic analysis of ultra-long documents and extended video content. In long-horizon tasks, plans autonomously, iterates through closed feedback loops, and continuously evolves.

1M context

50% off

  • $0.825 $1.65 /M input tokens
  • $2.475 $4.951 /M output tokens

Qwen: Qwen3.8 Max Prime

Text generation

Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point. It accepts text, image, and video input and returns text, with a 1M-token context window and reasoning enabled by default. Tool calling, structured outputs, and configurable reasoning effort are supported, matching Qwen3.8 Max.

1M context

50% off

  • $2.00 $4.00 /M input tokens
  • $6.00 $12.00 /M output tokens

Qwen: Qwen3.8 Omni Flash

Text generation

Qwen’s next-generation native omni-modal model supports context lengths of up to 1M tokens and natively accepts text, image, audio, and video inputs. Built on the Qwen3.8-Flash-Next architecture, it is designed for agentic capabilities in real-world productivity scenarios. In addition to coding, knowledge work, GUI interaction, and other agentic tasks, it delivers significant performance gains in workflows that require integrated processing of text, images, audio, and video, including video editing, music video creation, film and video production and narration, multimedia summarization, and audio-video dialogue. It supports two-channel and four-channel spatial audio understanding and is compatible with both the DashScope and OpenAI protocols. We recommend installing the companion Qwen-MM-Plugins to help agent frameworks access its native multimodal capabilities.

1M context

50% off

  • $0.057 $0.113 /M input tokens
  • $0.191 $0.382 /M output tokens

Upstage: Solar Mini 4

Text generation

Solar Mini 4 is Upstage's compact, cost-efficient language model, a 35B-parameter mixture-of-experts with 3B active parameters and a 524K context window. It is built for agentic use cases where response speed and cost matter, with fluent Korean alongside strong English and Japanese, and support for long-context workloads.

524.3K context

50% off

  • $0.05 $0.10 /M input tokens
  • $0.20 $0.40 /M output tokens

Z.AI: GLM 4.6

Text generation

GLM-4.6 achieves comprehensive enhancements across multiple domains, including real-world coding, long-context processing, reasoning, searching, writing, and agentic applications. Details are as follows: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex agentic tasks. Superior coding performance: The model achieves higher scores on code benchmarks and demonstrates better real-world performance in applications such as Claude Code、Cline、Roo Code and Kilo Code, including improvements in generating visually polished front-end pages. Advanced reasoning: GLM-4.6 shows a clear improvement in reasoning performance and supports tool use during inference, leading to stronger overall capability. More capable agents: GLM-4.6 exhibits stronger performance in tool use and search-based agents, and integrates more effectively within agent frameworks. Refined writing: Better aligns with human preferences in style and readability, and performs more naturally in role-playing scenarios.

198K context

50% off

  • $0.215 $0.431 /M input tokens
  • $1.004 $2.007 /M output tokens

Z.AI: GLM 4.7

Text generation

GLM-4.7 is Z.AI’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while delivering more natural conversational experiences and superior front-end aesthetics.

198K context

50% off

  • $0.215 $0.431 /M input tokens
  • $1.004 $2.007 /M output tokens

Z.AI: GLM 5

Text generation

GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading closed-source models. With advanced agentic planning, deep backend reasoning, and iterative self-correction, GLM-5 moves beyond code generation to full-system construction and autonomous execution.

198K context

50% off

  • $0.286 $0.573 /M input tokens
  • $1.29 $2.58 /M output tokens

Z.AI: GLM 5.1

Text generation

GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on a single task for more than 8 hours, autonomously planning, executing, and improving itself throughout the process, ultimately delivering complete, engineering-grade results.

202K context

50% off

  • $0.412 $0.825 /M input tokens
  • $1.651 $3.301 /M output tokens

Z.AI: GLM 5.2

Text generation

GLM-5.2 is Z.ai’s flagship model for the era of long-horizon tasks. With a truly usable 1M-token context window, it can handle project-level engineering context, execute long-running tasks more reliably, follow engineering standards more consistently, and complete the full development workflow from requirements to multi-platform deployment in a single task.

1M context

50% off

  • $0.55 $1.10 /M input tokens
  • $1.925 $3.851 /M output tokens

Z.AI: GLM 5.2 Fast

Text generation

GLM-5.2-Fast-Preview is the high-speed version of Zhipu AI’s flagship model, GLM-5.2. It supports an ultra-long context window of 1 million tokens and matches the capabilities of the standard GLM-5.2 edition, excelling in logical reasoning, long-text comprehension, and code generation. Through inference acceleration optimizations, its output throughput (TPS) reaches 1.5 to 2 times that of the standard version, significantly boosting output speed. It is ideally suited for scenarios where speed is critical, such as real-time conversations, multi-turn agent interactions, and streaming code generation.

1M context

50% off

  • $1.40 $2.80 /M input tokens
  • $4.40 $8.80 /M output tokens

Z.AI: GLM 5.3

Text generation

GLM-5.3 is an advanced large language model designed to deliver strong performance across a wide range of natural language processing tasks, including text generation, reasoning, summarization, translation, coding assistance, and conversational interaction. Built on the GLM architecture, it aims to provide more accurate understanding, more coherent responses, and improved instruction-following capabilities. With enhanced contextual comprehension and multilingual support, GLM-5.3 can be applied in education, business, research, software development, and intelligent assistant scenarios, offering users an efficient and flexible AI-powered solution for complex language tasks.

1M context

50% off

  • $0.70 $1.40 /M input tokens
  • $2.20 $4.40 /M output tokens

Z.AI: GLM 5.3 Prime

Text generation

GLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5–2× the output throughput through inference acceleration. It supports text input and output with a 1M-token context window and up to 128K output tokens, and targets coding and agentic workloads, including long-horizon multi-turn agent orchestration, real-time conversation, and streaming code generation.

1M context

50% off

  • $1.40 $2.80 /M input tokens
  • $4.40 $8.80 /M output tokens

Alibaba: HappyHorse-1.0 (Video Edit)

Video Edit

HappyHorse video editing supports advanced video editing through natural language instructions. It allows for local or global editing of video elements using up to 5 reference images.

40% off

  • $0.084 $0.14 /second video

Alibaba: HappyHorse-1.1 (Image to Video)

Image-To-Video

Happy Horse 1.1 is Alibaba's #1-ranked video model. This image-to-video endpoint animates a still image into 1080p video with synchronized native audio and multilingual lip-sync

40% off

  • $0.084 $0.14 /second video

Alibaba: HappyHorse-1.1 (Reference to Video)

Reference to Video

Happy Horse 1.1 is Alibaba's #1-ranked video model. This reference-to-video endpoint turns up to 9 reference images into 1080p video with synchronized native audio and multilingual lip-sync for consistent characters.

40% off

  • $0.084 $0.14 /second video

Alibaba: HappyHorse-1.1 (Text to Video)

Text-To-Video

Happy Horse 1.1 is Alibaba's #1-ranked video model. This text-to-video endpoint generates 1080p video with synchronized native audio and multilingual lip-sync from a text prompt alone.

40% off

  • $0.084 $0.14 /second video

Alibaba: Qwen Image 3.0 (Image to Image)

Image-To-Image

Generates images from a text prompt at resolutions up to 2048×2048, with automatic prompt rewriting and prompt-guided resolution selection, building on Qwen's strength in complex text rendering and precise prompt adherence

4.5K context

40% off

  • $0.018 $0.03 /generation

Alibaba: Qwen Image 3.0 (Text to Image)

Text-To-Image

Edits images from one to three reference images and a natural-language instruction, preserving key details such as facial features and identity while applying the requested changes

4.5K context

40% off

  • $0.018 $0.03 /generation

Alibaba: Qwen Image 3.0 Pro (Image to Image)

Image-To-Image

Qwen Image 3.0 Pro Edit is a professional-grade image editing model that transforms existing images with natural-language instructions, delivering advanced instruction understanding, superior visual quality, and up to 2K output for creative and production workflows.

4.5K context

40% off

  • $0.024 $0.04 /generation

Alibaba: Qwen Image 3.0 Pro (Text to Image)

Text-To-Image

Qwen Image 3.0 Pro Text-to-Image is a professional-grade image generation model that creates high-quality images from text prompts, with advanced prompt understanding, strong visual quality, and up to 2K output for creative and production workflows.

4.5K context

40% off

  • $0.024 $0.04 /generation

Alibaba: Wan 2.7 Image (Image to Image)

Image-To-Image

Generate high-quality images from image prompts using the WAN 2.7 model with advanced prompt understanding and detailed output.

40% off

  • $0.018 $0.03 /generation

Alibaba: Wan 2.7 Image (Text to Image)

Text-To-Image

Generate high-quality images from text prompts using the WAN 2.7 model with advanced prompt understanding and detailed output.

40% off

  • $0.018 $0.03 /generation

Alibaba: Wan 2.7 Image Pro (Image to Image)

Image-To-Image

Wan2.7–image-pro，supports text to image, text/image to sequential images, image editing, multi-image reference generation, and interactive editing. Delivers enhanced performance in text rendering, subject consistency, and complex instruction following.

40% off

  • $0.045 $0.075 /generation

Alibaba: Wan 2.7 Image Pro (Text to Image)

Text-To-Image

Wan2.7–image-pro，supports text to image, text/image to sequential images, image editing, multi-image reference generation, and interactive editing. Delivers enhanced performance in text rendering, subject consistency, and complex instruction following.

40% off

  • $0.045 $0.075 /generation

Alibaba: Wan 3.0 (Image to Video)

Image-To-Video

Wan 3.0 Image to Video animates a first-frame image into a cinematic video, with optional last-frame guidance, flexible 2-30 second duration, aspect ratio control, optional audio, and deep-thinking controls for high-quality motion and scene continuity.

40% off

  • $0.03 $0.05 /second video

Alibaba: Wan 3.0 (Reference to Video)

Image-To-Video

Wan 3.0 Reference to Video creates coherent videos from prompts and multimodal references, including images, videos, and audio, with flexible 2-30 second duration and aspect ratio control for subject consistency, motion guidance, timing control, and scene continuity.

40% off

  • $0.03 $0.05 /second video

Alibaba: Wan 3.0 (Text to Video)

Text-To-Video

Wan 3.0 Text to Video generates cinematic videos from text prompts, with flexible 2-30 second duration, aspect ratio control, optional audio, and deep-thinking controls for high-quality video generation.

40% off

  • $0.03 $0.05 /second video

Alibaba: Wan 3.0 (Video Edit)

Video-To-Video

Wan 3.0 Reference to Video creates coherent videos from prompts and multimodal references, including images, videos, and audio, with flexible 2-30 second duration and aspect ratio control for subject consistency, motion guidance, timing control, and scene continuity.

40% off

  • $0.03 $0.05 /second video

Moonshotai: Kimi K3

Text generation

Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at navigating large repositories, using tools, debugging, and iterating against images, logs, tests, and runtime feedback. Its architecture uses KDA and Attention Residuals for computational efficiency.

1M context

40% off

  • $1.696 $2.827 /M input tokens
  • $8.48 $14.133 /M output tokens

Alibaba: HappyHorse-1.0 (Image to Video)

Image-To-Video

Alibaba's #1-ranked Happy Horse 1.0 — generate 1080p video with synchronized native audio and multilingual lip-sync from text prompts or images.

40% off

  • $0.074 $0.124 /second video

Alibaba: HappyHorse-1.0 (Reference to Video)

Reference to Video

Generate 1080p video with synchronized native audio from a text prompt and references. Aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4. Duration: 3–15s.

40% off

  • $0.074 $0.124 /second video

Alibaba: HappyHorse-1.0 (Text to Video)

Text-To-Video

Generate 1080p video with synchronized native audio from a text prompt. Aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4. Duration: 3–15s.

40% off

  • $0.074 $0.124 /second video

Alibaba: Wan 2.7 (Image to Video)

Image-To-Video

Wan 2.7 is the latest generation AI video model, delivering enhanced motion smoothness, superior scene fidelity, and greater visual coherence.

40% off

  • $0.052 $0.086 /second video

Alibaba: Wan 2.7 (Reference to Video)

Image-To-Video

Wan 2.7 is the latest generation AI video model, delivering enhanced motion smoothness, superior scene fidelity, and greater visual coherence.

40% off

  • $0.052 $0.086 /second video

Alibaba: Wan 2.7 (Text to Video)

Text-To-Video

Generate high-quality images from text prompts using the WAN 2.7 model with advanced prompt understanding and detailed output.

40% off

  • $0.052 $0.086 /second video

Alibaba: Wan 2.7 (Video Edit)

Video-To-Video

Wan 2.7 is the latest generation AI video model, delivering enhanced motion smoothness, superior scene fidelity, and greater visual coherence.

40% off

  • $0.052 $0.086 /second video

Z.AI: GLM 5.3 Flash

Text generation

GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while reducing compute overhead.

1M context

30% off

  • $0.105 $0.15 /M input tokens
  • $0.35 $0.50 /M output tokens

Google: Gemini 2.5 flash

Text generation

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 accuracy and nuanced context handling.

1M context

25% off

  • $0.225 $0.30 /M input tokens
  • $1.875 $2.50 /M output tokens

Google: Gemini 2.5 flash image

Text generation

Gemini 2.5 Flash Image, AKA Nano Banana is a state of the art image generation model with contextual understanding. It is capable of image generation, edits, and multi-turn conversations.

32.8K context

25% off

  • $0.225 $0.30 /M input tokens
  • $22.50 $30.00 /M output tokens

Google: Gemini 2.5 flash image preview

Text generation

Gemini 2.5 Flash Image Preview, AKA Nano Banana is a state of the art image generation model with contextual understanding. It is capable of image generation, edits, and multi-turn conversations.

32.8K context

25% off

  • $0.225 $0.30 /M input tokens
  • $22.50 $30.00 /M output tokens

Google: Gemini 2.5 flash lite

Text generation

Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance across common benchmarks compared to earlier Flash models.

1M context

25% off

  • $0.075 $0.10 /M input tokens
  • $0.30 $0.40 /M output tokens

Google: Gemini 2.5 flash preview

Text generation

Gemini 2.5 Flash is our best model in terms of price and performance, and offers well-rounded capabilities. Gemini 2.5 Flash is our first Flash model model that features thinking capabilities, which lets you see the thinking process that the model goes through when generating its response.

1M context

25% off

  • $0.225 $0.30 /M input tokens
  • $1.875 $2.50 /M output tokens

Google: Gemini 2.5 flash preview 05 20

Text generation

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 accuracy and nuanced context handling.

1M context

25% off

  • $0.225 $0.30 /M input tokens
  • $1.875 $2.50 /M output tokens

Google: Gemini 2.5 pro

Text generation

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 and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.

1M context

25% off

  • $0.938 $1.25 /M input tokens
  • $7.50 $10.00 /M output tokens

Google: Gemini 2.5 pro preview 03 25

Text generation

Gemini 2.5 Pro is our most advanced reasoning Gemini model, capable of solving complex problems. Gemini 2.5 Pro can comprehend vast datasets and challenging problems from different information sources, including text, audio, images, video, and even entire code repositories.

1M context

25% off

  • $0.938 $1.25 /M input tokens
  • $7.50 $10.00 /M output tokens

Google: Gemini 2.5 pro preview 05 06

Text generation

Gemini 2.5 Pro is our most advanced reasoning Gemini model, capable of solving complex problems. Gemini 2.5 Pro can comprehend vast datasets and challenging problems from different information sources, including text, audio, images, video, and even entire code repositories.

1M context

25% off

  • $0.938 $1.25 /M input tokens
  • $7.50 $10.00 /M output tokens

Google: Gemini 2.5 pro preview 06 05

Text generation

Gemini 2.5 Pro is our most advanced reasoning Gemini model, capable of solving complex problems. Gemini 2.5 Pro can comprehend vast datasets and challenging problems from different information sources, including text, audio, images, video, and even entire code repositories.

1M context

25% off

  • $0.938 $1.25 /M input tokens
  • $7.50 $10.00 /M output tokens

Google: Gemini 3 flash preview

Text generation

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 and tool use performance with substantially lower latency than larger Gemini variants, making it well suited for interactive development, long running agent loops, and collaborative coding tasks. Compared to Gemini 2.5 Flash, it provides broad quality improvements across reasoning, multimodal understanding, and reliability. The model supports a 1M token context window and multimodal inputs including text, images, audio, video, and PDFs, with text output. It includes configurable reasoning via thinking levels (minimal, low, medium, high), structured output, tool use, and automatic context caching. Gemini 3 Flash Preview is optimized for users who want strong reasoning and agentic behavior without the cost or latency of full scale frontier models.

1M context

25% off

  • $0.375 $0.50 /M input tokens
  • $2.25 $3.00 /M output tokens

Google: Gemini 3.1 flash lite

Text generation

Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic workflows, simple data extraction, and applications where responsiveness and API cost are the primary constraints. Supports full thinking levels (minimal, low, medium, high) for fine-grained cost/performance trade-offs. Priced at half the cost of Gemini 3 Flash.

1M context

25% off

  • $0.188 $0.25 /M input tokens
  • $1.125 $1.50 /M output tokens

Google: Gemini 3.1 flash lite preview

Text generation

Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2.5 Flash performance across key capabilities. Improvements span audio input/ASR, RAG snippet ranking, translation, data extraction, and code completion. Supports full thinking levels (minimal, low, medium, high) for fine-grained cost/performance trade-offs. Priced at half the cost of Gemini 3 Flash.

1M context

25% off

  • $0.188 $0.25 /M input tokens
  • $1.125 $1.50 /M output tokens

Google: Gemini 3.1 pro preview

Speech-To-Text

Gemini 3.1 Pro is designed to tackle the most challenging agentic problems with strong coding and state-of-the-art reasoning capabilities as well as complex multimodal understanding. Compared to Gemini 2.5 Pro, it improves significantly on complex instruction following and delivers outcomes with better output efficiency. Gemini 3 family models are thinking models, capable of reasoning through their thoughts before responding, resulting in enhanced performance and improved accuracy.

1M context

25% off

  • $1.50 $2.00 /M input tokens
  • $9.00 $12.00 /M output tokens

Google: Gemini 3.5 Flash

Text generation

Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution loops, supporting text, image, video, audio, and PDF inputs. Defaults to medium thinking effort for faster and more cost-efficient responses, with full support for thinking levels (minimal, low, medium, high) for fine-grained cost/performance trade-offs.

1M context

25% off

  • $1.125 $1.50 /M input tokens
  • $6.75 $9.00 /M output tokens

Google: Gemini 3.5 Flash Lite

Text generation

Gemini 3.5 Flash Lite is Flash-Lite's first step into the agentic space, prioritizing thinking and tool calling to serve as a quick, efficient, and capable subagent for larger, more complex workflows. Compared to Gemini 3.1 Flash-Lite, it delivers stronger agentic performance and tool use, more precise and complete document understanding, and improved overall reasoning capabilities, all while retaining Flash-Lite's cost efficiency and high throughput. Customers on Gemini 2.5 Flash can also migrate directly to Gemini 3.5 Flash Lite.

1M context

25% off

  • $0.225 $0.30 /M input tokens
  • $1.875 $2.50 /M output tokens

Google: Gemini 3.6 Flash

Text generation

Gemini 3.6 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution loops, supporting text, image, video, audio, and PDF inputs. Defaults to medium thinking effort for faster and more cost-efficient responses, with full support for thinking levels (minimal, low, medium, high) for fine-grained cost/performance trade-offs.

1M context

25% off

  • $0.563 $0.75 /M input tokens
  • $2.813 $3.75 /M output tokens

Google: Gemini 3.7 Flash

Text generation

Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step problem solving.

1M context

25% off

  • $0.563 $0.75 /M input tokens
  • $2.813 $3.75 /M output tokens

Google: Gemini 3.8 Flash

Text generation

Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.

1M context

25% off

  • $0.563 $0.75 /M input tokens
  • $2.813 $3.75 /M output tokens

Google: Gemini 4 Argon

Text generation

Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across long, multi-step tasks and to turn long documents mixing text, tables, charts and images into a single grounded output. It leads the Vals Index across finance, legal, coding and tax work, and supports long decode of up to 1M output tokens in a single response.

1M context

25% off

  • $1.50 $2.00 /M input tokens
  • $7.50 $10.00 /M output tokens

Google: Gemini Embedding 001

Embedding

gemini-embedding-001 provides a unified cutting edge experience across domains, including science, legal, finance, and coding. This embedding model has consistently held a top spot on the Massive Text Embedding Benchmark (MTEB) Multilingual leaderboard since the experimental launch in March.

2K context

25% off

  • $0.113 $0.15 /M input tokens
  • - /M output tokens

Google: Gemini Nano Banana 2.1 (Image to Image)

Image-To-Image

Nano Banana 2.1 Edit by Google transforms reference images using text instructions, with output resolutions up to 4K and optional video or PDF context.

131.1K context

25% off

  • $1.125 $1.50 /M input tokens
  • $22.50 $30.00 /M output tokens

Google: Gemini Nano Banana 2.1 (Text to Image)

Text-To-Image

Nano Banana 2.1 by Google generates images from text prompts, with output resolutions up to 4K, adjustable aspect ratios, and optional web search grounding.

131.1K context

25% off

  • $1.125 $1.50 /M input tokens
  • $22.50 $30.00 /M output tokens

Google: Nano Banana (Text to Image)

Text-To-Image

Google's famous original image generation and editing model

25% off

  • $0.225 $0.30 /M input tokens
  • $22.50 $30.00 /M output tokens

Google: Nano Banana 2 (Image to Image)

Image-To-Image

Nano Banana 2 is Google's new state-of-the-art image generation and editing model.

25% off

  • $0.375 $0.50 /M input tokens
  • $45.00 $60.00 /M output tokens

Google: Nano Banana 2 (Text to Image)

Text-To-Image

Google Nano Banana 2 (Gemini 3.1 Flash Image) delivers Pro-quality image generation at Flash speed with 512px to 4K resolution support. Features include improved text rendering, character consistency for up to 5 characters, and real-world knowledge integration. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

25% off

  • $0.375 $0.50 /M input tokens
  • $45.00 $60.00 /M output tokens

Google: Nano Banana 2 Lite (Text to Image)

Text-To-Image

Google Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) delivers Pro-quality image generation at Flash speed with 512px to 4K resolution support. Features include improved text rendering, character consistency for up to 5 characters, and real-world knowledge integration.

25% off

  • $0.188 $0.25 /M input tokens
  • $22.50 $30.00 /M output tokens

Google: Nano Banana Pro (Image to Image)

Image-To-Image

Google Nano Banana Pro (Gemini 3.0 Pro Image) Edit enables image editing with 4K-capable output. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

25% off

  • $1.50 $2.00 /M input tokens
  • $90.00 $120.00 /M output tokens

Google: Nano Banana Pro (Text to Image)

Text-To-Image

Google's Nano Banana pro (Gemini 3.0 Pro Image) is a cutting-edge text-to-image model enabling high-res 4K image generation optimized for phones. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

25% off

  • $1.50 $2.00 /M input tokens
  • $90.00 $120.00 /M output tokens

Google: Veo 3.1 (Image to Video)

Image-To-Video

Google Veo 3.1 is an Image-to-Video model that converts images into high-quality videos with native 1080P output for enhanced detail and creative flexibility. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

25% off

  • $0.15 $0.20 /second video

Google: Veo 3.1 (Text to Video)

Text-To-Video

Google Veo 3.1 converts text prompts into videos with synchronized audio at native 1080p for high-quality outputs. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

25% off

  • $0.15 $0.20 /second video

Google: Veo 3.1 (Video Extend)

Video-To-Video

Extend and continue Veo 3.1 videos with smooth motion, preserved style, and strong scene coherence. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

25% off

  • $0.15 $0.20 /second video

OpenAI: Gpt 4

Text generation

OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning capabilities. Training data: up to Sep 2021.

8.2K context

25% off

  • $22.50 $30.00 /M input tokens
  • $45.00 $60.00 /M output tokens

OpenAI: Gpt 4.1 mini

Text generation

GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard instruction evals, 35.8% on MultiChallenge, and 84.1% on IFEval. Mini also shows strong coding ability (e.g., 31.6% on Aider’s polyglot diff benchmark) and vision understanding, making it suitable for interactive applications with tight performance constraints.

1M context

25% off

  • $0.30 $0.40 /M input tokens
  • $1.20 $1.60 /M output tokens

OpenAI: Gpt 4.1 nano

Text generation

For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million token context window, and scores 80.1% on MMLU, 50.3% on GPQA, and 9.8% on Aider polyglot coding – even higher than GPT‑4o mini. It’s ideal for tasks like classification or autocompletion.

1.1M context

25% off

  • $0.075 $0.10 /M input tokens
  • $0.30 $0.40 /M output tokens

OpenAI: Gpt 4o

Text generation

OpenAI ChatGPT 4o is continually updated by OpenAI to point to the current version of GPT-4o used by ChatGPT. It therefore differs slightly from the API version of GPT-4o in that it has additional RLHF. It is intended for research and evaluation. OpenAI notes that this model is not suited for production use-cases as it may be removed or redirected to another model in the future.

128K context

25% off

  • $1.875 $2.50 /M input tokens
  • $7.50 $10.00 /M output tokens

OpenAI: Gpt 5

Text generation

GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like "think hard about this." Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.

400K context

25% off

  • $0.938 $1.25 /M input tokens
  • $7.50 $10.00 /M output tokens

OpenAI: GPT 5 chat

Text generation

GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like "think hard about this." Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.

400 context

25% off

  • $0.938 $1.25 /M input tokens
  • $7.50 $10.00 /M output tokens

OpenAI: Gpt 5 codex

Text generation

GPT-5-Codex is a specialized version of GPT-5 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks. The model supports building projects from scratch, feature development, debugging, large-scale refactoring, and code review. Compared to GPT-5, Codex is more steerable, adheres closely to developer instructions, and produces cleaner, higher-quality code outputs. Reasoning effort can be adjusted with the reasoning.effort parameter Codex integrates into developer environments including the CLI, IDE extensions, GitHub, and cloud tasks. It adapts reasoning effort dynamically—providing fast responses for small tasks while sustaining extended multi-hour runs for large projects. The model is trained to perform structured code reviews, catching critical flaws by reasoning over dependencies and validating behavior against tests. It also supports multimodal inputs such as images or screenshots for UI development and integrates tool use for search, dependency installation, and environment setup. Codex is intended specifically for agentic coding applications.

400K context

25% off

  • $0.938 $1.25 /M input tokens
  • $7.50 $10.00 /M output tokens

OpenAI: gpt 5 mini

Text generation

GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost. GPT-5 Mini is the successor to OpenAI's o4-mini model.

400K context

25% off

  • $0.188 $0.25 /M input tokens
  • $1.50 $2.00 /M output tokens

OpenAI: Gpt 5 nano

Text generation

GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger counterparts, it retains key instruction-following and safety features. It is the successor to GPT-4.1-nano and offers a lightweight option for cost-sensitive or real-time applications.

400K context

25% off

  • $0.037 $0.05 /M input tokens
  • $0.30 $0.40 /M output tokens

OpenAI: Gpt 5 pro

Text generation

GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy in high-stakes use cases. It supports test-time routing features and advanced prompt understanding, including user-specified intent like "think hard about this." Improvements include reductions in hallucination, sycophancy, and better performance in coding, writing, and health-related tasks.

400K context

25% off

  • $11.25 $15.00 /M input tokens
  • $90.00 $120.00 /M output tokens

OpenAI: Gpt 5.1

Text generation

GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning to allocate computation dynamically, responding quickly to simple queries while spending more depth on complex tasks. The model produces clearer, more grounded explanations with reduced jargon, making it easier to follow even on technical or multi-step problems. Built for broad task coverage, GPT-5.1 delivers consistent gains across math, coding, and structured analysis workloads, with more coherent long-form answers and improved tool-use reliability. It also features refined conversational alignment, enabling warmer, more intuitive responses without compromising precision. GPT-5.1 serves as the primary full-capability successor to GPT-5

400K context

25% off

  • $0.938 $1.25 /M input tokens
  • $7.50 $10.00 /M output tokens

OpenAI: Gpt 5.1 chat

Text generation

GPT-5.1 Chat (AKA Instant is the fast, lightweight member of the 5.1 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on harder queries, improving accuracy on math, coding, and multi-step tasks without slowing down typical conversations. The model is warmer and more conversational by default, with better instruction following and more stable short-form reasoning. GPT-5.1 Chat is designed for high-throughput, interactive workloads where responsiveness and consistency matter more than deep deliberation.

128K context

25% off

  • $0.938 $1.25 /M input tokens
  • $7.50 $10.00 /M output tokens

OpenAI: Gpt 5.1 codex

Text generation

GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks. The model supports building projects from scratch, feature development, debugging, large-scale refactoring, and code review. Compared to GPT-5.1, Codex is more steerable, adheres closely to developer instructions, and produces cleaner, higher-quality code outputs. Reasoning effort can be adjusted with the reasoning.effort parameter. Codex integrates into developer environments including the CLI, IDE extensions, GitHub, and cloud tasks. It adapts reasoning effort dynamically—providing fast responses for small tasks while sustaining extended multi-hour runs for large projects. The model is trained to perform structured code reviews, catching critical flaws by reasoning over dependencies and validating behavior against tests. It also supports multimodal inputs such as images or screenshots for UI development and integrates tool use for search, dependency installation, and environment setup. Codex is intended specifically for agentic coding applications.

400K context

25% off

  • $0.938 $1.25 /M input tokens
  • $7.50 $10.00 /M output tokens

OpenAI: Gpt 5.1 codex mini

Text generation

GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex

400K context

25% off

  • $0.188 $0.25 /M input tokens
  • $1.50 $2.00 /M output tokens

OpenAI: GPT Image 2.5 Flare (Image to Image)

Image-To-Image

Precise image editing that changes only what's asked, keeping subject, composition, and background intact, with reference subjects staying recognizable across styles and successive edits.

25% off

  • $3.75 $5.00 /M input tokens
  • $22.50 $30.00 /M output tokens

OpenAI: GPT Image 2.5 Flare (Text to Image)

Text-To-Image

OpenAI's default image model for most applications. Fast, high-quality generation with natural lighting, rich textures, and support for complex layouts including transparent backgrounds.

25% off

  • $3.75 $5.00 /M input tokens
  • $22.50 $30.00 /M output tokens

OpenAI: GPT Image 2.5 Sunburst (Image to Image)

Image-To-Image

Editing built for the tightest control, edits scoped precisely to the instruction, with subject and composition preserved across many rounds of revision.

25% off

  • $3.75 $5.00 /M input tokens
  • $22.50 $30.00 /M output tokens

OpenAI: GPT Image 2.5 Sunburst (Text to Image)

Text-To-Image

OpenAI's precision-focused image model, built for premium visual work, extra fidelity on intricate detail, in exchange for longer generation times.

25% off

  • $3.75 $5.00 /M input tokens
  • $22.50 $30.00 /M output tokens

OpenAI: GPT Images 2 (Image to Image)

Image-To-Image

GPT Image 2, OpenAI's latest image model, is capable of creating extremely detailed images with fine typography.

25% off

  • $3.75 $5.00 /M input tokens
  • $22.50 $30.00 /M output tokens

OpenAI: GPT Images 2 (Text to Image)

Text-To-Image

GPT Image 2, OpenAI's latest image model, is capable of creating extremely detailed images with fine typography.

25% off

  • $3.75 $5.00 /M input tokens
  • $22.50 $30.00 /M output tokens

OpenAI: gpt oss 120b

Text generation

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized to run on a single H100 GPU with native MXFP4 quantization. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.

131.1K context

25% off

  • $0.113 $0.15 /M input tokens
  • $0.45 $0.60 /M output tokens

OpenAI: GPT-5.4

Text generation

GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs, enabling high-context reasoning, coding, and multimodal analysis within the same workflow. The model delivers improved performance in coding, document understanding, tool use, and instruction following. It is designed as a strong default for both general-purpose tasks and software engineering, capable of generating production-quality code, synthesizing information across multiple sources, and executing complex multi-step workflows with fewer iterations and greater token efficiency.

1.1M context

25% off

  • $1.875 $2.50 /M input tokens
  • $11.25 $15.00 /M output tokens

OpenAI: GPT-5.4 Mini

Text generation

GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding, and tool use, while reducing latency and cost for large-scale deployments. The model is designed for production environments that require a balance of capability and efficiency, making it well suited for chat applications, coding assistants, and agent workflows that operate at scale. GPT-5.4 mini delivers reliable instruction following, solid multi-step reasoning, and consistent performance across diverse tasks with improved cost efficiency.

400K context

25% off

  • $0.563 $0.75 /M input tokens
  • $3.375 $4.50 /M output tokens

OpenAI: GPT-5.4 Nano

Text generation

GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency use cases such as classification, data extraction, ranking, and sub-agent execution. The model prioritizes responsiveness and efficiency over deep reasoning, making it ideal for pipelines that require fast, reliable outputs at scale. GPT-5.4 nano is well suited for background tasks, real-time systems, and distributed agent architectures where minimizing cost and latency is essential.

400K context

25% off

  • $0.15 $0.20 /M input tokens
  • $0.938 $1.25 /M output tokens

OpenAI: GPT-5.4 Pro

Text generation

GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K output) with support for text and image inputs. Optimized for step-by-step reasoning, instruction following, and accuracy, GPT-5.4 Pro excels at agentic coding, long-context workflows, and multi-step problem solving.

1.1M context

25% off

  • $22.50 $30.00 /M input tokens
  • $135.00 $180.00 /M output tokens

OpenAI: GPT-5.6 Luna

Text generation

GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for its price tier.

1.1M context

25% off

  • $0.15 $0.20 /M input tokens
  • $0.90 $1.20 /M output tokens

OpenAI: GPT-5.6 Sol

Text generation

GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks and long-horizon problem solving.

1.1M context

25% off

  • $3.75 $5.00 /M input tokens
  • $22.50 $30.00 /M output tokens

OpenAI: GPT-5.6 Terra

Text generation

GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic tasks where capability and cost need to be balanced, offering strong performance at roughly half the cost of Sol.

1.1M context

25% off

  • $1.50 $2.00 /M input tokens
  • $9.00 $12.00 /M output tokens

OpenAI: GPT-6 Astra

Text generation

GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon agentic tasks that involve computer and browser use.

1.1M context

25% off

  • $7.50 $10.00 /M input tokens
  • $37.50 $50.00 /M output tokens

OpenAI: GPT-6 Luna

Text generation

GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic tasks, and at higher reasoning effort it can take on complex software engineering and computer-use tasks that previously called for a Sol-tier model. It shares the GPT-6 family's gains in factual reliability and its clearer, more concise communication style.

1.1M context

25% off

  • $0.075 $0.10 /M input tokens
  • $0.375 $0.50 /M output tokens

OpenAI: GPT-6 Sol

Text generation

GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional work, agentic coding, business workflow automation, and computer use, and is particularly strong at long-horizon software engineering tasks in real codebases. It approaches Astra-level factual reliability at a much lower cost and shares Astra's clearer, more concise communication style in technical and coding conversations.

1.1M context

25% off

  • $1.50 $2.00 /M input tokens
  • $7.50 $10.00 /M output tokens

OpenAI: GPT-6.1 Sol

Text generation

GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional work, and multi-step business workflow automation, and approaches Astra-level results on these tasks at a much lower cost. Compared with GPT-6 Sol, it makes fewer factual errors and is more reliable at respecting explicit restrictions and user intent during agentic tasks.

1.1M context

25% off

  • $1.50 $2.00 /M input tokens
  • $7.50 $10.00 /M output tokens

OpenAI: O1

Text generation

The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learning to reason using chain of thought. The o1 models are optimized for math, science, programming, and other STEM-related tasks. They consistently exhibit PhD-level accuracy on benchmarks in physics, chemistry, and biology.

200K context

25% off

  • $11.25 $15.00 /M input tokens
  • $45.00 $60.00 /M output tokens

OpenAI: O1 Mini

Text generation

The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 models are optimized for math, science, programming, and other STEM-related tasks. They consistently exhibit PhD-level accuracy on benchmarks in physics, chemistry, and biology.

200K context

25% off

  • $0.907 $1.21 /M input tokens
  • $3.63 $4.84 /M output tokens

OpenAI: O3 Mini

Text generation

OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the reasoning_effort parameter, which can be set to "high", "medium", or "low" to control the thinking time of the model. The default is "medium". OpenRouter also offers the model slug openai/o3-mini-high to default the parameter to "high". The model features three adjustable reasoning effort levels and supports key developer capabilities including function calling, structured outputs, and streaming, though it does not include vision processing capabilities. The model demonstrates significant improvements over its predecessor, with expert testers preferring its responses 56% of the time and noting a 39% reduction in major errors on complex questions. With medium reasoning effort settings, o3-mini matches the performance of the larger o1 model on challenging reasoning evaluations like AIME and GPQA, while maintaining lower latency and cost.

200K context

25% off

  • $0.907 $1.21 /M input tokens
  • $3.63 $4.84 /M output tokens

OpenAI: O4 Mini

Text generation

OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning and coding performance across benchmarks like AIME (99.5% with Python) and SWE-bench, outperforming its predecessor o3-mini and even approaching o3 in some domains. Despite its smaller size, o4-mini exhibits high accuracy in STEM tasks, visual problem solving (e.g., MathVista, MMMU), and code editing. It is especially well-suited for high-throughput scenarios where latency or cost is critical. Thanks to its efficient architecture and refined reinforcement learning training, o4-mini can chain tools, generate structured outputs, and solve multi-step tasks with minimal delay—often in under a minute.

200K context

25% off

  • $0.907 $1.21 /M input tokens
  • $3.63 $4.84 /M output tokens

xAI: Grok 4.2 Non Reasoning

Text generation

Grok 4.20 is xAI's newest flagship model with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering consistently precise and truthful responses.

2M context

20% off

  • $1.00 $1.25 /M input tokens
  • $2.00 $2.50 /M output tokens

xAI: Grok 4.2 Reasoning

Text generation

Grok 4.20 is xAI's newest flagship model with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering consistently precise and truthful responses.

2M context

20% off

  • $1.00 $1.25 /M input tokens
  • $2.00 $2.50 /M output tokens

xAI: Grok 4.3

Text generation

Grok 4.3 is a reasoning model from xAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual accuracy. Reasoning is always active and cannot be disabled or configured by effort level. It supports a 1 million token context window with no output token limit, making it well-suited for long-document analysis, deep research, and multi-step agentic tasks. Pricing is tiered: requests exceeding 200k total tokens are billed at a higher rate.

1M context

20% off

  • $1.00 $1.25 /M input tokens
  • $2.00 $2.50 /M output tokens

xAI: Grok 4.5

Text generation

Grok 4.5 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.

500K context

20% off

  • $1.60 $2.00 /M input tokens
  • $4.80 $6.00 /M output tokens

xAI: Grok 4.6

Text generation

Grok 4.6 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.

500K context

20% off

  • $1.60 $2.00 /M input tokens
  • $4.80 $6.00 /M output tokens

xAI: Grok Build 0.1

Text generation

Grok Build 0.1 is xAI’s fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs with text output, and is optimized for interactive coding agents, tool use, and multi-step development tasks. The model powers xAI’s Grok Build CLI and features a 256K context window with no text output limit, making it well suited for long-horizon coding and automation workflows. Currently in early access.

256K context

20% off

  • $0.80 $1.00 /M input tokens
  • $1.60 $2.00 /M output tokens

xAI: Grok Imagine Image Quality (Image to Image)

Image-To-Image

Grok Imagine Pro is an advanced AI model from xAI that creates high-quality visuals from text prompts and allows you to edit or analyze existing images.

20% off

  • $0.04 $0.05 /generation

xAI: Grok Imagine Image Quality (Text to Image)

Text-To-Image

Grok Imagine Pro is an advanced AI model from xAI that creates high-quality visuals from text prompts and allows you to edit or analyze existing images.

20% off

  • $0.04 $0.05 /generation

These are provider-level public discounts. Personal or team pricing overrides are not included, and prices may change as provider offers are updated.