Generated from the live model registry. Last synced 2026-10-28 (UTC). The model picker is source of truth if anything drifts.
How to read this page
| Column | Meaning |
|---|---|
| Model | Name in the model picker |
| Note | One-line summary |
| Context | How much the agent can read at once |
| In / Out | At-cost USD per 1M input / output tokens |
| Trusted | OK for Google-connected agents |
By provider
Anthropic (14)
Anthropic (14)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| Claude Opus 4.1 | Claude Opus 4.1 is an updated version of Anthropic s flagship model, offering improved performance… | 200K | $15 | $75 | Yes |
| Claude Fable 5 | Claude Fable 5 is a Mythos-class model with safeguards. It can handle long-running, complex, and… | 1M | $10 | $50 | |
| Claude Fable 5.1 | Claude Fable 5.1 improves on Fable 5 across long-running agentic coding, knowledge work, and… | 1M | $10 | $50 | |
| Claude Opus 4.8 (Fast) | Opus 4.8 is a focused upgrade to Opus 4.7 and is Anthropic’s best generally available model for… | 1M | $10 | $50 | |
| Claude Opus 5 (Fast) | Claude Opus 5 is the latest model in Anthropic’s Opus family and a step-change improvement over… | 1M | $10 | $50 | |
| Claude Opus 5.5 (Fast) | Claude Opus 5.5 is a step-change improvement over Opus 5 for agentic coding, long-running agentic… | 1M | $8 | $40 | |
| Claude Opus 4.5 | Claude Opus 4.5 is Anthropic s latest model in the Opus series, meant for demanding reasoning… | 200K | $5 | $25 | Yes |
| Claude Opus 4.8 | Opus 4.8 is a focused upgrade to Opus 4.7 and is Anthropic’s best generally available model for… | 1M | $5 | $25 | Yes |
| Claude Opus 5 | Claude Opus 5 is the latest model in Anthropic’s Opus family and a step-change improvement over… | 1M | $5 | $25 | Yes |
| Claude Opus 5.5 | Claude Opus 5.5 is a step-change improvement over Opus 5 for agentic coding, long-running agentic… | 1M | $4 | $20 | Yes |
| Claude Sonnet 5 | Sonnet 5 is an upgrade to Sonnet 4.6, with gains across agentic coding and professional work. It… | 1M | $2 | $10 | Yes |
| Claude Sonnet 5.5 | Claude Sonnet 5.5 is a step-change improvement over Sonnet 5 for well-scoped everyday work like… | 1M | $2 | $10 | Yes |
| Claude Haiku 4.5 | Claude Haiku 4.5 matches Sonnet 4’s performance on coding, computer use, and agent tasks at… | 200K | $1 | $5 | Yes |
| Claude Haiku 5.5 | Claude Haiku 5.5 brings adaptive reasoning to Anthropic s low-cost Haiku family for everyday… | 1M | $0.1 | $0.5 | Yes |
OpenAI (88)
OpenAI (88)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| GPT 5.4 Pro | GPT-5.4 Pro uses more compute to think harder and provide consistently better answers. It’s… | 1.1M | $30 | $180 | Yes |
| GPT 5.5 Pro | Reasoning model, 1M+ context. | 1.1M | $30 | $180 | |
| GPT-4 | OpenAI’s flagship model, GPT-4 is a large-scale multimodal language model capable of solving… | 8K | $30 | $60 | Yes |
| GPT 5.2 | Version of GPT-5.2 that produces smarter and more precise responses. | 400K | $21 | $168 | |
| GPT-6 Astra (Fast) | GPT-6 Astra is OpenAI’s most capable model for complex reasoning, coding, computer use, research… | 1.1M | $20 | $100 | |
| o3 Pro | The o-series of models are trained with reinforcement learning to think before they answer and… | 200K | $20 | $80 | |
| GPT-5 pro | GPT-5 pro uses more compute to think harder and provide consistently better answers. Since GPT-5… | 400K | $15 | $120 | |
| o1 | o1 is OpenAI’s flagship reasoning model, designed for complex problems that require deep thinking… | 200K | $15 | $60 | |
| GPT 5.5 (Fast) | GPT-5.5 understands what you re trying to do faster and can carry more of the work itself. It… | 1M | $12.5 | $75 | |
| GPT-4 Turbo | The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and… | 128K | $10 | $30 | |
| GPT-6 Astra | GPT-6 Astra is OpenAI’s most capable model for complex reasoning, coding, computer use, research… | 1.1M | $10 | $50 | Yes |
| GPT-6 Astra Pro | GPT-6 Astra Pro is the same underlying model as GPT-6 Astra, served with reasoning.mode set to pro… | 1.1M | $10 | $50 | Yes |
| GPT 5.6 Sol (Fast) | GPT-5.6 Sol is the flagship of OpenAI’s GPT-5.6 series, its most capable model for long-horizon… | 1.1M | $8 | $40 | |
| GPT 5.4 (Fast) | GPT-5.4 is OpenAI’s best general-purpose model, part of the GPT-5 flagship model family. It’s… | 1.1M | $5 | $30 | |
| GPT 5.5 | GPT-5.5 understands what you re trying to do faster and can carry more of the work itself. It… | 272K | $5 | $30 | Yes |
| GPT Chat Latest | GPT Chat Latest points to OpenAI’s stable API alias chat-latest that always resolves to the latest… | 400K | $5 | $30 | |
| GPT Image 1 | Standard model. | - | $5 | $40 | |
| GPT Image 2 | Standard model. | - | $5 | $30 | |
| GPT-4o (2024-05-13) | GPT-4o (“o” for “omni”) is OpenAI’s latest AI model, supporting both text and image inputs with… | 128K | $5 | $15 | Yes |
| GPT-4o (Fast) | GPT-4o from OpenAI has broad general knowledge and domain expertise allowing it to follow complex… | 128K | $4.25 | $17 | |
| GPT 5.6 Sol | GPT-5.6 Sol is the flagship of OpenAI’s GPT-5.6 series, its most capable model for long-horizon… | 272K | $4 | $20 | Yes |
| GPT 5.6 Terra (Fast) | GPT-5.6 Terra is a balanced GPT-5.6 model for everyday work, with performance comparable to the… | 1.1M | $4 | $24 | |
| GPT-5.6 Sol Pro | GPT-5.6 Sol Pro is the same underlying model as GPT-5.6 Sol, served with reasoning.mode set to pro… | 1.1M | $4 | $20 | Yes |
| GPT-6 Sol (Fast) | GPT-6 Sol is OpenAI’s reasoning model for complex coding and agentic workflows. It accepts text… | 1.1M | $4 | $20 | |
| GPT-6.1 Sol (Fast) | GPT-6.1 Sol is OpenAI’s reasoning model for complex coding, computer use, and professional work… | 1.1M | $4 | $20 | |
| GPT 5.2 (Fast) | GPT-5.2 is OpenAI’s best general-purpose model, part of the GPT-5 flagship model family. It’s… | 400K | $3.5 | $28 | |
| GPT 5.3 Codex (Fast) | GPT-5.3-Codex advances both the frontier coding performance of GPT-5.2-Codex and the reasoning and… | 400K | $3.5 | $28 | |
| GPT-4.1 (Fast) | GPT 4.1 is OpenAI’s flagship model for complex tasks. It is well suited for problem solving across… | 1M | $3.5 | $14 | |
| o3 (Fast) | OpenAI’s o3 is their most powerful reasoning model, setting new state-of-the-art benchmarks in… | 200K | $3.5 | $14 | |
| GPT-3.5 Turbo 16k | This model offers four times the context length of gpt-3.5-turbo, allowing it to support… | 16K | $3 | $4 | Yes |
| GPT 5.1 Thinking (Fast) | An upgraded version of GPT-5 that adapts thinking time more precisely to the question to spend… | 400K | $2.5 | $20 | |
| GPT 5.4 | GPT-5.4 is OpenAI’s best general-purpose model, part of the GPT-5 flagship model family. It’s… | 272K | $2.5 | $15 | Yes |
| GPT Audio | The gpt-audio model is OpenAI’s first generally available audio model. The new snapshot features… | 128K | $2.5 | $10 | |
| GPT Image 1 Mini | Standard model. | - | $2.5 | $32 | |
| GPT-4o | GPT-4o from OpenAI has broad general knowledge and domain expertise allowing it to follow complex… | 128K | $2.5 | $10 | Yes |
| GPT-4o (2024-08-06) | The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the… | 128K | $2.5 | $10 | Yes |
| GPT-4o (2024-11-20) | The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural… | 128K | $2.5 | $10 | |
| GPT-5 (Fast) | GPT-5 is OpenAI’s flagship language model that excels at complex reasoning, broad real-world… | 400K | $2.5 | $20 | |
| GPT 5.6 Terra | GPT-5.6 Terra is a balanced GPT-5.6 model for everyday work, with performance comparable to the… | 272K | $2 | $12 | Yes |
| GPT-4.1 | GPT 4.1 is OpenAI’s flagship model for complex tasks. It is well suited for problem solving across… | 1M | $2 | $8 | Yes |
| GPT-5.6 Terra Pro | GPT-5.6 Terra Pro is the same underlying model as GPT-5.6 Terra, served with reasoning.mode set to… | 1.1M | $2 | $12 | Yes |
| GPT-6 Sol | GPT-6 Sol is OpenAI’s reasoning model for complex coding and agentic workflows. It accepts text… | 1.1M | $2 | $10 | Yes |
| GPT-6 Sol Pro | GPT-6 Sol Pro is the same underlying model as GPT-6 Sol, served with reasoning.mode set to pro for… | 1.1M | $2 | $10 | Yes |
| GPT-6.1 Sol | GPT-6.1 Sol is OpenAI’s reasoning model for complex coding, computer use, and professional work… | 1.1M | $2 | $10 | Yes |
| GPT-6.1 Sol Pro | GPT-6.1 Sol Pro is the same underlying model as GPT-6.1 Sol, served with reasoning.mode set to pro… | 1.1M | $2 | $10 | Yes |
| GPT-6.1 Terra (Fast) | GPT-6.1 Terra is OpenAI s model for visual reasoning, precise computer use, and natural writing… | 1.1M | $2 | $10 | |
| o3 | OpenAI’s o3 is their most powerful reasoning model, setting new state-of-the-art benchmarks in… | 200K | $2 | $8 | |
| GPT 5.2 | GPT-5.2 is OpenAI’s best general-purpose model, part of the GPT-5 flagship model family. It’s… | 400K | $1.75 | $14 | Yes |
| GPT 5.2 Codex | GPT-5.2-Codex is a version of GPT-5.2 further optimized for agentic coding in Codex, including… | 400K | $1.75 | $14 | Yes |
| GPT 5.3 Codex | GPT-5.3-Codex advances both the frontier coding performance of GPT-5.2-Codex and the reasoning and… | 400K | $1.75 | $14 | Yes |
| GPT-5.2 Chat | GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for… | 128K | $1.75 | $14 | Yes |
| GPT 5.4 Mini (Fast) | GPT-5.4 Mini brings the strengths of GPT-5.4 to a faster, more efficient model designed for… | 400K | $1.5 | $9 | |
| GPT 5.1 Codex Max | GPT-5.1-Codex-Max is purpose-built for agentic coding. | 400K | $1.25 | $10 | Yes |
| GPT 5.1 Thinking | An upgraded version of GPT-5 that adapts thinking time more precisely to the question to spend… | 400K | $1.25 | $10 | |
| GPT-5 | GPT-5 is OpenAI’s flagship language model that excels at complex reasoning, broad real-world… | 400K | $1.25 | $10 | Yes |
| GPT-5-Codex | GPT-5-Codex is a version of GPT-5 optimized for agentic coding tasks in Codex or similar… | 400K | $1.25 | $10 | |
| GPT-5.1 | GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose… | 400K | $1.25 | $10 | Yes |
| GPT-5.1-Codex | GPT-5.1-Codex is a version of GPT-5.1 optimized for agentic coding tasks in Codex or similar… | 400K | $1.25 | $10 | Yes |
| o3 Mini High | OpenAI o3-mini-high is the same model as o3-mini with reasoning_effort set to high. o3-mini is a… | 200K | $1.1 | $4.4 | |
| o3-mini | o3-mini is OpenAI’s most recent small reasoning model, providing high intelligence at the same… | 200K | $1.1 | $4.4 | |
| o4 Mini High | OpenAI o4-mini-high is the same model as o4-mini with reasoning_effort set to high. OpenAI o4-mini… | 200K | $1.1 | $4.4 | |
| o4-mini | OpenAI’s o4-mini delivers fast, cost-efficient reasoning with exceptional performance for its… | 200K | $1.1 | $4.4 | |
| GPT-3.5 Turbo (older v0613) | GPT-3.5 Turbo is OpenAI’s fastest model. It can understand and generate natural language or code… | 4K | $1 | $2 | Yes |
| GPT-6.1 Terra | GPT-6.1 Terra is OpenAI s model for visual reasoning, precise computer use, and natural writing… | 1.1M | $1 | $5 | Yes |
| GPT-6.1 Terra Pro | GPT-6.1 Terra Pro is the same underlying model as GPT-6.1 Terra, served with reasoning.mode set to… | 1.1M | $1 | $5 | Yes |
| GPT 5.4 Mini | GPT-5.4 Mini brings the strengths of GPT-5.4 to a faster, more efficient model designed for… | 400K | $0.75 | $4.5 | Yes |
| GPT-4.1 mini (Fast) | GPT 4.1 mini provides a balance between intelligence, speed, and cost that makes it an attractive… | 1M | $0.7 | $2.8 | |
| GPT Audio Mini | A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more… | 128K | $0.6 | $2.4 | |
| GPT-5 mini (Fast) | GPT-5 mini is a cost optimized model that excels at reasoning/chat tasks. It offers an optimal… | 400K | $0.45 | $3.6 | |
| GPT 5.6 Luna (Fast) | GPT-5.6 Luna is a fast, affordable GPT-5.6 model that brings strong capability at the lowest cost… | 1.1M | $0.4 | $2.4 | |
| GPT-4.1 mini | GPT 4.1 mini provides a balance between intelligence, speed, and cost that makes it an attractive… | 1M | $0.4 | $1.6 | Yes |
| GPT 5.1 Codex Mini | GPT-5.1 Codex mini is a smaller, faster, and cheaper version of GPT-5.1 Codex. | 400K | $0.25 | $2 | Yes |
| GPT-4o mini (Fast) | GPT-4o mini from OpenAI is their most advanced and cost-efficient small model. It is multi-modal… | 128K | $0.25 | $1 | |
| GPT-5 mini | GPT-5 mini is a cost optimized model that excels at reasoning/chat tasks. It offers an optimal… | 400K | $0.25 | $2 | Yes |
| GPT 5.4 Nano | GPT-5.4 Nano is designed for tasks where speed and cost matter most like classification, data… | 400K | $0.2 | $1.25 | Yes |
| GPT 5.6 Luna | GPT-5.6 Luna is a fast, affordable GPT-5.6 model that brings strong capability at the lowest cost… | 272K | $0.2 | $1.2 | Yes |
| GPT-5.6 Luna Pro | GPT-5.6 Luna Pro is the same underlying model as GPT-5.6 Luna, served with reasoning.mode set to… | 1.1M | $0.2 | $1.2 | Yes |
| GPT-6 Luna (Fast) | GPT-6 Luna is OpenAI’s efficient reasoning model for focused, high-volume tasks. It accepts text… | 1.1M | $0.2 | $1 | |
| GPT OSS 120B | Extremely capable general-purpose LLM with strong, controllable reasoning capabilities | 131K | $0.15 | $0.6 | Yes |
| GPT OSS Safeguard 120B | GPT OSS Safeguard 120B is OpenAI s open-weight safety model for content moderation and guardrail… | 128K | $0.15 | $0.6 | |
| GPT-4o mini | GPT-4o mini from OpenAI is their most advanced and cost-efficient small model. It is multi-modal… | 128K | $0.15 | $0.6 | Yes |
| GPT-4o-mini (2024-07-18) | GPT-4o mini is OpenAI’s newest model after GPT-4 Omni, supporting both text and image inputs with… | 128K | $0.15 | $0.6 | |
| GPT-4.1 nano | GPT-4.1 nano is the fastest, most cost-effective GPT 4.1 model. | 1M | $0.1 | $0.4 | Yes |
| GPT-6 Luna | GPT-6 Luna is OpenAI’s efficient reasoning model for focused, high-volume tasks. It accepts text… | 1.1M | $0.1 | $0.5 | Yes |
| GPT-6 Luna Pro | GPT-6 Luna Pro is the same underlying model as GPT-6 Luna, served with reasoning.mode set to pro… | 1.1M | $0.1 | $0.5 | Yes |
| GPT OSS Safeguard 20B | OpenAI’s first open weight reasoning model specifically trained for safety classification tasks… | 131K | $0.075 | $0.3 | Yes |
| GPT-5 nano | GPT-5 nano is a high throughput model that excels at simple instruction or classification tasks. | 400K | $0.05 | $0.4 | Yes |
| GPT OSS 20B | A compact, open-weight language model optimized for low-latency and resource-constrained… | 131K | $0.018 | $0.09 | Yes |
Google (23)
Google (23)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| Gemini 3.1 Pro Preview | This model improves upon Gemini 2.5 Pro and is catered towards challenging tasks, especially those… | 1M | $2 | $12 | Yes |
| Gemini 3.1 Pro Preview Custom Tools | Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection… | 1M | $2 | $12 | |
| Gemini 4 Argon | Gemini 4 Argon is Google s multimodal reasoning model, supporting text, image, and file inputs… | 1M | $2 | $10 | Yes |
| Nano Banana Pro (Gemini 3 Pro Image) | Nano Banana Pro is Google s most advanced image-generation and editing model, built on Gemini 3… | 66K | $2 | $12 | Yes |
| Gemini 3.5 Flash | Google’s latest model, highly optimized for coding proficiency and parallel agentic execution… | 1M | $1.5 | $9 | Yes |
| Nano Banana 2.1 | Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google’s image generation and editing model on the… | 66K | $1.5 | $7.5 | |
| Gemini 2.5 Pro | Gemini 2.5 Pro is our most advanced reasoning Gemini model, capable of solving complex problems… | 1M | $1.25 | $10 | |
| Gemini 2.5 Pro Preview 06-05 | Gemini 2.5 Pro is Google s state-of-the-art AI model designed for advanced reasoning, coding… | 1M | $1.25 | $10 | Yes |
| Gemini 3.8 Flash | Gemini 3.8 Flash is the high-efficiency, cost-effective powerhouse of the Gemini 3 family. It… | 1M | $0.825 | $4.12 | Yes |
| Gemini 3.6 Flash | Gemini 3.6 Flash delivers higher quality across coding, agentic workflows, and web development… | 1M | $0.75 | $3.75 | Yes |
| Gemini 3.7 Flash | Gemini 3.7 Flash is the high-efficiency, cost-effective powerhouse of the Gemini 3 family. It… | 1M | $0.75 | $3.75 | Yes |
| Gemini 3 Flash | Google’s most intelligent model built for speed, combining frontier intelligence with superior… | 1M | $0.5 | $3 | |
| Gemini 3 Flash Preview | Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows… | 1M | $0.5 | $3 | Yes |
| Nano Banana 2 | Gemini 3.1 Flash Image, a.k.a. “Nano Banana 2,” is Google s latest state of the art image… | - | $0.5 | $60 | |
| Gemini 2.5 Flash | Gemini 2.5 Flash is a thinking model that offers great, well-rounded capabilities. It is designed… | 1M | $0.3 | $2.5 | |
| Gemini 3.5 Flash Lite | Gemini 3.5 Flash Lite features upgraded agentic capabilities, making the model ideal for subagents… | 1M | $0.3 | $2.5 | Yes |
| Gemini 3.1 Flash Lite | Gemini 3.1 Flash Lite outperforms 2.5 Flash Lite on overall quality and lands close to 2.5 Flash… | 1M | $0.25 | $1.5 | Yes |
| Gemini 3.1 Flash Lite Preview | Gemini 3.1 Flash Lite Preview is Google’s high-efficiency model optimized for high-volume use… | 1M | $0.25 | $1.5 | |
| Gemma 4 31B IT | Gemma 4 31B is engineered to tackle the most demanding enterprise workloads and complex reasoning… | 262K | $0.2 | $0.4 | Yes |
| Gemini 2.5 Flash Lite | Gemini 2.5 Flash-Lite is a balanced, low-latency model with configurable thinking budgets and tool… | 1M | $0.1 | $0.4 | |
| Google Gemma 4 26B A4B | Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling… | 262K | $0.09 | $0.3 | Yes |
| Gemma 3 27B | Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles… | 131K | $0.08 | $0.35 | Yes |
| Gemma 3 12B | Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles… | 131K | $0.05 | $0.15 | Yes |
xAI (6)
xAI (6)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| Grok 4.5 | Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM. | 500K | $2 | $6 | Yes |
| Grok 4.6 | Grok 4.6 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM… | 500K | $2 | $6 | Yes |
| Grok 4.7 | Grok 4.7 is SpaceXAI’s flagship model for coding, agentic tasks, and knowledge work, succeeding… | 500K | $2 | $6 | Yes |
| Grok 4.20 | Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling… | 2M | $1.25 | $2.5 | Yes |
| Grok 4.3 | Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output… | 1M | $1.25 | $2.5 | Yes |
| Grok Build 0.1 | Grok Build 0.1 is SpaceXAI s fast coding model trained specifically for agentic software… | 256K | $1 | $2 | Yes |
DeepSeek (19)
DeepSeek (19)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| DeepSeek-R1 | DeepSeek-R1 provides customers a state-of-the-art reasoning model, optimized for general reasoning… | 64K | $1.35 | $5.4 | |
| DeepSeek V4 Pro | DeepSeek-V4 series incorporate several key upgrades in architecture and optimization: (1) a hybrid… | 1M | $0.955 | $1.91 | Yes |
| DeepSeek V4 Pro 0813 | This is the 8/13 updated weights version of DeepSeek V4 Pro. | 1M | $0.66 | $1.98 | Yes |
| DeepSeek V3.2 Thinking | DeepSeek-V3.2 from DeepSeek harmonizes high computational efficiency with superior reasoning and… | 128K | $0.62 | $1.85 | |
| DeepSeek V4.1 Flash 1017 Fast | Higher-throughput variant of DeepSeek V4.1 Flash 1017 served by Baseten for multimodal reasoning… | 1M | $0.6 | $2.4 | |
| DeepSeek V4.1 Flash Fast | Higher-throughput variant of DeepSeek V4.1 Flash for responsive coding, reasoning, and agentic… | 1M | $0.6 | $2.4 | |
| R1 0528 | May 28th update to the original DeepSeek R1 Performance on par with OpenAI o1, but open-sourced… | 164K | $0.5 | $2.15 | Yes |
| DeepSeek V3 0324 | DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship… | 164K | $0.29 | $1.14 | Yes |
| DeepSeek V3.2 | DeepSeek-V3.2 from DeepSeek harmonizes high computational efficiency with superior reasoning and… | 164K | $0.28 | $0.42 | Yes |
| DeepSeek V3.1 Terminus | DeepSeek-V3.1 Terminus is an update to DeepSeek V3.1 that maintains the model’s original… | 164K | $0.27 | $1 | Yes |
| DeepSeek V3.2 Exp | DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate… | 164K | $0.27 | $0.41 | Yes |
| DeepSeek V3 | DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following… | 128K | $0.257 | $1.03 | Yes |
| DeepSeek V3.1 | DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both… | 164K | $0.25 | $0.95 | Yes |
| DeepSeek V3.1 | DeepSeek-V3.1 is post-trained on the top of DeepSeek-V3.1-Base, which is built upon the original… | 164K | $0.25 | $0.95 | |
| DeepSeek V4 Flash Vision Exp | DeepSeek-V4-Flash-Vision-Exp is an experimental multimodal model that combines the agentic… | 1M | $0.216 | $0.647 | Yes |
| DeepSeek V4.1 Flash 1017 | DeepSeek V4.1 Flash 1017 served by Fireworks for multimodal reasoning, coding, tool calling, and… | 1M | $0.15 | $0.6 | Yes |
| DeepSeek V4.1 Flash | DeepSeek V4.1 Flash is an AI model from DeepSeek designed for fast, efficient multimodal… | 1M | $0.14 | $0.42 | Yes |
| DeepSeek V4 Flash 0731 | Reasoning model, trusted for Google-connected agents, 1M+ context. | 1M | $0.119 | $0.238 | Yes |
| DeepSeek V4 Flash | Reasoning model, trusted for Google-connected agents, 1M+ context. | 1M | $0.091 | $0.182 | Yes |
Moonshot (11)
Moonshot (11)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| Kimi K3 Fast | Fast version of Kimi s flagship model for long-horizon coding and end-to-end knowledge work, with… | 1M | $4.5 | $22.5 | |
| Kimi K3.1 Pro Highspeed | Kimi K3.1 Pro Highspeed is the high-speed variant of Moonshot AI s frontier Kimi K3.1 Pro model… | 1M | $4 | $20 | |
| Kimi K3.1 Pro | Kimi K3.1 Pro is a frontier model from Moonshot AI for complex reasoning, coding, and agentic… | 1M | $2 | $10 | Yes |
| Kimi K2.7 Code High Speed | Kimi K2.7 Code HighSpeed is the high-speed version of Kimi K2.7 Code, the same model as Kimi K2.7… | 262K | $1.9 | $8 | |
| Kimi K2.6 | Kimi K2.6 demonstrates particularly strong performance in long-horizon coding tasks and produces… | 262K | $0.65 | $3.41 | Yes |
| Kimi K2 0905 | Kimi K2 0905 is the September update of Kimi K2 0711. It is a large-scale Mixture-of-Experts (MoE)… | 262K | $0.6 | $2.5 | Yes |
| Kimi K2 Thinking | Kimi K2 Thinking is Moonshot AI s most advanced open reasoning model to date, extending the K2… | 262K | $0.6 | $2.5 | Yes |
| Kimi K2 Instruct | Kimi K2 is a state-of-the-art mixture-of-experts (MoE) language model with 32 billion activated… | 131K | $0.57 | $2.3 | Yes |
| Kimi K2.7 Code | Kimi-K2.7-Code is a coding model from Moonshot AI. It has improved coding & agent performance over… | 262K | $0.56 | $3.1 | Yes |
| Kimi K2.5 | kimi-k2.5 is Kimi’s most versatile model to date, featuring a native multimodal architecture that… | 262K | $0.5 | $2.5 | Yes |
| Kimi K3 | Kimi s flagship model for long-horizon coding and end-to-end knowledge work, with a 1M-token… | 1M | $0.179 | $20 | Yes |
Qwen (50)
Qwen (50)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| Qwen 3.8 Max Prime | Qwen 3.8 Max Prime is the high-speed edition of Qwen 3.8 Max, retaining its 2.4-trillion-parameter… | 1M | $4 | $12 | |
| Qwen 3.8 Max | Qwen 3.8 Max is a 2.4-trillion-parameter MoE model delivering a comprehensive leap in coding and… | 1M | $2 | $6 | |
| Qwen3.8 2.4T A95B | Qwen 3.8 Max is a 2.4-trillion-parameter MoE model delivering a comprehensive leap in coding and… | 1M | $2 | $6 | Yes |
| Qwen3.8 Max 0902 | Qwen3.8-Max-0902 is an upgraded snapshot of qwen3.8-max. | 1M | $2 | $6 | |
| Qwen 3.7 Max | Qwen3.7 is a next-generation flagship model designed for the agent-centric era, with its core… | 1M | $1.48 | $4.42 | |
| Qwen 3 Max Thinking | Compared with the snapshot as of September 23, 2025, the Qwen-3 series Max model in this release… | 262K | $1.2 | $6 | |
| Qwen3.5 397B A17B | The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that… | 262K | $0.5 | $3.6 | Yes |
| Qwen 3.6 27B | The Qwen3.6 35B-A3B native vision-language model is built on a hybrid architecture that integrates… | 262K | $0.45 | $2.7 | Yes |
| Qwen3 235B A22B Thinking 2507 | Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language… | 131K | $0.45 | $3.5 | Yes |
| Qwen 3.5 Plus | The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that… | 1M | $0.4 | $2.4 | |
| Qwen2.5 72B Instruct | Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following… | 33K | $0.36 | $0.4 | Yes |
| Qwen 3.6 Plus | The Qwen3.6 native vision-language Plus series models demonstrate exceptional performance on par… | 1M | $0.325 | $1.95 | |
| Qwen 3.7 Plus | Among the Qwen3.7 series, the cost-effective Plus model builds on its text capabilities while… | 1M | $0.32 | $1.28 | |
| Qwen3 Coder 480B A35B Instruct | Mixture-of-experts LLM with advanced coding and reasoning capabilities | 262K | $0.3 | $1 | Yes |
| Qwen3.5 Plus 2026-04-20 | Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts… | 1M | $0.3 | $1.8 | |
| Qwen3 VL 30B A3B Thinking | Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual… | 131K | $0.29 | $1 | Yes |
| Qwen-Plus | Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced… | 1M | $0.26 | $0.78 | |
| Qwen3.5 Plus 2026-02-15 | The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that… | 1M | $0.26 | $1.56 | |
| Qwen3.5-122B-A10B | The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that… | 262K | $0.26 | $2.08 | Yes |
| Qwen3.5-27B | The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism… | 262K | $0.26 | $2.6 | Yes |
| Qwen3 VL 8B Instruct | Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for… | 131K | $0.25 | $0.75 | Yes |
| Qwen3 235B A22B | Standard model, 262K context. | 262K | $0.22 | $0.88 | |
| Qwen3 VL 235B A22B Instruct | Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation… | 131K | $0.21 | $1.9 | Yes |
| Qwen3 VL 235B A22B Instruct | The Qwen3 series VL models has been comprehensively upgraded in areas such as visual coding and… | 262K | $0.2 | $0.88 | |
| Qwen3 Coder Flash | Qwen3 Coder Flash is Alibaba’s fast and cost efficient version of their proprietary Qwen3 Coder… | 1M | $0.195 | $0.975 | |
| Qwen3.6 Flash | Qwen3.6 Flash is a fast, efficient language model from Alibaba’s Qwen 3.6 series. It supports… | 1M | $0.188 | $1.12 | |
| Qwen3.5-9B | Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong… | 262K | $0.17 | $0.25 | Yes |
| Qwen 3 32B | Qwen3-32B is a world-class model with comparable quality to DeepSeek R1 while outperforming… | 128K | $0.15 | $0.6 | |
| Qwen 3 Coder 30B A3B Instruct | Efficient coding specialist balancing performance with cost-effectiveness for daily development… | 262K | $0.15 | $0.6 | |
| Qwen 3.8 Flash | Qwen3.8-Flash is Qwen s fast, cost-efficient multimodal model, combining advanced reasoning and… | 1M | $0.15 | $0.47 | |
| Qwen 3.8 Omni Flash | Qwen3.8-Omni-Flash is Alibaba s native multimodal model for understanding text, images, audio, and… | 1M | $0.15 | $0.47 | |
| Qwen3 Next 80B A3B Thinking | Qwen3-Next uses a highly sparse MoE design: 80B total parameters, but only ~3B activated per… | 131K | $0.15 | $1.2 | Yes |
| Qwen3 VL 30B A3B Instruct | Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual… | 131K | $0.15 | $0.6 | Yes |
| Qwen3.5-35B-A3B | The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture… | 262K | $0.14 | $1 | Yes |
| Qwen3 14B | Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for… | 41K | $0.12 | $0.24 | Yes |
| Qwen3 30B A3B | Qwen3, the latest generation in the Qwen large language model series, features both dense and… | 41K | $0.12 | $0.5 | Yes |
| Qwen3 Coder Next | Qwen3-Coder-Next is an open-weight language model built specifically for coding, with strong… | 262K | $0.12 | $0.8 | Yes |
| Qwen3-14B | Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive… | 41K | $0.12 | $0.24 | |
| Qwen3-30B-A3B | Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive… | 41K | $0.12 | $0.5 | |
| Qwen 3.5 Flash | The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates… | 1M | $0.1 | $0.4 | |
| Qwen2.5 7B Instruct | Qwen2.5 7B is the latest series of Qwen large language models. Qwen2.5 brings the following… | 33K | $0.1 | $0.2 | Yes |
| Qwen3 30B A3B Instruct 2507 | Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with… | 128K | $0.1 | $0.3 | Yes |
| Qwen3.6 35B A3B | Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total… | 262K | $0.1 | $0.9 | Yes |
| Qwen3 235B A22B Instruct 2507 | Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language… | 262K | $0.09 | $0.55 | Yes |
| Qwen3 Next 80B A3B Instruct | A new generation of open-source, non-thinking mode model powered by Qwen3. This version… | 262K | $0.09 | $1.1 | Yes |
| Qwen3 32B | Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for… | 41K | $0.08 | $0.28 | Yes |
| Qwen3 Coder 30B A3B Instruct | Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts… | 262K | $0.07 | $0.28 | Yes |
| Qwen3.5-Flash | The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates… | 1M | $0.065 | $0.26 | |
| Qwen3.8 27B | Built on the architectural foundation of Qwen3.5, Qwen3.8 delivers substantial gains across… | 1M | $0.039 | $1.25 | Yes |
| Qwen 3.7 Flash | The Qwen3.7 native vision-language Flash model series delivers a comprehensive upgrade over… | 1M | $0.03 | $0.13 |
Mistral (26)
Mistral (26)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| Mistral Large | This is Mistral AI’s flagship model, Mistral Large 2 (version mistral-large-2407). It’s a… | 128K | $2 | $6 | Yes |
| Mistral Large 2407 | This is Mistral AI’s flagship model, Mistral Large 2 (version mistral-large-2407). It’s a… | 131K | $2 | $6 | Yes |
| Mixtral 8x22B Instruct | Mistral’s official instruct fine-tuned version of Mixtral 8x22B. It uses 39B active parameters out… | 66K | $2 | $6 | Yes |
| Mistral Medium Latest | Mistral’s frontier-class multimodal model optimized for agentic and coding use cases. | 262K | $1.5 | $7.5 | Yes |
| Mistral Large 4 | Mistral Large 4 is Mistral AI’s open-weight, natively multimodal model, available in public… | 524K | $1.36 | $4.18 | |
| Mistral Large 4 | Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for… | 1M | $1.36 | $4.18 | Yes |
| Mistral Large 3 | Mistral Large 3 2512 is Mistral s most capable model to date. It has a sparse mixture-of-experts… | 256K | $0.5 | $1.5 | |
| Mistral Large 3 2512 | Mistral Large 3 2512 is Mistral s most capable model to date, featuring a sparse… | 262K | $0.5 | $1.5 | Yes |
| Devstral 2 2512 | Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding… | 262K | $0.4 | $2 | Yes |
| Mistral Medium 3 | Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver… | 131K | $0.4 | $2 | Yes |
| Mistral Medium 3.1 | Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance… | 131K | $0.4 | $2 | Yes |
| Mistral Small 3.1 24B | Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24… | 128K | $0.351 | $0.555 | Yes |
| Codestral 2508 | Mistral’s cutting-edge language model for coding released end of July 2025. Codestral specializes… | 256K | $0.3 | $0.9 | Yes |
| Mistral Codestral | Mistral’s cutting-edge language model for coding released end of July 2025, Codestral specializes… | 128K | $0.3 | $0.9 | |
| Ministral 14B | Ministral 3 14B is the largest model in the Ministral 3 family, offering state-of-the-art… | 256K | $0.2 | $0.2 | |
| Ministral 3 14B 2512 | The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and… | 262K | $0.2 | $0.2 | Yes |
| Saba | Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South… | 33K | $0.2 | $0.6 | Yes |
| Ministral 3 8B 2512 | A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language… | 262K | $0.15 | $0.15 | Yes |
| Ministral 8B | A more powerful model with faster, memory-efficient inference, ideal for complex workflows and… | 128K | $0.15 | $0.15 | |
| Mistral Small | Mistral Small currently runs Mistral Small 4, a multimodal model combining instruction following… | 32K | $0.15 | $0.6 | |
| Mistral Small 4 | Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities… | 256K | $0.15 | $0.6 | Yes |
| Ministral 3 3B 2512 | The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny… | 131K | $0.1 | $0.1 | Yes |
| Ministral 3B | A compact, efficient model for on-device tasks like smart assistants and local analytics, offering… | 128K | $0.1 | $0.1 | |
| Voxtral Small 24B 2507 | Voxtral Small is an of Mistral Small 3, incorporating state-of-the-art audio input capabilities… | 32K | $0.1 | $0.3 | Yes |
| Mistral Small 3.2 24B | Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for… | 256K | $0.075 | $0.2 | Yes |
| Mistral Nemo 12B | 12B model trained jointly by Mistral AI and NVIDIA, it significantly outperforms existing models… | 128K | $0.029 | $0.03 | Yes |
Meta (17)
Meta (17)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| Muse Wonder | Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and… | 1M | $4 | $20 | |
| Muse Wonder | Muse Wonder is Meta s model for frontier coding, long-running agents, and advanced computer use… | 1M | $4 | $20 | |
| Muse Spark 1.1 | Muse Spark 1.1 is strongest at agentic performance, tool use, and computer use. It does well on… | 1M | $1.25 | $4.25 | |
| Muse Spark 1.2 | A coding-optimized model purpose-built for agentic workflows. Improvements to code generation… | 1M | $1.25 | $4.25 | |
| Muse Spark 1.3 | Muse Spark 1.3 is Meta s multimodal reasoning model for long-horizon agentic and coding workflows… | 1M | $1.25 | $4.25 | |
| Muse Spark Open | Muse Spark Open is Meta s open-weight reasoning model for coding and agentic workflows. Its sparse… | 1M | $1.25 | $4.25 | Yes |
| Llama 3.1 70B Instruct | An update to Meta Llama 3 70B Instruct that includes an expanded 128K context length… | 128K | $0.72 | $0.72 | |
| Llama 3.3 70B Instruct | Where performance meets efficiency. This model supports high-performance conversational AI… | 128K | $0.72 | $0.72 | |
| Llama 3.1 70B Instruct | Meta’s latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B… | 131K | $0.4 | $0.4 | Yes |
| Muse Glimmer 30B | Reasoning model, trusted for Google-connected agents, 131K context. | 131K | $0.3 | $1.2 | Yes |
| Llama 3.1 8B Instruct | An update to Meta Llama 3 8B Instruct that includes an expanded 128K context length… | 128K | $0.22 | $0.22 | |
| Llama 4 Maverick 17B Instruct | As a general purpose LLM, Llama 4 Maverick contains 17 billion active parameters, 128 experts, and… | 1M | $0.188 | $0.652 | Yes |
| Llama 3.3 70B Instruct | The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned… | 131K | $0.1 | $0.32 | Yes |
| Llama 4 Scout 17B Instruct | Llama 4 Scout is the best multimodal model in the world in its class and is more powerful than our… | 328K | $0.1 | $0.3 | Yes |
| Muse Spark 1.2 Contributor | A coding-optimized model with pricing designed for builders. Same model, same capabilities , up to… | 1M | $0.1 | $0.2 | |
| Muse Spark 1.3 Contributor | Muse Spark 1.3 Contributor is Meta s cost-optimized API option for agentic coding workflows. It… | 1M | $0.1 | $0.2 | |
| Llama 3.1 8B Instruct | Meta’s latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B… | 131K | $0.02 | $0.04 | Yes |
MiniMax (10)
MiniMax (10)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| MiniMax M2.5 High Speed | M2.5 highspeed: Same performance, faster and more agile (output speed approximately 100 tps) | 205K | $0.6 | $2.4 | |
| MiniMax M2.7 High Speed | M2.7 Highspeed: Same performance, faster and more agile (output speed approximately 100 tps) | 205K | $0.6 | $2.4 | |
| MiniMax M1 | MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and… | 1M | $0.55 | $2.2 | Yes |
| MiniMax M2.1 | MiniMax 2.1 is MiniMax’s latest model, optimized specifically for in coding, tool use, instruction… | 205K | $0.3 | $1.2 | Yes |
| MiniMax M2.1 Lightning | MiniMax-M2.1-lightning is a faster version of MiniMax-M2.1, offering the same performance but with… | 205K | $0.3 | $2.4 | |
| MiniMax M2.5 | MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. It is capable of… | 197K | $0.3 | $1.2 | Yes |
| MiniMax M2.7 | M2.7 delivers outstanding performance in real-world software engineering, including end-to-end… | 205K | $0.3 | $1.2 | Yes |
| MiniMax M3 | MiniMax-M3 is a frontier-class foundation model that unites the three capabilities defining… | 524K | $0.3 | $1.2 | Yes |
| MiniMax M2 | MiniMax-M2 redefines efficiency for agents. It is a compact, fast, and cost-effective MoE model… | 205K | $0.255 | $1.02 | Yes |
| MiniMax-M3.1-Flash | MiniMax-M3.1-Flash is MiniMax s multimodal M-series model for agent reasoning, tool use, coding… | 1M | $0.15 | $0.6 | Yes |
NVIDIA (7)
NVIDIA (7)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| Nemotron 3 Ultra | A 550B parameter (55B active) open reasoning model from NVIDIA, built for long-running agent… | 512K | $0.6 | $2.4 | Yes |
| NVIDIA Nemotron 3 Super 120B A12B | NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters… | 262K | $0.3 | $2.4 | Yes |
| Nvidia Nemotron Nano 12B V2 VL | The model is an auto-regressive vision language model that uses an optimized transformer… | 131K | $0.2 | $0.6 | |
| NVIDIA Nemotron 3.5 Super VL | NVIDIA Nemotron 3.5 Super VL is a vision-language model for reasoning, coding, tool use, and… | 1M | $0.15 | $0.5 | Yes |
| Nemotron 3.5 Lightning 30B | NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 is a large language model (LLM) trained by NVIDIA. The… | 262K | $0.07 | $0.2 | Yes |
| Nemotron 3 Nano 30B A3B | NVIDIA Nemotron 3 Nano is an open reasoning model optimized for fast, cost-efficient inference… | 262K | $0.06 | $0.24 | Yes |
| Nvidia Nemotron Nano 9B V2 | NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and… | 131K | $0.06 | $0.23 |
Amazon (9)
Amazon (9)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| Nova Premier 1.0 | Amazon Nova Premier is the most capable of Amazon s multimodal models for complex reasoning tasks… | 1M | $2.5 | $12.5 | Yes |
| Nova Pro | A highly capable multimodal model with the best combination of accuracy, speed, and cost for a… | 300K | $0.8 | $3.2 | |
| Nova Pro 1.0 | Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination… | 300K | $0.8 | $3.2 | Yes |
| Nova 2 Lite | Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process… | 1M | $0.33 | $2.75 | |
| Nova 2 Lite | Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process… | 1M | $0.3 | $2.5 | Yes |
| Nova Lite | A very low cost multimodal model that is lightning fast for processing image, video, and text… | 300K | $0.06 | $0.24 | |
| Nova Lite 1.0 | Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast… | 300K | $0.06 | $0.24 | Yes |
| Nova Micro | A text-only model that delivers the lowest latency responses at very low cost. | 128K | $0.035 | $0.14 | |
| Nova Micro 1.0 | Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the… | 128K | $0.035 | $0.14 | Yes |
Cohere (4)
Cohere (4)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| Command A | Command A is Cohere’s most performant model to date, excelling at tool use, agents, retrieval… | 256K | $2.5 | $10 | |
| Command R+ (08-2024) | command-r-plus-08-2024 is an update of the Command R+ with roughly 50% higher throughput and 25%… | 128K | $2.5 | $10 | |
| Command A+ | Command A+ is Cohere’s flagship model for enterprise agentic workflows. It accepts text and image… | 192K | $0.3 | $1.5 | Yes |
| Command R (08-2024) | command-r-08-2024 is an update of the Command R with improved performance for multilingual… | 128K | $0.15 | $0.6 |
ByteDance (6)
ByteDance (6)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| Seed 2.1 Turbo | Seed 2.1 Turbo is a multimodal model from ByteDance Seed for coding and long-horizon agent… | 262K | $0.5 | $2.5 | Yes |
| Seed-2.0-Code | Seed 2.0 Code is a model from ByteDance Seed optimized for agentic coding. It is suited for… | 262K | $0.5 | $3 | Yes |
| Seed 1.6 | Seed 1.6 is a general-purpose model released by the ByteDance Seed team. It incorporates… | 262K | $0.25 | $2 | Yes |
| Seed-2.0-Lite | Seed-2.0-Lite is a versatile, cost-efficient enterprise workhorse that delivers strong multimodal… | 262K | $0.25 | $2 | Yes |
| Seed-2.0-Mini | Seed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios… | 262K | $0.1 | $0.4 | Yes |
| Seed 1.6 Flash | Seed 1.6 Flash is an ultra-fast multimodal deep thinking model by ByteDance Seed, supporting both… | 262K | $0.075 | $0.3 | Yes |
OpenRouter (4)
OpenRouter (4)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| Auto Router (Beta) | The experimental version of our Auto Router where we test new improvements. Use it to get the… | 2M | - | - | |
| OpenRouter Auto | The Auto Router automatically selects the best model for your prompt, powered by the wisdom of the… | 2M | - | - | |
| OpenRouter Fusion | Fusion turns your prompt into a small multi-model deliberation. A panel of expert models (see… | 1M | - | - | |
| Pareto Code Router | The Pareto Router maintains a tiered shortlist of strong coding models, ranked by Artificial… | 2M | - | - |
Aion-labs (5)
Aion-labs (5)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| Aion 3.5 | Aion 3.5 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM… | 262K | $3 | $6 | |
| Aion-3.0 | Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM… | 131K | $3 | $6 | |
| Aion-2.0 | Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling. It is… | 131K | $0.8 | $1.6 | |
| Aion 3.5 Mini | Aion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM… | 262K | $0.7 | $1.4 | |
| Aion-3.0-Mini | Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the… | 131K | $0.7 | $1.4 |
Arcee-ai (1)
Arcee-ai (1)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| Trinity Large Thinking | Trinity-Large-Thinking is a reasoning-optimized variant of Arcee AI’s Trinity-Large family , a… | 262K | $0.25 | $0.8 |
Bytedance (3)
Bytedance (3)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| Seed 2.1 Turbo | Seed 2.1 Turbo is ByteDance s multimodal language model supporting text, image, and video inputs… | 262K | $0.5 | $2.5 | |
| Bytedance Seed 1.8 | Bytedance Seed 1.8 features stronger multimodal understanding and agent capabilities. The model… | 256K | $0.25 | $2 | |
| Seed 1.6 | ByteDance’s new multimodal deep-thinking model, supporting both text and visual inputs with… | 256K | $0.25 | $2 |
Callstack (1)
Callstack (1)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| Apex | Apex is Callstack s agentic coding model for mobile and web development, optimized for React… | 262K | $0.5 | $3 |
Elorian (1)
Elorian (1)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| Glimpse | Glimpse is a multimodal visual reasoning model from Elorian, built for visual understanding and… | 262K | $0.6 | $3 | Yes |
Fireworks (1)
Fireworks (1)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| Ember-1 | Ember-1 is Fireworks research-preview reasoning model built on Kimi K3 for coding and agentic… | 1M | $3 | $15 | Yes |
Ibm-granite (1)
Ibm-granite (1)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| Granite 4.2 8B | Granite 4.2 8B is a dense reasoning model from IBM. It is suited for mathematics, code generation… | 131K | $0.06 | $0.25 | Yes |
Inception (4)
Inception (4)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| Mercury 2 | A diffusion-based reasoning LLM that generates text via parallel refinement (not token-by-token)… | 128K | $0.25 | $0.75 | Yes |
| Mercury Coder Small Beta | Mercury Coder Small is ideal for code generation, debugging, and refactoring tasks with minimal… | 32K | $0.25 | $1 | |
| Mercury 3 | Mercury 3 is Inception s most capable model for agentic workflows and real-time applications. It… | 1M | $0.1 | $0.35 | Yes |
| Mercury 2.5 | Mercury 2.5 is Inception s diffusion-based reasoning model for chat, agents, and structured… | 260K | $0.04 | $0.15 | Yes |
Inclusionai (5)
Inclusionai (5)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| Ling 3.0 Flash Fin | Ling 3.0 Flash Fin is InclusionAI s finance- MoE language model, combining 124 billion total… | 256K | $0.075 | $0.22 | |
| Ling 3.0 Flash Sante | Ling-3.0-Flash-Sante is inclusionAI s language model specialized for health and medicine, built on… | 256K | $0.075 | $0.22 | |
| Ling 3.1 Flash | Ling 3.1 Flash is InclusionAI’s hybrid reasoning language model for coding, multi-step analysis… | 1M | $0.075 | $0.225 | Yes |
| Ling 3.0 Flash VL | Ling 3.0 Flash VL builds on Ling 3.0 Flash with stronger language capabilities, native visual… | 131K | $0.06 | $0.18 | Yes |
| Ling 3.0 Flash | Ling 3.0 Flash is designed with token efficiency and production-scale agentic inference as key… | 262K | $0.021 | $0.063 | Yes |
Interfaze (1)
Interfaze (1)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| Interfaze Beta | Interfaze is an AI model built on a new architecture that merges specialized DNN/CNN models with… | 1M | $1.5 | $3.5 |
Liquid (3)
Liquid (3)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| LFM2.5-2.6B | LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data… | 128K | $0.35 | $0.5 | |
| LFM2.5-24B-A2B | LFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B… | 128K | $0.05 | $0.7 | Yes |
| LFM2.5-24B-A2B | LFM2.5-24B-A2B is a text-generation model from Liquid AI with a 128,000-token context window. | 128K | $0.05 | $0.7 |
Meituan (2)
Meituan (2)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| LongCat 2.0 | LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters… | 1M | $0.3 | $1.2 | |
| LongCat 2.5 Preview | LongCat-2.5-Preview is Meituan s multimodal reasoning model for coding and agentic workflows, with… | 1M | $0.3 | $1.2 |
Mixedbread (1)
Mixedbread (1)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| Toast 1 | Built for knowledge-intensive questions, multi-step retrieval, and evidence synthesis. Toast 1 can… | 131K | $0.3 | $0.72 |
Nex-agi (1)
Nex-agi (1)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| Nex-N2.5-Pro | Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core… | 262K | $0.075 | $0.25 |
Perceptron (1)
Perceptron (1)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| Perceptron Mk1.5 | Perceptron Mk1.5 is Perceptron’s embodied reasoning model for physical agents. It accepts text… | 37K | $0.15 | $1.5 | Yes |
Poolside (2)
Poolside (2)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| Laguna S 2.1 | Laguna S 2.1 is Poolside’s new open-weight model for agentic coding and long-horizon work. | 1M | $0.09 | $0.18 | |
| Laguna XS 2.1 | Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from Poolside and a step… | 262K | $0.06 | $0.12 |
Prism-ml (2)
Prism-ml (2)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| Ternary Bonsai 2 9B | Ternary Bonsai 2 9B is PrismML s compact, open-weight language model for conversational AI… | 262K | $0.08 | $0.13 | |
| Ternary Bonsai 2 27B | Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports… | 262K | $0.075 | $0.5 |
Quiverai (2)
Quiverai (2)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| Arrow 2 Telos | Higher-refinement Arrow 2 variant combining Arrow’s speed with frontier-model reasoning. | 131K | $6 | $30 | |
| Arrow 2 | SVG generation model with agentic refinement and tool calling. | 131K | $4 | $20 |
Reflection (1)
Reflection (1)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| Beam 1.0 501B A23B | Beam 1.0 is Reflection’s open-weight reasoning model for coding and long-horizon agentic… | 1M | $0.25 | $1 | Yes |
Rekaai (1)
Rekaai (1)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| Reka Edge | Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts… | 16K | $0.1 | $0.1 | Yes |
Relace (1)
Relace (1)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| Relace Search | The relace-search model uses 4-12 view_file and grep tools in parallel to explore a codebase and… | 256K | $1 | $3 | Yes |
Sakana (5)
Sakana (5)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| Fugu Ultra | Fugu Ultra coordinates a deeper pool of expert agents to maximize answer quality on hard… | 1M | $5 | $30 | |
| Fugu Ultra v2 | Fugu Ultra coordinates a deeper pool of expert agents to maximize answer quality on hard… | 1M | $5 | $30 | |
| Fugu Max | Fugu Max orchestrates our largest pool of models to push the cost-performance Pareto frontier. It… | 1M | $2 | $6 | |
| Sakana Namazu | Sakana Namazu is a Japanese-specialized reasoning model from Sakana AI, based on Kimi K2.6 with… | 262K | $0.95 | $4 | |
| Sakana Namazu | Sakana Namazu is a Japanese-specialized LLM that combines a deep understanding of Japanese culture… | 256K | $0.95 | $4 |
Spacexai (11)
Spacexai (11)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| Grok 4.5 | SpaceXAI’s smartest model with frontier performance on coding, knowledge work, and STEM. | 500K | $2 | $6 | |
| Grok 4.6 | Grok 4.6 builds on Grok 4.5 with a particular focus on long-running agents and more ambitious… | 500K | $2 | $6 | |
| Grok 4.7 | Grok 4.7 is SpaceXAI s advanced AI model for coding and professional knowledge work, built to… | 500K | $2 | $6 | |
| Grok 4.20 Beta Non-Reasoning | Grok 4.20 Beta is the newest flagship model from xAI with industry-leading speed and agentic tool… | 2M | $1.25 | $2.5 | |
| Grok 4.20 Beta Reasoning | Grok 4.20 Beta is the newest flagship model from xAI with industry-leading speed and agentic tool… | 2M | $1.25 | $2.5 | |
| Grok 4.20 Multi Agent Beta | Multiple agents collaborate in parallel to perform deep research tasks. | 2M | $1.25 | $2.5 | |
| Grok 4.20 Multi-Agent | Multiple agents collaborate in parallel to perform deep research tasks. | 2M | $1.25 | $2.5 | |
| Grok 4.20 Non-Reasoning | Grok 4.20 Beta is the newest flagship model from xAI with industry-leading speed and agentic tool… | 2M | $1.25 | $2.5 | |
| Grok 4.20 Reasoning | Grok 4.20 Beta is the newest flagship model from xAI with industry-leading speed and agentic tool… | 2M | $1.25 | $2.5 | |
| Grok 4.3 | Grok 4.3 is a new model matching the scale of Grok 4.20 with an improved architecture and a… | 1M | $1.25 | $2.5 | |
| Grok Build 0.1 | xAI’s fast coding model trained specifically for agentic coding. | 256K | $1 | $2 |
Stealth (1)
Stealth (1)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| Glyph Cluster | Glyph Cluster is an anonymous reasoning model in early access. Prompts and outputs will be… | 256K | - | - |
Stepfun (3)
Stepfun (3)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| Step 5 Preview | Step 5 Preview is StepFun s flagship AI model for agentic coding, professional knowledge work, and… | 1M | $1 | $2.7 | Yes |
| Step 3.7 Flash | StepFun s flagship multimodal reasoning model. Powered by a 198B-parameter / 11B-activation sparse… | 256K | $0.2 | $1.15 | Yes |
| Step 3.5 Flash | Step 3.5 Flash is StepFun’s most capable open-source foundation model. Built on a sparse Mixture… | 262K | $0.1 | $0.3 | Yes |
Tencent (3)
Tencent (3)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| Tencent Hy4 Preview | Tencent Hy4 preview is Tencent Hy s open-source large language model, featuring 770B total… | 1M | $0.834 | $2.5 | Yes |
| Hy3 preview | Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic… | 262K | $0.18 | $0.6 | |
| Hy3 | Built for real-world business scenarios, Hy3 features a 295B/21B active MoE architecture, native… | 262K | $0.132 | $0.528 | Yes |
Thinkingmachines (2)
Thinkingmachines (2)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| Inkling | Inkling is a multimodal MoE model (975B total, 41B active, 256k context) reasoning over text… | 524K | $1 | $4.05 | Yes |
| Inkling Small | Inkling-Small is a lighter-weight model with 12B active parameters, trained with a similar recipe… | 524K | $0.45 | $1.2 | Yes |
Typesafe (1)
Typesafe (1)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| Jev Router | Jev Router picks the best model and reasoning effort for each request, balancing quality, speed… | 1M | - | - |
Unbiased (2)
Unbiased (2)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| Pareto 26.9 | Pareto is a multimodal composite model built for research, coding, and agentic workflows, while… | 262K | $2.5 | $7.5 | |
| Pareto 26.10 | Pareto is a multimodal composite model built for research, coding, and agentic workflows, while… | 1M | $0.8 | $3.2 | Yes |
Upstage (3)
Upstage (3)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| Solar Pro 3 | Solar Pro 3 is Upstage’s powerful Mixture-of-Experts (MoE) language model. With 102B total… | 131K | $0.15 | $0.6 | |
| Solar Pro 4 | Solar Pro 4 is Upstage’s cost-efficient large language model, featuring a 524K context window. It… | 524K | $0.15 | $0.6 | Yes |
| Solar Mini 4 | Solar Mini 4 is Upstage’s compact, cost-efficient language model, a 35B-parameter… | 524K | $0.05 | $0.2 | Yes |
Xiaomi (5)
Xiaomi (5)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| MiMo V2.6 Pro UltraSpeed | MiMo V2.6 Pro UltraSpeed is Xiaomi’s accelerated inference offering for MiMo V2.6 Pro, designed… | 1M | $4.35 | $8.7 | |
| MiMo V2.5 Pro | MiMo V2.5 Pro delivers significant improvements over its predecessor, MiMo-V2-Pro, in general… | 1M | $0.48 | $1.8 | Yes |
| MiMo V2.6 Pro | MiMo V2.6 Pro is Xiaomi’s flagship multimodal reasoning model for complex software engineering… | 1.1M | $0.435 | $0.87 | Yes |
| MiMo M2.5 | A native full-modal model supporting text, image, video, and audio understanding, with powerful… | 1M | $0.4 | $2 | Yes |
| MiMo V2.6 Flash | MiMo V2.6 Flash is Xiaomi’s efficient multimodal reasoning model for coding, automation, and… | 1.1M | $0.14 | $0.28 | Yes |
Zhipu (19)
Zhipu (19)
| Model | Note | Context | In | Out | Trusted |
|---|---|---|---|---|---|
| GLM 5.2 Fast | GLM-5.2-Fast-Preview is the high-speed variant of Zhipu AI’s GLM-5.2, with 1M context and… | 1M | $2.8 | $8.8 | |
| GLM 5.3 Prime | GLM-5.3-Prime is the high-speed variant of Z.ai’s GLM-5.3, inheriting its full capabilities while… | 1M | $2.8 | $8.8 | |
| GLM 5.3 Fast | Speed-optimized version of Z.AI s GLM-5.3 agentic coding model, built for responsive, real-time… | 1M | $2.1 | $6.6 | |
| GLM 5.1 | GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in… | 203K | $1.4 | $4.4 | Yes |
| GLM 5 Turbo | GLM 5 Turbo is a foundation model deeply optimized for the OpenClaw scenario. It has been… | 200K | $1.2 | $4 | Yes |
| GLM 5V Turbo | GLM-5V-Turbo is Z.AI s first multimodal coding foundation model, built for vision-based coding… | 203K | $1.2 | $4 | Yes |
| GLM 5 | GLM 5 is a frontier-class, general-purpose large language model optimized for complex systems… | 205K | $1 | $3.2 | Yes |
| GLM 4.5 | GLM-4.5 and GLM-4.5-Air are our latest flagship models, purpose-built as foundational models for… | 131K | $0.6 | $2.2 | Yes |
| GLM 4.5V | Built on the GLM-4.5-Air base model, GLM-4.5V inherits proven techniques from GLM-4.1V-Thinking… | 66K | $0.6 | $1.8 | Yes |
| GLM 4.6 | As the latest iteration in the GLM series, GLM-4.6 achieves comprehensive enhancements across… | 203K | $0.55 | $2.2 | Yes |
| GLM 4.7 | GLM-4.7 is a powerful next-generation coding model that delivers major gains in multilingual… | 205K | $0.54 | $1.98 | Yes |
| GLM 5.3 FlashX | GLM-5.3-FlashX is the high-speed serving option for Z.ai s native multimodal coding model… | 1M | $0.37 | $1.25 | Yes |
| GLM 4.6V | GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and… | 131K | $0.3 | $0.9 | Yes |
| GLM 5.3 Flash | GLM-5.3-Flash is Z.ai s native multimodal coding model, featuring 320B total parameters, 18B… | 1M | $0.15 | $0.5 | Yes |
| GLM 4.5 Air | GLM-4.5 and GLM-4.5-Air are our latest flagship models, purpose-built as foundational models for… | 131K | $0.13 | $0.85 | Yes |
| GLM 5.3 | GLM 5.3 delivers comprehensive advancements in complex software engineering and agent… | 1M | $0.07 | $1.4 | Yes |
| GLM 4.7 Flash | GLM-4.7-Flash balances high performance with efficiency, making it the perfect lightweight… | 203K | $0.061 | $0.4 | Yes |
| GLM 4.7 FlashX | GLM-4.7-Flash balances high performance with efficiency, making it the perfect lightweight… | 200K | $0.06 | $0.4 | |
| GLM 5.2 | GLM-5.2 delivers powerful coding capabilities, usable 1M-context support, and continued strengths… | 1M | $0.014 | $7 | Yes |
Related
Models
How to pick, switch, and keep spend in check.
Trusted models
Why Google connections lock an agent to a smaller set.
Pricing
Credit balance and at-cost model usage.
Usage
See which models are drawing down credit.