Models
301 models from 6 providers, on one schema and one bill — every price below is what the route costs and what you are billed.
- Claude Opus 5anthropic/claude-opus-5
For complex agentic coding and enterprise work. Adaptive thinking on by default, 1M context.
VisionReasoningTools+3$5.00in / 1M$25.00out / 1M1Mcontext2providers - GPT-5.6 Solopenai/gpt-5.6-sol
OpenAI's frontier reasoning model. Largest of the 5.6 family, for the hardest analysis and long-horizon agentic work.
VisionReasoningTools+3$4.00in / 1M$20.00out / 1M1.0Mcontext1provider - Claude Fable 5anthropic/claude-fable-5
Anthropic's most capable model, for the most demanding reasoning and long-horizon agentic work. Thinking is always on.
VisionReasoningTools+3$10.00in / 1M$50.00out / 1M1Mcontext2providers - GPT-5.6 Terraopenai/gpt-5.6-terra
The balanced 5.6 model. Most production workloads that need frontier quality without Sol pricing.
VisionReasoningTools+3$2.00in / 1M$12.00out / 1M1.0Mcontext2providers - Claude Sonnet 5anthropic/claude-sonnet-5
Near-Opus quality on coding and agentic work at Sonnet cost.
VisionReasoningTools+3$2.00in / 1M$10.00out / 1M1Mcontext3providers - GPT-5.6 Lunaopenai/gpt-5.6-luna
The cheap, fast 5.6 model. Classification, extraction and high-volume chat at a fraction of Terra's cost.
VisionReasoningTools+3$0.2000in / 1M$1.20out / 1M1.0Mcontext2providers - Claude Opus 4.8anthropic/claude-opus-4-8
Previous-generation Opus. Highly autonomous on long-horizon agentic work, at the same price as Opus 5.
VisionReasoningTools+3$5.00in / 1M$25.00out / 1M1Mcontext1provider - GPT-5.1openai/gpt-5.1
Previous-generation flagship. Still a strong default for general reasoning and tool use.
VisionReasoningTools+3$1.25in / 1M$10.00out / 1M400Kcontext2providers - Claude Sonnet 4.6anthropic/claude-sonnet-4-6
Previous-generation Sonnet. 1M context, adaptive thinking.
VisionReasoningTools+3$3.00in / 1M$15.00out / 1M1Mcontext1provider - Kimi K3moonshot/kimi-k3
Moonshot's frontier agentic model, with a 1M context window.
ReasoningToolsJSON+1$3.00in / 1M$15.00out / 1M1Mcontext2providers - DeepSeek V4 Prodeepseek/deepseek-v4-pro
DeepSeek's frontier release. 512K context.
ReasoningToolsJSON+1$1.30in / 1M$2.60out / 1M512Kcontext2providers - GLM-5.2zai/glm-5.2
Z.ai's flagship open-weights model. Strong on coding and tool use.
ReasoningToolsJSON+1$1.40in / 1M$4.40out / 1M262Kcontext1provider - Claude Haiku 4.5anthropic/claude-haiku-4-5
Anthropic's fastest and most cost-effective model. 200K context rather than the 1M of the larger models.
VisionReasoningTools+3$1.00in / 1M$5.00out / 1M200Kcontext2providers - GPT-5 miniopenai/gpt-5-mini
Small GPT-5 variant. Good cost/quality balance for summarisation and routing.
VisionReasoningTools+3$0.2500in / 1M$2.00out / 1M400Kcontext2providers - Qwen3.7 Plusqwen/qwen3.7-plus
1M context at a mid-tier price. Good for large-document work.
ReasoningToolsJSON+1$0.3200in / 1M$1.28out / 1M1Mcontext2providers - MiniMax M3minimax/minimax-m3
Cheap long-context model with a 512K window.
ToolsJSONStreaming$0.3000in / 1M$1.20out / 1M524Kcontext2providers - GPT-OSS 120Bopenai/gpt-oss-120b
OpenAI's open-weights 120B model. Reasoning-capable, and cheap enough to run in a loop.
ReasoningToolsJSON+1$0.1500in / 1M$0.6000out / 1M131Kcontext1provider - DeepSeek V3.2deepseek/deepseek-v3.2
DeepSeek's mainline model. Frontier-adjacent quality at open-weights prices.
ReasoningToolsJSON+1$0.2600in / 1M$0.3800out / 1M164Kcontext2providers - Llama 3.3 70B Instructmeta/llama-3.3-70b-instruct
Meta's open-weights 70B instruct model, served here by three independent providers. Failover between them is transparent to your code.
ToolsJSONStreaming$0.1000in / 1M$0.3200out / 1M131Kcontext4providers - o3openai/o3
Reasoning model for maths, science and multi-step problems where a chain of thought earns its cost.
VisionReasoningTools+3$2.00in / 1M$8.00out / 1M200Kcontext2providers - GPT-4.1openai/gpt-4.1
Long-context workhorse with a 1M window. Widely deployed and cheap to run against large documents.
VisionToolsJSON+2$2.00in / 1M$8.00out / 1M1.0Mcontext2providers - GPT-5 nanoopenai/gpt-5-nano
The cheapest GPT-5 variant. Built for classification and other short, high-volume calls.
VisionReasoningTools+3$0.0500in / 1M$0.4000out / 1M400Kcontext2providers - GPT-OSS 20Bopenai/gpt-oss-20b
The small open-weights GPT-OSS model, served by two providers.
ReasoningToolsJSON+1$0.0500in / 1M$0.2000out / 1M128Kcontext2providers - Qwen3 235B A22B Instructqwen/qwen3-235b-a22b-instruct
Large sparse MoE: 235B total parameters, 22B active. Cheap for its capability class.
ToolsJSONStreaming$0.0900in / 1M$0.5500out / 1M262Kcontext1provider - Llama 3.1 8B Instructmeta/llama-3.1-8b-instruct
Small, extremely cheap open-weights model. The floor of the catalogue for simple classification work.
ToolsJSONStreaming$0.0200in / 1M$0.0400out / 1M131Kcontext3providers - DeepSeek R1 (0528)deepseek/deepseek-r1
Open-weights reasoning model. Emits an explicit chain of thought before answering.
ReasoningJSONStreaming$0.5000in / 1M$2.15out / 1M64Kcontext2providers - GPT-4.1 miniopenai/gpt-4.1-mini
1M context at a fifth of GPT-4.1's price. A strong default for RAG.
VisionToolsJSON+2$0.4000in / 1M$1.60out / 1M1.0Mcontext2providers - GPT-4oopenai/gpt-4o
The multimodal 4-series model. Kept in the catalogue because a great deal of production code still pins it.
VisionToolsJSON+2$2.50in / 1M$10.00out / 1M128Kcontext2providers - GPT-4o miniopenai/gpt-4o-mini
Cheap, fast and still widely pinned. Vision-capable.
VisionToolsJSON+2$0.1500in / 1M$0.6000out / 1M128Kcontext2providers - o4-miniopenai/o4-mini
Small reasoning model. Most of o3's method at a fraction of the latency.
VisionReasoningTools+3$1.10in / 1M$4.40out / 1M200Kcontext2providers - Qwen3 32Bqwen/qwen3-32b
Dense 32B model. A solid mid-tier open-weights default.
ToolsJSONStreaming$0.0800in / 1M$0.2800out / 1M131Kcontext2providers - DeepSeek V3.1deepseek/deepseek-v3.1
The previous DeepSeek mainline release. Still widely pinned.
ReasoningToolsJSON+1$0.2500in / 1M$0.9500out / 1M164Kcontext1provider - Gemma 3n E4B Instructgoogle/gemma-3n-e4b
Google's small open-weights model. The cheapest completion price in the catalogue.
JSONStreaming$0.0600in / 1M$0.1200out / 1M33Kcontext1provider - Qwen3.5 9Bqwen/qwen3.5-9b
Small, fast and cheap, with a 256K context window.
ToolsJSONStreaming$0.1700in / 1M$0.2500out / 1M262Kcontext1provider - BGE-M3Embeddingsbaai/bge-m3
Multilingual open-weights embeddings with an 8K context. The cheapest route in the catalogue.
$0.0100in / 1M$0.00out / 1M8Kcontext1provider - Embedding 3 LargeEmbeddingsopenai/text-embedding-3-large
Higher-dimensional embeddings for when retrieval quality matters more than cost.
$0.1300in / 1M$0.00out / 1M8Kcontext1provider - Embedding 3 SmallEmbeddingsopenai/text-embedding-3-small
Cheap, fast general-purpose embeddings. The sensible default for search and RAG.
$0.0200in / 1M$0.00out / 1M8Kcontext1provider - FLUX.1 [schnell]Imageblack-forest-labs/flux-1-schnell
Open-weights image generation in a handful of steps. The cheap, fast end of the image catalogue.
$0.002700per megapixel1Kcontext1provider - Multilingual E5 Large InstructEmbeddingsintfloat/multilingual-e5-large-instruct
Instruction-tuned multilingual embeddings across 100 languages.
$0.0200in / 1M$0.00out / 1M1Kcontext1provider - Aion-2.0aion-labs/aion-2.0
Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling. It is particularly strong at introducing tension, crises, and conflict into stories, making narratives feel more engaging....
ReasoningToolsJSON+2$0.8440in / 1M$1.69out / 1M131Kcontext1provider - Aion-3.0aion-labs/aion-3.0
Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each contribute...
ReasoningToolsJSON+2$3.17in / 1M$6.33out / 1M131Kcontext1provider - Aion-3.0-Miniaion-labs/aion-3.0-mini
Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. It uses a collaborative generation process in which multiple specialized models each...
ReasoningToolsJSON+2$0.7385in / 1M$1.48out / 1M131Kcontext1provider - Aion-RP 1.0 (8B)aion-labs/aion-rp-llama-3.1-8b
Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tuned base model...
CachingStreaming$0.8440in / 1M$1.69out / 1M33Kcontext1provider - Claude 3 Haikuanthropic/claude-3-haiku
Claude 3 Haiku is Anthropic's fastest and most compact model for near-instant responsiveness. Quick and accurate targeted performance. See the launch announcement and benchmark results here multimodal
VisionToolsCaching+1$0.2638in / 1M$1.32out / 1M200Kcontext1provider - Claude Haiku 4.5anthropic/claude-haiku-4.5
Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...
VisionReasoningTools+3$1.06in / 1M$5.28out / 1M200Kcontext1provider - Claude Opus 4anthropic/claude-opus-4
Claude Opus 4 is benchmarked as the world’s best coding model, at time of release, bringing sustained performance on complex, long-running tasks and agent workflows. It sets new benchmarks in...
VisionReasoningTools+2$15.83in / 1M$79.13out / 1M200Kcontext1provider - Claude Opus 4.1anthropic/claude-opus-4.1
Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...
VisionReasoningTools+3$15.83in / 1M$79.13out / 1M200Kcontext1provider - Claude Opus 4.5anthropic/claude-opus-4.5
Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...
VisionReasoningTools+3$5.28in / 1M$26.38out / 1M200Kcontext1provider - Claude Opus 4.6anthropic/claude-opus-4.6
Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...
VisionReasoningTools+3$5.28in / 1M$26.38out / 1M1Mcontext1provider - Claude Opus 4.7anthropic/claude-opus-4.7
Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on...
VisionReasoningTools+3$5.28in / 1M$26.38out / 1M1Mcontext1provider - Claude Opus 4.7 (Fast)anthropic/claude-opus-4.7-fast
Fast-mode variant of Opus 4.7 - identical capabilities with higher output speed at premium 6x pricing. Learn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode
VisionReasoningTools+3$31.65in / 1M$158.25out / 1M1Mcontext1provider - Claude Opus 4.8anthropic/claude-opus-4.8
Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...
VisionReasoningTools+3$5.28in / 1M$26.38out / 1M1Mcontext1provider - Claude Opus 4.8 (Fast)anthropic/claude-opus-4.8-fast
Fast-mode variant of Opus 4.8 - identical capabilities with higher output speed at 2x pricing relative to regular Opus 4.8. Learn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode
VisionReasoningTools+3$10.55in / 1M$52.75out / 1M1Mcontext1provider - Claude Opus 5 (Fast)anthropic/claude-opus-5-fast
Fast-mode variant of Opus 5 - identical capabilities with higher output speed at 2x pricing relative to regular Opus 5. Learn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode
VisionReasoningTools+3$10.55in / 1M$52.75out / 1M1Mcontext1provider - Claude Sonnet 4anthropic/claude-sonnet-4
Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the-art performance on SWE-bench (72.7%),...
VisionReasoningTools+2$3.17in / 1M$15.83out / 1M1Mcontext1provider - Claude Sonnet 4.5anthropic/claude-sonnet-4.5
Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...
VisionReasoningTools+3$3.17in / 1M$15.83out / 1M1Mcontext1provider - Claude Sonnet 4.6anthropic/claude-sonnet-4.6
Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...
VisionReasoningTools+3$3.17in / 1M$15.83out / 1M1Mcontext1provider - Codestral 2508mistralai/codestral-2508
Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. Blog Post
ToolsJSONCaching+1$0.3165in / 1M$0.9495out / 1M256Kcontext1provider - Command Acohere/command-a
Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary...
JSONCachingStreaming$2.64in / 1M$10.55out / 1M256Kcontext1provider - Command R (08-2024)cohere/command-r-08-2024
command-r-08-2024 is an update of the Command R with improved performance for multilingual retrieval-augmented generation (RAG) and tool use. More broadly, it is better at math, code and reasoning and...
ToolsJSONCaching+1$0.1583in / 1M$0.6330out / 1M128Kcontext1provider - Command R+ (08-2024)cohere/command-r-plus-08-2024
command-r-plus-08-2024 is an update of the Command R+ with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while keeping the hardware footprint...
ToolsJSONCaching+1$2.64in / 1M$10.55out / 1M128Kcontext1provider - Command R7B (12-2024)cohere/command-r7b-12-2024
Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning...
JSONCachingStreaming$0.0396in / 1M$0.1583out / 1M128Kcontext1provider - Cydonia 24B V4.1thedrummer/cydonia-24b-v4.1
Uncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and intelligence.
JSONCachingStreaming$0.3165in / 1M$0.5275out / 1M131Kcontext1provider - DeepSeek V3deepseek/deepseek-chat
DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...
ToolsJSONCaching+1$0.2716in / 1M$1.09out / 1M164Kcontext1provider - DeepSeek V3 0324deepseek/deepseek-chat-v3-0324
DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the DeepSeek V3 model and performs really well...
ToolsJSONCaching+1$0.2638in / 1M$1.06out / 1M164Kcontext1provider - DeepSeek V3.1deepseek/deepseek-chat-v3.1
DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...
ReasoningToolsJSON+2$0.5803in / 1M$1.74out / 1M164Kcontext1provider - DeepSeek V3.1 Terminusdeepseek/deepseek-v3.1-terminus
DeepSeek-V3.1 Terminus is an update to DeepSeek V3.1 that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's...
ReasoningToolsJSON+2$0.2849in / 1M$1.06out / 1M164Kcontext1provider - DeepSeek V3.2 Expdeepseek/deepseek-v3.2-exp
DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...
ReasoningToolsJSON+2$0.2849in / 1M$0.4326out / 1M164Kcontext1provider - DeepSeek V4 Flashdeepseek/deepseek-v4-flash
DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...
ReasoningToolsJSON+2$0.0634in / 1M$0.1267out / 1M1.0Mcontext1provider - DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-0731
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.
ReasoningToolsJSON+2$0.0844in / 1M$0.1899out / 1M1.0Mcontext1provider - ERNIE 4.5 VL 424B A47Bbaidu/ernie-4.5-vl-424b-a47b
ERNIE-4.5-VL-424B-A47B is a multimodal Mixture-of-Experts (MoE) model from Baidu’s ERNIE 4.5 series, featuring 424B total parameters with 47B active per token. It is trained jointly on text and image data...
VisionReasoningCaching+1$0.4431in / 1M$1.32out / 1M123Kcontext1provider - Fugu Ultrasakana/fugu-ultra
Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...
VisionReasoningTools+3$5.28in / 1M$31.65out / 1M1Mcontext1provider - Gemini 2.5 Flashgoogle/gemini-2.5-flash
The previous-generation price-performance model. Still a cheap default for high-volume work that needs reasoning.
VisionReasoningTools+3$0.3000in / 1M$2.50out / 1M1.0Mcontext1provider - Gemini 2.5 Flash-Litegoogle/gemini-2.5-flash-lite
Google's cheapest multimodal model. Classification, extraction and other short, high-frequency calls.
VisionReasoningTools+3$0.1000in / 1M$0.4000out / 1M1.0Mcontext1provider - Gemini 2.5 Progoogle/gemini-2.5-pro
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...
VisionReasoningTools+3$1.32in / 1M$10.55out / 1M1.0Mcontext1provider - Gemini 2.5 Pro Preview 05-06google/gemini-2.5-pro-preview-05-06
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...
VisionReasoningTools+3$1.32in / 1M$10.55out / 1M1.0Mcontext1provider - Gemini 2.5 Pro Preview 06-05google/gemini-2.5-pro-preview
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...
VisionReasoningTools+3$1.32in / 1M$10.55out / 1M1.0Mcontext1provider - Gemini 3 Flash Previewgoogle/gemini-3-flash-preview
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...
VisionReasoningTools+3$0.5275in / 1M$3.17out / 1M1.0Mcontext1provider - Gemini 3.1 Flash Litegoogle/gemini-3.1-flash-lite
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...
VisionReasoningTools+3$0.2638in / 1M$1.58out / 1M1.0Mcontext1provider - Gemini 3.1 Flash Lite Previewgoogle/gemini-3.1-flash-lite-preview
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...
VisionReasoningTools+3$0.2638in / 1M$1.58out / 1M1.0Mcontext1provider - Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-preview
Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...
VisionReasoningTools+3$2.11in / 1M$12.66out / 1M1.0Mcontext1provider - Gemini 3.1 Pro Preview Custom Toolsgoogle/gemini-3.1-pro-preview-customtools
Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash tool when more efficient third-party...
VisionReasoningTools+3$2.11in / 1M$12.66out / 1M1.0Mcontext1provider - Gemini 3.5 Flashgoogle/gemini-3.5-flash
Google's most capable Flash model, aimed at sustained agentic and coding work over a 1M-token window.
VisionReasoningTools+3$1.50in / 1M$9.00out / 1M1.0Mcontext1provider - Gemini 3.5 Flash-Litegoogle/gemini-3.5-flash-lite
The low-latency 3.5 model, built for high-throughput subagent work and document parsing.
VisionReasoningTools+2$0.3000in / 1M$2.50out / 1M1.0Mcontext1provider - Gemini 3.6 Flashgoogle/gemini-3.6-flash
Google's current Flash model: speed and intelligence balanced for agentic and multimodal work, with a 1M-token window.
VisionReasoningTools+3$1.50in / 1M$7.50out / 1M1.0Mcontext1provider - Gemma 2 27Bgoogle/gemma-2-27b-it
Gemma 2 27B by Google is an open model built from the same research and technology used to create the Gemini models. Gemma models are well-suited for a variety of...
JSONCachingStreaming$0.6858in / 1M$0.6858out / 1M8Kcontext1provider - Gemma 3 12Bgoogle/gemma-3-12b-it
Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...
VisionToolsJSON+2$0.0528in / 1M$0.1583out / 1M131Kcontext1provider - Gemma 3 27Bgoogle/gemma-3-27b-it
Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...
VisionToolsJSON+2$0.0844in / 1M$0.4748out / 1M262Kcontext1provider - Gemma 3 4Bgoogle/gemma-3-4b-it
Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...
VisionJSONCaching+1$0.0528in / 1M$0.1055out / 1M131Kcontext1provider - Gemma 3n 4Bgoogle/gemma-3n-e4b-it
Gemma 3n E4B-it is optimized for efficient execution on mobile and low-resource devices, such as phones, laptops, and tablets. It supports multimodal inputs (including text, visual data, and audio) enabling diverse tasks...
JSONCachingStreaming$0.0633in / 1M$0.1266out / 1M33Kcontext1provider - Gemma 4 26B A4Bgoogle/gemma-4-26b-a4b-it
Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference, delivering near-31B quality at...
VisionReasoningTools+3$0.0739in / 1M$0.3587out / 1M262Kcontext1provider - Gemma 4 31Bgoogle/gemma-4-31b-it
Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...
VisionReasoningTools+3$0.1055in / 1M$0.3587out / 1M262Kcontext1provider - GLM 4.5zai/glm-4.5
GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly...
ReasoningToolsJSON+2$0.6330in / 1M$2.32out / 1M131Kcontext1provider - GLM 4.5 Airzai/glm-4.5-air
GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter...
ReasoningToolsCaching+1$0.1372in / 1M$0.8968out / 1M131Kcontext1provider - GLM 4.5Vzai/glm-4.5v
GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding,...
VisionReasoningTools+3$0.6330in / 1M$1.90out / 1M66Kcontext1provider - GLM 4.6zai/glm-4.6
Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...
ReasoningToolsJSON+2$0.5275in / 1M$2.11out / 1M205Kcontext1provider - GLM 4.6Vzai/glm-4.6v
GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts...
VisionReasoningTools+3$0.3165in / 1M$0.9495out / 1M131Kcontext1provider - GLM 4.7zai/glm-4.7
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...
ReasoningToolsJSON+2$0.4220in / 1M$1.85out / 1M205Kcontext1provider - GLM 4.7 Flashzai/glm-4.7-flash
As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning,...
ReasoningToolsJSON+2$0.0633in / 1M$0.4220out / 1M203Kcontext1provider - GLM 5zai/glm-5
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...
ReasoningToolsJSON+2$0.6330in / 1M$2.03out / 1M205Kcontext1provider - GLM 5 Turbozai/glm-5-turbo
GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows...
ReasoningToolsJSON+2$1.27in / 1M$4.22out / 1M203Kcontext1provider - GLM 5.1zai/glm-5.1
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...
ReasoningToolsJSON+2$1.02in / 1M$3.20out / 1M205Kcontext1provider - GLM 5V Turbozai/glm-5v-turbo
GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, complex coding,...
VisionReasoningTools+3$1.27in / 1M$4.22out / 1M203Kcontext1provider - GPT Chat Latestopenai/gpt-chat-latest
GPT Chat Latest points to OpenAI's stable API alias chat-latest that always resolves to the latest Instant chat model used in ChatGPT. As OpenAI rolls out new Instant model updates...
VisionToolsJSON+2$5.28in / 1M$31.65out / 1M400Kcontext1provider - GPT-3.5 Turboopenai/gpt-3.5-turbo
GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks. Training data up to Sep 2021.
ToolsJSONCaching+1$0.5275in / 1M$1.58out / 1M16Kcontext1provider - GPT-3.5 Turbo (older v0613)openai/gpt-3.5-turbo-0613
GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks. Training data up to Sep 2021.
ToolsJSONCaching+1$1.06in / 1M$2.11out / 1M4Kcontext1provider - GPT-3.5 Turbo 16kopenai/gpt-3.5-turbo-16k
This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up...
ToolsJSONCaching+1$3.17in / 1M$4.22out / 1M16Kcontext1provider - GPT-3.5 Turbo Instructopenai/gpt-3.5-turbo-instruct
This model is a variant of GPT-3.5 Turbo tuned for instructional prompts and omitting chat-related optimizations. Training data: up to Sep 2021.
JSONCachingStreaming$1.58in / 1M$2.11out / 1M4Kcontext1provider - GPT-4openai/gpt-4
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...
ToolsJSONCaching+1$31.65in / 1M$63.30out / 1M8Kcontext1provider - GPT-4 Turboopenai/gpt-4-turbo
The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Training data: up to December 2023.
VisionToolsJSON+2$10.55in / 1M$31.65out / 1M128Kcontext1provider - GPT-4 Turbo Previewopenai/gpt-4-turbo-preview
The preview GPT-4 model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. Training data: up to Dec 2023. Note: heavily rate limited by OpenAI while...
ToolsJSONCaching+1$10.55in / 1M$31.65out / 1M128Kcontext1provider - GPT-4.1 Nanoopenai/gpt-4.1-nano
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...
VisionToolsJSON+2$0.1055in / 1M$0.4220out / 1M1.0Mcontext1provider - GPT-4o (2024-05-13)openai/gpt-4o-2024-05-13
GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of GPT-4 Turbo while being twice as...
VisionToolsJSON+2$5.28in / 1M$15.83out / 1M128Kcontext1provider - GPT-4o (2024-08-06)openai/gpt-4o-2024-08-06
The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the responeformat. Read more here. GPT-4o ("o" for "omni") is...
VisionToolsJSON+2$2.64in / 1M$10.55out / 1M128Kcontext1provider - GPT-4o (2024-11-20)openai/gpt-4o-2024-11-20
The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance & readability. It’s also better at working with uploaded...
VisionToolsJSON+2$2.64in / 1M$10.55out / 1M128Kcontext1provider - GPT-4o-mini (2024-07-18)openai/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 text outputs. As their most advanced small model, it is many multiples more affordable...
VisionToolsJSON+2$0.1583in / 1M$0.6330out / 1M128Kcontext1provider - GPT-5openai/gpt-5
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...
VisionReasoningTools+3$1.32in / 1M$10.55out / 1M400Kcontext1provider - GPT-5 Proopenai/gpt-5-pro
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...
VisionReasoningTools+3$15.83in / 1M$126.60out / 1M400Kcontext1provider - GPT-5.1-Codexopenai/gpt-5.1-codex
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....
VisionReasoningTools+3$1.32in / 1M$10.55out / 1M400Kcontext1provider - GPT-5.1-Codex-Maxopenai/gpt-5.1-codex-max
GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic...
VisionReasoningTools+3$1.32in / 1M$10.55out / 1M400Kcontext1provider - GPT-5.1-Codex-Miniopenai/gpt-5.1-codex-mini
GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex
VisionReasoningTools+3$0.2638in / 1M$2.11out / 1M400Kcontext1provider - GPT-5.2openai/gpt-5.2
GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly...
VisionReasoningTools+3$1.85in / 1M$14.77out / 1M400Kcontext1provider - GPT-5.2 Chatopenai/gpt-5.2-chat
GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on...
VisionToolsJSON+2$1.85in / 1M$14.77out / 1M128Kcontext1provider - GPT-5.2 Proopenai/gpt-5.2-pro
GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning,...
VisionReasoningTools+3$22.16in / 1M$177.24out / 1M400Kcontext1provider - GPT-5.2-Codexopenai/gpt-5.2-codex
GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....
VisionReasoningTools+3$1.85in / 1M$14.77out / 1M400Kcontext1provider - GPT-5.3-Codexopenai/gpt-5.3-codex
GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2. It achieves state-of-the-art results...
VisionReasoningTools+3$1.85in / 1M$14.77out / 1M400Kcontext1provider - GPT-5.4openai/gpt-5.4
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...
VisionReasoningTools+3$2.64in / 1M$15.83out / 1M1.1Mcontext1provider - GPT-5.4 Miniopenai/gpt-5.4-mini
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,...
VisionReasoningTools+3$0.7913in / 1M$4.75out / 1M400Kcontext1provider - GPT-5.4 Nanoopenai/gpt-5.4-nano
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...
VisionReasoningTools+3$0.2110in / 1M$1.32out / 1M400Kcontext1provider - GPT-5.4 Proopenai/gpt-5.4-pro
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...
VisionReasoningTools+3$31.65in / 1M$189.90out / 1M1.1Mcontext1provider - GPT-5.5openai/gpt-5.5
GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...
VisionReasoningTools+3$5.28in / 1M$31.65out / 1M1.1Mcontext1provider - GPT-5.5 Proopenai/gpt-5.5-pro
GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for...
VisionReasoningTools+3$31.65in / 1M$189.90out / 1M1.1Mcontext1provider - GPT-5.6 Luna Proopenai/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 pro for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoningreasoning-mode
VisionReasoningTools+3$0.2110in / 1M$1.27out / 1M1.1Mcontext1provider - GPT-5.6 Sol Proopenai/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 for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoningreasoning-mode
VisionReasoningTools+3$4.22in / 1M$21.10out / 1M1.1Mcontext1provider - GPT-5.6 Terra Proopenai/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 pro for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoningreasoning-mode
VisionReasoningTools+3$2.11in / 1M$12.66out / 1M1.1Mcontext1provider - gpt-oss-safeguard-20bopenai/gpt-oss-safeguard-20b
gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust...
ReasoningToolsJSON+2$0.0791in / 1M$0.3165out / 1M131Kcontext1provider - Granite 4.0 Microibm-granite/granite-4.0-h-micro
Granite-4.0-H-Micro is a 3B parameter from the Granite 4 family of models. These models are the latest in a series of models released by IBM. They are fine-tuned for long...
JSONCachingStreaming$0.0179in / 1M$0.1182out / 1M131Kcontext1provider - Granite 4.1 8Bibm-granite/granite-4.1-8b
Granite 4.1 8B is a dense, decoder-only 8-billion-parameter language model from IBM, part of the Granite 4.1 family. It supports a 131K-token context window and is designed for enterprise tasks...
ToolsJSONCaching+1$0.0528in / 1M$0.1055out / 1M131Kcontext1provider - Grok 4.20x-ai/grok-4.20
Grok 4.20 is a reasoning model from xAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...
VisionReasoningTools+3$1.32in / 1M$2.64out / 1M2Mcontext1provider - Grok 4.20 Multi-Agentx-ai/grok-4.20-multi-agent
Grok 4.20 Multi-Agent is a variant of xAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information...
VisionReasoningJSON+2$1.32in / 1M$2.64out / 1M2Mcontext1provider - Grok 4.3x-ai/grok-4.3
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...
VisionReasoningTools+3$1.32in / 1M$2.64out / 1M1Mcontext1provider - Grok 4.5x-ai/grok-4.5
Grok 4.5 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.
VisionReasoningTools+3$2.11in / 1M$6.33out / 1M500Kcontext1provider - Grok Build 0.1x-ai/grok-build-0.1
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...
VisionReasoningTools+3$1.06in / 1M$2.11out / 1M256Kcontext1provider - Hermes 3 405B Instructnousresearch/hermes-3-llama-3.1-405b
Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...
JSONCachingStreaming$1.06in / 1M$1.06out / 1M131Kcontext1provider - Hermes 3 70B Instructnousresearch/hermes-3-llama-3.1-70b
Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...
JSONCachingStreaming$0.7385in / 1M$0.7385out / 1M131Kcontext1provider - Hermes 4 405Bnousresearch/hermes-4-405b
Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...
ReasoningJSONCaching+1$1.06in / 1M$3.17out / 1M131Kcontext1provider - Hermes 4 70Bnousresearch/hermes-4-70b
Hermes 4 70B is a hybrid reasoning model from Nous Research, built on Meta-Llama-3.1-70B. It introduces the same hybrid mode as the larger 405B release, allowing the model to either...
ReasoningJSONCaching+1$0.1372in / 1M$0.4220out / 1M131Kcontext1provider - Hunyuan A13B Instructtencent/hunyuan-a13b-instruct
Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark...
ReasoningJSONCaching+1$0.1477in / 1M$0.6014out / 1M131Kcontext1provider - Hy3tencent/hy3
Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...
ReasoningToolsJSON+2$0.1393in / 1M$0.5570out / 1M262Kcontext1provider - Hy3 previewtencent/hy3-preview
Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to...
ReasoningToolsCaching+1$0.1899in / 1M$0.6330out / 1M262Kcontext1provider - Inklingthinkingmachines/inkling
Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...
VisionReasoningTools+3$1.00in / 1M$4.27out / 1M1.0Mcontext1provider - Inkling Smallthinkingmachines/inkling-small
Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...
VisionReasoningTools+2$0.4748in / 1M$1.27out / 1M524Kcontext1provider - KAT-Coder-Air V2.5kwaipilot/kat-coder-air-v2.5
KAT-Coder-Air V2.5 is a flagship-level Agentic Coding model that can directly hand over an entire issue or an entire business workflow to it, allowing it to autonomously locate and make...
ToolsJSONCaching+1$0.1583in / 1M$0.6330out / 1M256Kcontext1provider - KAT-Coder-Pro V2kwaipilot/kat-coder-pro-v2
KAT-Coder-Pro V2 is the latest high-performance model in KwaiKAT’s KAT-Coder series, designed for complex enterprise-grade software engineering and SaaS integration. It builds on the agentic coding strengths of earlier versions,...
ToolsJSONCaching+1$0.3165in / 1M$1.27out / 1M262Kcontext1provider - KAT-Coder-Pro V2.5kwaipilot/kat-coder-pro-v2.5
KAT-Coder-Pro V2.5 is a flagship-level Agentic Coding model that can directly hand over an entire issue or an entire business workflow to it, allowing it to autonomously locate and make...
ToolsJSONCaching+1$0.7807in / 1M$3.12out / 1M256Kcontext1provider - Kimi K2 0711moonshot/kimi-k2
Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...
ToolsCachingStreaming$0.6014in / 1M$2.43out / 1M131Kcontext1provider - Kimi K2 0905moonshot/kimi-k2-0905
Kimi K2 0905 is the September update of Kimi K2 0711. It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...
ToolsJSONCaching+1$0.6330in / 1M$2.64out / 1M262Kcontext1provider - Kimi K2 Thinkingmoonshot/kimi-k2-thinking
Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...
ReasoningToolsJSON+2$0.6330in / 1M$2.64out / 1M262Kcontext1provider - Kimi K2.5moonshot/kimi-k2.5
Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...
VisionReasoningTools+3$0.4748in / 1M$2.37out / 1M262Kcontext1provider - Kimi K2.6moonshot/kimi-k2.6
Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...
VisionReasoningTools+3$0.5713in / 1M$2.41out / 1M262Kcontext1provider - Kimi K2.7 Codemoonshot/kimi-k2.7-code
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...
VisionReasoningTools+3$0.7069in / 1M$3.59out / 1M262Kcontext1provider - Laguna S 2.1poolside/laguna-s-2.1
Laguna S 2.1 is the latest coding agent model from Poolside. Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and...
ReasoningToolsCaching+1$0.0950in / 1M$0.1899out / 1M1.0Mcontext1provider - Laguna XS 2.1poolside/laguna-xs-2.1
Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from Poolside and a step forward from their Laguna XS.2 model (released in April 2026). It combines...
ReasoningToolsCaching+1$0.0633in / 1M$0.1266out / 1M262Kcontext1provider - Ling-2.6-1Tinclusionai/ling-2.6-1t
Ling-2.6-1T is an instant (instruct) model from inclusionAI and the company’s trillion-parameter flagship, designed for real-world agents that require fast execution and high efficiency at scale. It uses a “fast...
ToolsJSONCaching+1$0.0791in / 1M$0.6594out / 1M262Kcontext1provider - Ling-2.6-flashinclusionai/ling-2.6-flash
Ling-2.6-flash is an instant (instruct) model from inclusionAI with 104B total parameters and 7.4B active parameters, designed for real-world agents that require fast responses, strong execution, and high token efficiency....
ToolsJSONCaching+1$0.0106in / 1M$0.0317out / 1M262Kcontext1provider - Llama 3 8B Lunarissao10k/l3-lunaris-8b
Lunaris 8B is a versatile generalist and roleplaying model based on Llama 3. It's a strategic merge of multiple models, designed to balance creativity with improved logic and general knowledge....
JSONCachingStreaming$0.0422in / 1M$0.0528out / 1M8Kcontext1provider - Llama 3.1 70B Instructmeta/llama-3.1-70b-instruct
Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases. It has demonstrated strong...
ToolsJSONCaching+1$0.4220in / 1M$0.4220out / 1M131Kcontext1provider - Llama 3.1 Euryale 70B v2.2sao10k/l3.1-euryale-70b
Euryale L3.1 70B v2.2 is a model focused on creative roleplay from Sao10k. It is the successor of Euryale L3 70B v2.1.
ToolsJSONCaching+1$0.8968in / 1M$0.8968out / 1M131Kcontext1provider - Llama 3.2 1B Instructmeta/llama-3.2-1b-instruct
Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate...
CachingStreaming$0.0285in / 1M$0.2121out / 1M60Kcontext1provider - Llama 3.2 3B Instructmeta/llama-3.2-3b-instruct
Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it...
JSONCachingStreaming$0.0528in / 1M$0.3482out / 1M131Kcontext1provider - Llama 3.3 Euryale 70Bsao10k/l3.3-euryale-70b
Euryale L3.3 70B is a model focused on creative roleplay from Sao10k. It is the successor of Euryale L3 70B v2.2.
JSONCachingStreaming$0.6858in / 1M$0.7913out / 1M131Kcontext1provider - Llama 4 Maverickmeta/llama-4-maverick
Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...
VisionToolsJSON+2$0.2110in / 1M$0.8440out / 1M1.0Mcontext1provider - Llama 4 Scoutmeta/llama-4-scout
Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...
VisionToolsJSON+2$0.1055in / 1M$0.3165out / 1M1.3Mcontext1provider - Llama Guard 4 12Bmeta/llama-guard-4-12b
Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM...
VisionJSONCaching+1$0.1899in / 1M$0.1899out / 1M1.0Mcontext1provider - LongCat 2.0meituan/longcat-2.0
LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total. It is suited for coding, repository-level changes, long-horizon problem solving, and agentic...
ReasoningToolsCaching+1$0.3165in / 1M$1.27out / 1M1.0Mcontext1provider - Magnum v4 72Banthracite-org/magnum-v4-72b
This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://openrouter.ai/anthropic/claude-3-opus). The model is fine-tuned on top of Qwen2.5 72B.
JSONCachingStreaming$3.17in / 1M$5.28out / 1M16Kcontext1provider - Mercury 2inception/mercury-2
Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving...
ReasoningToolsJSON+2$0.2638in / 1M$0.7913out / 1M128Kcontext1provider - MiMo-V2.5xiaomi/mimo-v2.5
MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...
VisionReasoningTools+3$0.1477in / 1M$0.2954out / 1M1.1Mcontext1provider - MiMo-V2.5-Proxiaomi/mimo-v2.5-pro
MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro....
ReasoningToolsJSON+2$0.4589in / 1M$0.9179out / 1M1.1Mcontext1provider - MiniMax M1minimax/minimax-m1
MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom "lightning attention" mechanism, allowing it...
ReasoningToolsCaching+1$0.5803in / 1M$2.32out / 1M1Mcontext1provider - MiniMax M2minimax/minimax-m2
MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning,...
ReasoningToolsJSON+2$0.2690in / 1M$1.08out / 1M205Kcontext1provider - MiniMax M2-herminimax/minimax-m2-her
MiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn conversations. Designed to stay consistent in tone and personality, it supports rich message...
CachingStreaming$0.3165in / 1M$1.27out / 1M66Kcontext1provider - MiniMax M2.1minimax/minimax-m2.1
MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world...
ReasoningToolsJSON+2$0.3165in / 1M$1.27out / 1M205Kcontext1provider - MiniMax M2.5minimax/minimax-m2.5
MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...
ReasoningToolsJSON+2$0.2849in / 1M$1.14out / 1M205Kcontext1provider - MiniMax M2.7minimax/minimax-m2.7
MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent...
ReasoningToolsJSON+2$0.3165in / 1M$1.27out / 1M205Kcontext1provider - MiniMax-01minimax/minimax-01
MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billion parameters, with 45.9 billion parameters activated per inference, and can handle a context...
VisionCachingStreaming$0.2110in / 1M$1.16out / 1M1.0Mcontext1provider - Ministral 3 14B 2512mistralai/ministral-14b-2512
The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language...
VisionToolsJSON+2$0.2110in / 1M$0.2110out / 1M262Kcontext1provider - Ministral 3 3B 2512mistralai/ministral-3b-2512
The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.
VisionToolsJSON+2$0.1055in / 1M$0.1055out / 1M131Kcontext1provider - Ministral 3 8B 2512mistralai/ministral-8b-2512
A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.
VisionToolsJSON+2$0.1583in / 1M$0.1583out / 1M262Kcontext1provider - Mistral Largemistralai/mistral-large
This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement here....
ToolsJSONCaching+1$2.11in / 1M$6.33out / 1M128Kcontext1provider - Mistral Large 2407mistralai/mistral-large-2407
This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement here....
ToolsJSONCaching+1$2.11in / 1M$6.33out / 1M131Kcontext1provider - Mistral Large 3 2512mistralai/mistral-large-2512
Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.
VisionToolsJSON+2$0.5275in / 1M$1.58out / 1M262Kcontext1provider - Mistral Medium 3mistralai/mistral-medium-3
Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost...
VisionToolsJSON+2$0.4220in / 1M$2.11out / 1M131Kcontext1provider - Mistral Medium 3.1mistralai/mistral-medium-3.1
Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances...
VisionToolsJSON+2$0.4220in / 1M$2.11out / 1M131Kcontext1provider - Mistral Medium 3.5mistralai/mistral-medium-3-5
Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...
VisionReasoningTools+3$1.58in / 1M$7.91out / 1M262Kcontext1provider - Mistral Nemomistralai/mistral-nemo
A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,...
ToolsJSONCaching+1$0.0200in / 1M$0.0317out / 1M131Kcontext1provider - Mistral Small 3mistralai/mistral-small-24b-instruct-2501
Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed...
JSONCachingStreaming$0.0528in / 1M$0.0844out / 1M33Kcontext1provider - Mistral Small 3.1 24Bmistralai/mistral-small-3.1-24b-instruct
Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and...
VisionCachingStreaming$0.3703in / 1M$0.5855out / 1M128Kcontext1provider - Mistral Small 3.2 24Bmistralai/mistral-small-3.2-24b-instruct
Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on...
VisionToolsJSON+2$0.0791in / 1M$0.2110out / 1M256Kcontext1provider - Mistral Small 4mistralai/mistral-small-2603
Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...
VisionReasoningTools+3$0.1583in / 1M$0.6330out / 1M262Kcontext1provider - Mixtral 8x22B Instructmistralai/mixtral-8x22b-instruct
Mistral's official instruct fine-tuned version of Mixtral 8x22B. It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding,...
ToolsJSONCaching+1$2.11in / 1M$6.33out / 1M66Kcontext1provider - Morph V3 Fastmorph/morph-v3-fast
Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code transformations. The model requires the prompt to be in the following format: <instruction{instruction}</instruction <code{initialcode}</code <update{editsnippet}</update...
CachingStreaming$0.8440in / 1M$1.27out / 1M82Kcontext1provider - Morph V3 Largemorph/morph-v3-large
Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations. The model requires the prompt to be in the following format: <instruction{instruction}</instruction <code{initialcode}</code...
JSONCachingStreaming$0.9495in / 1M$2.00out / 1M262Kcontext1provider - Muse Spark 1.1meta/muse-spark-1.1
Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with a 1M-token context...
VisionReasoningTools+3$1.32in / 1M$4.48out / 1M1.0Mcontext1provider - MythoMax 13Bgryphe/mythomax-l2-13b
One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay. merge
JSONCachingStreaming$0.0633in / 1M$0.0633out / 1M8Kcontext1provider - Nemotron 3 Nano 30B A3Bnvidia/nemotron-3-nano-30b-a3b
NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...
ReasoningToolsJSON+2$0.0528in / 1M$0.2110out / 1M262Kcontext1provider - Nemotron 3 Supernvidia/nemotron-3-super-120b-a12b
NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...
ReasoningToolsJSON+2$0.0897in / 1M$0.4220out / 1M1Mcontext1provider - Nemotron 3 Ultranvidia/nemotron-3-ultra-550b-a55b
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...
ReasoningToolsJSON+2$0.6330in / 1M$3.80out / 1M512Kcontext1provider - Nex-N2-Mininex-agi/nex-n2-mini
Nex-N2-Mini is an open-source agentic mixture-of-experts model from Nex AGI, the smaller sibling in the Nex-N2 series. It accepts text and image input and is built for coding, tool use,...
VisionReasoningTools+3$0.0264in / 1M$0.1055out / 1M262Kcontext1provider - Nex-N2-Pronex-agi/nex-n2-pro
Nex-N2-Pro is an agentic mixture-of-experts model from Nex AGI, with 17B active parameters out of 397B total. Built on the Qwen3.5 architecture, it accepts text and image input and produces...
VisionReasoningTools+2$0.2638in / 1M$1.06out / 1M262Kcontext1provider - Nova 2 Liteamazon/nova-2-lite-v1
Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilities in processing...
VisionReasoningTools+2$0.3165in / 1M$2.64out / 1M1Mcontext1provider - Nova Lite 1.0amazon/nova-lite-v1
Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite...
VisionToolsCaching+1$0.0633in / 1M$0.2532out / 1M300Kcontext1provider - Nova Micro 1.0amazon/nova-micro-v1
Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length...
ToolsCachingStreaming$0.0369in / 1M$0.1477out / 1M128Kcontext1provider - Nova Premier 1.0amazon/nova-premier-v1
Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models.
VisionToolsCaching+1$2.64in / 1M$13.19out / 1M1Mcontext1provider - Nova Pro 1.0amazon/nova-pro-v1
Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December...
VisionToolsCaching+1$0.8440in / 1M$3.38out / 1M300Kcontext1provider - o1openai/o1
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...
VisionReasoningTools+3$15.83in / 1M$63.30out / 1M200Kcontext1provider - o1-proopenai/o1-pro
The o1 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o1-pro model uses more compute to think harder and provide...
VisionReasoningJSON+2$158.25in / 1M$633.00out / 1M200Kcontext1provider - o3 Miniopenai/o3-mini
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 reasoningeffort parameter, which can be set to...
ReasoningToolsJSON+2$1.16in / 1M$4.64out / 1M200Kcontext1provider - o3 Mini Highopenai/o3-mini-high
OpenAI o3-mini-high is the same model as o3-mini with reasoningeffort set to high. o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and...
ReasoningToolsJSON+2$1.16in / 1M$4.64out / 1M200Kcontext1provider - o3 Proopenai/o3-pro
The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently...
VisionReasoningTools+3$21.10in / 1M$84.40out / 1M200Kcontext1provider - o4 Mini Highopenai/o4-mini-high
OpenAI o4-mini-high is the same model as o4-mini with reasoningeffort set to high. OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining...
VisionReasoningTools+3$1.16in / 1M$4.64out / 1M200Kcontext1provider - Olmo 3 32B Thinkallenai/olmo-3-32b-think
Olmo 3 32B Think is a large-scale, 32-billion-parameter model purpose-built for deep reasoning, complex logic chains and advanced instruction-following scenarios. Its capacity enables strong performance on demanding evaluation tasks and...
ReasoningJSONCaching+1$0.1583in / 1M$0.5275out / 1M66Kcontext1provider - Palmyra X5writer/palmyra-x5
Palmyra X5 is Writer's most advanced model, purpose-built for building and scaling AI agents across the enterprise. It delivers industry-leading speed and efficiency on context windows up to 1 million...
CachingStreaming$0.6330in / 1M$6.33out / 1M1.0Mcontext1provider - Perceptron Mk1perceptron/perceptron-mk1
Perceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language model for video and embodied reasoning. It accepts image and video inputs paired with natural language queries, and produces detailed visual understanding...
VisionReasoningJSON+2$0.1583in / 1M$1.58out / 1M33Kcontext1provider - Phi 4microsoft/phi-4
Microsoft Research Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...
JSONCachingStreaming$0.0739in / 1M$0.1477out / 1M16Kcontext1provider - Qwen Plus 0728qwen/qwen-plus-2025-07-28
Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.
ToolsJSONCaching+1$0.2743in / 1M$0.8229out / 1M1Mcontext1provider - Qwen Plus 0728 (thinking)qwen/qwen-plus-2025-07-28:thinking
Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost combination.
ReasoningToolsJSON+2$0.2743in / 1M$0.8229out / 1M1Mcontext1provider - Qwen-Plusqwen/qwen-plus
Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.
ToolsJSONCaching+1$0.2743in / 1M$0.8229out / 1M1Mcontext1provider - Qwen2.5 72B Instructqwen/qwen-2.5-72b-instruct
Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...
ToolsJSONCaching+1$0.3798in / 1M$0.4220out / 1M33Kcontext1provider - Qwen2.5 7B Instructqwen/qwen-2.5-7b-instruct
Qwen2.5 7B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...
ToolsJSONCaching+1$0.1055in / 1M$0.2110out / 1M33Kcontext1provider - Qwen2.5 Coder 32B Instructqwen/qwen-2.5-coder-32b-instruct
Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Significantly improvements in code generation, code reasoning...
CachingStreaming$0.6963in / 1M$1.06out / 1M33Kcontext1provider - Qwen2.5 VL 72B Instructqwen/qwen2.5-vl-72b-instruct
Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.
VisionJSONCaching+1$0.8440in / 1M$1.06out / 1M128Kcontext1provider - Qwen3 14Bqwen/qwen3-14b
Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for...
ReasoningToolsJSON+2$0.1266in / 1M$0.2532out / 1M131Kcontext1provider - Qwen3 235B A22Bqwen/qwen3-235b-a22b
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...
ReasoningToolsJSON+2$0.4800in / 1M$1.92out / 1M131Kcontext1provider - Qwen3 235B A22B Instruct 2507qwen/qwen3-235b-a22b-2507
Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,...
ToolsJSONCaching+1$0.0950in / 1M$0.5803out / 1M262Kcontext1provider - Qwen3 235B A22B Thinking 2507qwen/qwen3-235b-a22b-thinking-2507
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...
ReasoningToolsJSON+2$0.2427in / 1M$2.43out / 1M262Kcontext1provider - Qwen3 30B A3Bqwen/qwen3-30b-a3b
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...
ReasoningToolsJSON+2$0.1372in / 1M$0.5486out / 1M131Kcontext1provider - Qwen3 30B A3B Instruct 2507qwen/qwen3-30b-a3b-instruct-2507
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...
ToolsJSONCaching+1$0.0508in / 1M$0.2037out / 1M262Kcontext1provider - Qwen3 30B A3B Thinking 2507qwen/qwen3-30b-a3b-thinking-2507
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...
ReasoningToolsJSON+2$0.2110in / 1M$2.53out / 1M82Kcontext1provider - Qwen3 8Bqwen/qwen3-8b
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,...
ReasoningToolsJSON+2$0.1234in / 1M$0.4800out / 1M131Kcontext1provider - Qwen3 Coder 30B A3B Instructqwen/qwen3-coder-30b-a3b-instruct
Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...
ToolsJSONCaching+1$0.0739in / 1M$0.2954out / 1M262Kcontext1provider - Qwen3 Coder 480B A35Bqwen/qwen3-coder
Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...
ToolsJSONCaching+1$0.3165in / 1M$1.06out / 1M262Kcontext1provider - Qwen3 Coder Flashqwen/qwen3-coder-flash
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...
ToolsJSONCaching+1$0.2057in / 1M$1.03out / 1M1Mcontext1provider - Qwen3 Coder Nextqwen/qwen3-coder-next
Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per...
ToolsJSONCaching+1$0.1266in / 1M$0.8440out / 1M262Kcontext1provider - Qwen3 Coder Plusqwen/qwen3-coder-plus
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...
ToolsJSONCaching+1$0.6858in / 1M$3.43out / 1M1Mcontext1provider - Qwen3 Maxqwen/qwen3-max
Qwen3-Max is an updated release built on the Qwen3 series, offering major improvements in reasoning, instruction following, multilingual support, and long-tail knowledge coverage compared to the January 2025 version. It...
ToolsJSONCaching+1$0.8229in / 1M$4.11out / 1M262Kcontext1provider - Qwen3 Max Thinkingqwen/qwen3-max-thinking
Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi-step reasoning. By significantly scaling model capacity and reinforcement learning compute, it...
ReasoningToolsJSON+2$0.8229in / 1M$4.11out / 1M262Kcontext1provider - Qwen3 Next 80B A3B Instructqwen/qwen3-next-80b-a3b-instruct
Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...
ToolsJSONCaching+1$0.1055in / 1M$1.16out / 1M262Kcontext1provider - Qwen3 Next 80B A3B Thinkingqwen/qwen3-next-80b-a3b-thinking
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...
ReasoningToolsJSON+2$0.1583in / 1M$1.27out / 1M262Kcontext1provider - Qwen3 VL 235B A22B Instructqwen/qwen3-vl-235b-a22b-instruct
Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...
VisionToolsJSON+2$0.2216in / 1M$2.00out / 1M262Kcontext1provider - Qwen3 VL 235B A22B Thinkingqwen/qwen3-vl-235b-a22b-thinking
Qwen3-VL-235B-A22B Thinking is a multimodal model that unifies strong text generation with visual understanding across images and video. The Thinking model is optimized for multimodal reasoning in STEM and math....
VisionReasoningTools+3$0.4220in / 1M$4.22out / 1M131Kcontext1provider - Qwen3 VL 30B A3B Instructqwen/qwen3-vl-30b-a3b-instruct
Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception...
VisionToolsJSON+2$0.1372in / 1M$0.5486out / 1M262Kcontext1provider - Qwen3 VL 30B A3B Thinkingqwen/qwen3-vl-30b-a3b-thinking
Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex tasks. It excels...
VisionReasoningTools+3$0.2110in / 1M$2.53out / 1M262Kcontext1provider - Qwen3 VL 32B Instructqwen/qwen3-vl-32b-instruct
Qwen3-VL-32B-Instruct is a large-scale multimodal vision-language model designed for high-precision understanding and reasoning across text, images, and video. With 32 billion parameters, it combines deep visual perception with advanced text...
VisionToolsJSON+2$0.1097in / 1M$0.4389out / 1M131Kcontext1provider - Qwen3 VL 8B Instructqwen/qwen3-vl-8b-instruct
Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Interleaved-MRoPE for long-horizon...
VisionToolsJSON+2$0.1234in / 1M$0.4800out / 1M262Kcontext1provider - Qwen3 VL 8B Thinkingqwen/qwen3-vl-8b-thinking
Qwen3-VL-8B-Thinking is the reasoning-optimized variant of the Qwen3-VL-8B multimodal model, designed for advanced visual and textual reasoning across complex scenes, documents, and temporal sequences. It integrates enhanced multimodal alignment and...
VisionReasoningTools+3$0.1899in / 1M$2.22out / 1M131Kcontext1provider - Qwen3.5 397B A17Bqwen/qwen3.5-397b-a17b
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...
VisionReasoningTools+3$0.4115in / 1M$2.47out / 1M262Kcontext1provider - Qwen3.5 Plus 2026-02-15qwen/qwen3.5-plus-02-15
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...
VisionReasoningTools+3$0.2743in / 1M$1.65out / 1M1Mcontext1provider - Qwen3.5 Plus 2026-04-20qwen/qwen3.5-plus-20260420
Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context window. This...
VisionReasoningTools+3$0.3165in / 1M$1.90out / 1M1Mcontext1provider - Qwen3.5-122B-A10Bqwen/qwen3.5-122b-a10b
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...
VisionReasoningTools+3$0.2743in / 1M$2.19out / 1M262Kcontext1provider - Qwen3.5-27Bqwen/qwen3.5-27b
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...
VisionReasoningTools+3$0.2057in / 1M$1.65out / 1M262Kcontext1provider - Qwen3.5-35B-A3Bqwen/qwen3.5-35b-a3b
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...
VisionReasoningTools+3$0.2638in / 1M$1.32out / 1M262Kcontext1provider - Qwen3.5-Flashqwen/qwen3.5-flash-02-23
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...
VisionReasoningTools+3$0.0686in / 1M$0.2743out / 1M1Mcontext1provider - Qwen3.6 27Bqwen/qwen3.6-27b
Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities, accepting text, image, and video inputs...
VisionReasoningTools+3$0.6330in / 1M$3.80out / 1M262Kcontext1provider - Qwen3.6 35B A3Bqwen/qwen3.6-35b-a3b
Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...
VisionReasoningTools+3$0.1477in / 1M$1.06out / 1M262Kcontext1provider - Qwen3.6 Flashqwen/qwen3.6-flash
Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window. Tiered pricing kicks in...
VisionReasoningTools+3$0.1978in / 1M$1.19out / 1M1Mcontext1provider - Qwen3.6 Max Previewqwen/qwen3.6-max-preview
Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse mixture-of-experts architecture with approximately 1 trillion total parameters. It is optimized for agentic coding, tool use, and...
ReasoningToolsJSON+2$1.08in / 1M$6.50out / 1M262Kcontext1provider - Qwen3.6 Plusqwen/qwen3.6-plus
Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers...
VisionReasoningTools+3$0.3429in / 1M$2.06out / 1M1Mcontext1provider - Qwen3.7 Flashqwen/qwen3.7-flash
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...
VisionReasoningTools+3$0.0317in / 1M$0.1372out / 1M1Mcontext1provider - Qwen3.7 Maxqwen/qwen3.7-max
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,...
ReasoningToolsJSON+2$1.56in / 1M$4.67out / 1M1Mcontext1provider - R1 0528deepseek/deepseek-r1-0528
May 28th update to the original DeepSeek R1 Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...
ReasoningToolsJSON+2$0.5275in / 1M$2.27out / 1M164Kcontext1provider - R1 Distill Llama 70Bdeepseek/deepseek-r1-distill-llama-70b
DeepSeek R1 Distill Llama 70B is a distilled large language model based on Llama-3.3-70B-Instruct, using outputs from DeepSeek R1. The model combines advanced distillation techniques to achieve high performance across...
ReasoningCachingStreaming$0.8440in / 1M$0.8440out / 1M8Kcontext1provider - Reka Edgerekaai/reka-edge
Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to deliver industry-leading performance in image understanding,...
VisionToolsJSON+2$0.1055in / 1M$0.1055out / 1M16Kcontext1provider - Reka Flash 3rekaai/reka-flash-3
Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at general chat, coding tasks, instruction-following, and function calling. Featuring a...
ReasoningJSONCaching+1$0.1055in / 1M$0.2110out / 1M66Kcontext1provider - Relace Apply 3relace/relace-apply-3
Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your files at...
CachingStreaming$0.8968in / 1M$1.32out / 1M256Kcontext1provider - Relace Searchrelace/relace-search
The relace-search model uses 4-12 viewfile and grep tools in parallel to explore a codebase and return relevant files to the user request. In contrast to RAG, relace-search performs agentic...
ToolsJSONCaching+1$1.06in / 1M$3.17out / 1M256Kcontext1provider - ReMM SLERP 13Bundi95/remm-slerp-l2-13b
A recreation trial of the original MythoMax-L2-B13 but with updated models. merge
JSONCachingStreaming$0.4748in / 1M$0.6858out / 1M6Kcontext1provider - Ring-2.6-1Tinclusionai/ring-2.6-1t
Ring-2.6-1T is a 1T-parameter-scale thinking model with 63B active parameters, built for real-world agent workflows that require both strong capability and operational efficiency. It is optimized for coding agents, tool...
ReasoningToolsJSON+2$0.0791in / 1M$0.6594out / 1M262Kcontext1provider - Rocinante 12Bthedrummer/rocinante-12b
Rocinante 12B is designed for engaging storytelling and rich prose. Early testers have reported: - Expanded vocabulary with unique and expressive word choices - Enhanced creativity for vivid narratives -...
JSONCachingStreaming$0.2638in / 1M$0.5275out / 1M66Kcontext1provider - Sabamistralai/mistral-saba
Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional...
ToolsJSONCaching+1$0.2110in / 1M$0.6330out / 1M33Kcontext1provider - Seed 1.6bytedance-seed/seed-1.6
Seed 1.6 is a general-purpose model released by the ByteDance Seed team. It incorporates multimodal capabilities and adaptive deep thinking with a 256K context window.
VisionReasoningTools+3$0.2638in / 1M$2.11out / 1M262Kcontext1provider - Seed 1.6 Flashbytedance-seed/seed-1.6-flash
Seed 1.6 Flash is an ultra-fast multimodal deep thinking model by ByteDance Seed, supporting both text and visual understanding. It features a 256k context window and can generate outputs of...
VisionReasoningTools+3$0.0791in / 1M$0.3165out / 1M262Kcontext1provider - Seed-2.0-Litebytedance-seed/seed-2.0-lite
Seed-2.0-Lite is a versatile, cost‑efficient enterprise workhorse that delivers strong multimodal and agent capabilities while offering noticeably lower latency, making it a practical default choice for most production workloads across...
VisionReasoningTools+3$0.2638in / 1M$2.11out / 1M262Kcontext1provider - Seed-2.0-Minibytedance-seed/seed-2.0-mini
Seed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference deployment. It delivers performance comparable to ByteDance-Seed-1.6, supports 256k context, four reasoning effort modes (minimal/low/medium/high), multimodal understanding,...
VisionReasoningTools+3$0.1055in / 1M$0.4220out / 1M262Kcontext1provider - Skyfall 36B V2thedrummer/skyfall-36b-v2
Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-playing, and coherent storytelling.
JSONCachingStreaming$0.5803in / 1M$0.8440out / 1M33Kcontext1provider - Solar Pro 3upstage/solar-pro-3
Solar Pro 3 is Upstage's powerful Mixture-of-Experts (MoE) language model. With 102B total parameters and 12B active parameters per forward pass, it delivers exceptional performance while maintaining computational efficiency. Optimized...
ReasoningToolsJSON+2$0.1583in / 1M$0.6330out / 1M128Kcontext1provider - Sonarperplexity/sonar
Sonar is lightweight, affordable, fast, and simple to use, now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features...
VisionCachingStreaming$1.06in / 1M$1.06out / 1M127Kcontext1provider - Sonar Deep Researchperplexity/sonar-deep-research
Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers...
ReasoningCachingStreaming$2.11in / 1M$8.44out / 1M128Kcontext1provider - Sonar Properplexity/sonar-pro
Note: Sonar Pro pricing includes Perplexity search pricing. See details here For enterprises seeking more advanced capabilities, the Sonar Pro API can handle in-depth, multi-step queries with added extensibility, like...
VisionCachingStreaming$3.17in / 1M$15.83out / 1M200Kcontext1provider - Sonar Pro Searchperplexity/sonar-pro-search
Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is designed for deeper reasoning and analysis. Pricing is based...
VisionReasoningJSON+2$3.17in / 1M$15.83out / 1M200Kcontext1provider - Sonar Reasoning Properplexity/sonar-reasoning-pro
Note: Sonar Pro pricing includes Perplexity search pricing. See details here Sonar Reasoning Pro is a premier reasoning model powered by DeepSeek R1 with Chain of Thought (CoT). Designed for...
VisionReasoningCaching+1$2.11in / 1M$8.44out / 1M128Kcontext1provider - Step 3.5 Flashstepfun/step-3.5-flash
Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....
ReasoningToolsCaching+1$0.1055in / 1M$0.3165out / 1M262Kcontext1provider - Step 3.7 Flashstepfun/step-3.7-flash
Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...
VisionReasoningTools+3$0.2110in / 1M$1.21out / 1M262Kcontext1provider - Trinity Large Thinkingarcee-ai/trinity-large-thinking
Trinity Large Thinking is a powerful open source reasoning model from the team at Arcee AI. It shows strong performance in PinchBench, agentic workloads, and reasoning tasks. Launch video: https://youtu.be/Gc82AXLa0Rg?si=4RLn6WBz33qT--B7...
ReasoningToolsJSON+2$0.2321in / 1M$0.8968out / 1M262Kcontext1provider - UI-TARS 7Bbytedance/ui-tars-1.5-7b
UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, it builds upon the UI-TARS framework with reinforcement...
VisionJSONCaching+1$0.1055in / 1M$0.2110out / 1M128Kcontext1provider - Uncensoredcognitivecomputations/dolphin-mistral-24b-venice-edition
Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct-tuned LLM, preserving...
JSONCachingStreaming$0.2110in / 1M$0.9495out / 1M128Kcontext1provider - UnslopNemo 12Bthedrummer/unslopnemo-12b
UnslopNemo v4.1 is the latest addition from the creator of Rocinante, designed for adventure writing and role-play scenarios.
ToolsJSONCaching+1$0.4220in / 1M$0.4220out / 1M1.0Mcontext1provider - Virtuoso Largearcee-ai/virtuoso-large
Virtuoso‑Large is Arcee's top‑tier general‑purpose LLM at 72 B parameters, tuned to tackle cross‑domain reasoning, creative writing and enterprise QA. Unlike many 70 B peers, it retains the 128 k...
ToolsCachingStreaming$0.7913in / 1M$1.27out / 1M131Kcontext1provider - Voxtral Small 24B 2507mistralai/voxtral-small-24b-2507
Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding. Input audio...
ToolsJSONCaching+1$0.1055in / 1M$0.3165out / 1M32Kcontext1provider - Weaver (alpha)mancer/weaver
An attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory. Meant for use in roleplay/narrative situations.
JSONCachingStreaming$0.5275in / 1M$0.7913out / 1M8Kcontext1provider - WizardLM-2 8x22Bmicrosoft/wizardlm-2-8x22b
WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model. It demonstrates highly competitive performance compared to leading proprietary models, and it consistently outperforms all existing state-of-the-art opensource models. It is...
JSONCachingStreaming$0.6541in / 1M$0.6541out / 1M66Kcontext1provider
Point one endpoint at this catalogue
Signing up takes no card and commits you to nothing. You start at a zero balance, so nothing can be charged until you decide to add credit. Every price above is what that route costs us, with no spread of ours on top, and every request comes back with what it actually cost.