Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
The Pareto Router maintains a tiered shortlist of strong coding models, ranked by [Artificial Analysis](https://artificialanalysis.ai/) coding percentiles. Set min_coding_score between 0 and 1 on the [pareto-router plugin](https://openrouter.ai/docs/guides/routing/routers/pareto-router#the-min_coding_score-parameter) to control how...
This model always redirects to the latest model in the GPT Astra family.
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...
A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.
This model always redirects to the latest model in the GPT Sol family.
No provider description is available for this model yet.
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.
No provider description is available for this model yet.
No provider description is available for this model yet.
DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepseek-v4-flash-0731) from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...
No provider description is available for this model yet.
No provider description is available for this model yet.
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....
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...
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...
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
Laguna M.1 is the flagship coding agent model from [Poolside](https://poolside.ai/), optimized for complex software engineering tasks. Designed for agentic coding workflows, it supports tool calling and reasoning, with a 256K...
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
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:...
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...
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...
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
No provider description is available for this model yet.
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](https://www.anthropic.com/news/claude-3-haiku) #multimodal
No provider description is available for this model yet.
No provider description is available for this model yet.
Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...
No provider description is available for this model yet.
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...
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...
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...
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...
*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*. The model is designed with *token efficiency and production-scale agentic inference* as key priorities, enabling developers...
No provider description is available for this model yet.
No provider description is available for this model yet.
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...
Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...
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...
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...
No provider description is available for this model yet.
| Model | Creator | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|
| Pareto Code Routeropenrouter/pareto-code | Openrouter |
2M | — | — | — | ||
| OpenAI: GPT Astra Latest~openai/gpt-astra-latest | OpenAI |
1.05M | $10 | $50 | — | ||
| NVIDIA: Nemotron 3 Ultra (free)nvidia/nemotron-3-ultra-550b-a55b:free | NVIDIA |
1M | Free | Free | — | ||
| Mistral: Ministral 3 8B 2512mistralai/ministral-8b-2512 | Mistral AI |
262.144K | $0.15 | $0.15 | — | ||
| OpenAI: GPT Sol Latest~openai/gpt-sol-latest | OpenAI |
1.05M | $2 | $10 | — | ||
| labs-leanstral-1-5mistral/labs-leanstral-1-5 | Mistral |
262.144K | — | — | — | ||
| Mistral: Mistral Large 3 2512 (batch)mistralai/mistral-large-2512:batch | Mistral AI |
262.144K | $0.25 | $0.75 | — | ||
| claude-mythos-previewanthropic/claude-mythos-preview | Anthropic |
1M | $10 | $50 | — | ||
| grok-4.20-multi-agent-0309xai/grok-4.20-multi-agent-0309 | xAI |
1M | $1.25 | $2.5 | — | ||
| DeepSeek: DeepSeek V4 Flash Vision Exp (batch)deepseek/deepseek-v4-flash-vision-exp:batch | DeepSeek |
1.04858M | $0.11 | $0.33 | — | ||
| us-east-1/qwen.qwen3-coder-nextbedrock/us-east-1/qwen.qwen3-coder-next | 262.144K | $0.5 | $1.2 | — | |||
| ap-southeast-2/minimax.minimax-m2.5bedrock/ap-southeast-2/minimax.minimax-m2.5 | 1M | $0.309 | $1.236 | — | |||
| inclusionAI: Ling-2.6-flashinclusionai/ling-2.6-flash | 262.144K | $0.01 | $0.03 | — | |||
| Kwaipilot: KAT-Coder-Air V2.5kwaipilot/kat-coder-air-v2.5 | 256K | $0.15 | $0.6 | — | |||
| Anthropic: Claude Opus 4.7anthropic/claude-opus-4.7 | Anthropic |
1M | $5 | $25 | — | ||
| us-east-1/moonshotai.kimi-k2.5bedrock/us-east-1/moonshotai.kimi-k2.5 | 262.144K | $0.6 | $3 | — | |||
| ap-south-1/qwen.qwen3-coder-nextbedrock/ap-south-1/qwen.qwen3-coder-next | 262.144K | $0.6 | $1.44 | — | |||
| us-east-1/moonshotai.kimi-k2-thinkingbedrock/us-east-1/moonshotai.kimi-k2-thinking | 262.144K | $0.6 | $2.5 | — | |||
| Poolside: Laguna M.1 (free)poolside/laguna-m.1:free | Poolside |
262.144K | Free | Free | — | ||
| us-gov-east-1/xai.grok-4.6bedrock_mantle/us-gov-east-1/xai.grok-4.6 | 500K | $2.64 | $7.92 | — | |||
| us-gov-west-1/google.gemma-4-31bbedrock_mantle/us-gov-west-1/google.gemma-4-31b | 256K | $0.168 | $0.48 | — | |||
| ap-south-1/moonshotai.kimi-k2.5bedrock/ap-south-1/moonshotai.kimi-k2.5 | 262.144K | $0.72 | $3.6 | — | |||
| us-gov-west-1/google.gemma-4-26b-a4bbedrock_mantle/us-gov-west-1/google.gemma-4-26b-a4b | 256K | $0.156 | $0.48 | — | |||
| accounts/fireworks/routers/kimi-k3-usfireworks_ai/accounts/fireworks/routers/kimi-k3-us | Fireworks_Ai |
1.04858M | $3.3 | $16.5 | — | ||
| Tencent: Hy3 (free)tencent/hy3:free | Tencent |
262.144K | Free | Free | — | ||
| Qwen: Qwen3 Max Thinkingqwen/qwen3-max-thinking | Alibaba Qwen |
262.144K | $0.78 | $3.9 | — | ||
| Qwen: Qwen3.6 35B A3Bqwen/qwen3.6-35b-a3b | Alibaba Qwen |
262.144K | $0.1 | $0.9 | — | ||
| us-gov-west-1/xai.grok-4.6bedrock_mantle/us-gov-west-1/xai.grok-4.6 | 500K | $2.64 | $7.92 | — | |||
| accounts/fireworks/routers/kimi-k3-fastfireworks_ai/accounts/fireworks/routers/kimi-k3-fast | Fireworks_Ai |
1.04858M | $4.5 | $22.5 | — | ||
| ap-south-1/moonshotai.kimi-k2-thinkingbedrock/ap-south-1/moonshotai.kimi-k2-thinking | 262.144K | $0.71 | $2.94 | — | |||
| us-east-1/minimax.minimax-m2.5bedrock/us-east-1/minimax.minimax-m2.5 | 1M | $0.3 | $1.2 | — | |||
| us-gov-east-1/anthropic.claude-fable-5-1bedrock/us-gov-east-1/anthropic.claude-fable-5-1 | 1M | $12 | $60 | — | |||
| ap-south-1/minimax.minimax-m2.5bedrock/ap-south-1/minimax.minimax-m2.5 | 1M | $0.36 | $1.44 | — | |||
| Anthropic: Claude 3 Haikuanthropic/claude-3-haiku | Anthropic |
200K | $0.25 | $1.25 | — | ||
| accounts/fireworks/routers/glm-5p2-fast-usfireworks_ai/accounts/fireworks/routers/glm-5p2-fast-us | Fireworks_Ai |
1.04858M | $2.1 | $6.6 | — | ||
| accounts/fireworks/routers/glm-5p2-fastfireworks_ai/accounts/fireworks/routers/glm-5p2-fast | Fireworks_Ai |
1.04858M | $2.1 | $6.6 | — | ||
| Google: Gemini 3.6 Flash (batch)google/gemini-3.6-flash:batch | Google |
1.04858M | $0.375 | $1.875 | — | ||
| accounts/fireworks/models/qwen3p8-maxfireworks_ai/accounts/fireworks/models/qwen3p8-max | Fireworks_Ai |
262.144K | $2 | $6 | — | ||
| Kwaipilot: KAT-Coder-Air V2.5 (free)kwaipilot/kat-coder-air-v2.5:free | 256K | Free | Free | — | |||
| Qwen: Qwen3.5 Plus 2026-04-20qwen/qwen3.5-plus-20260420 | Alibaba Qwen |
1M | $0.3 | $1.8 | — | ||
| Qwen: Qwen3.6 27Bqwen/qwen3.6-27b | Alibaba Qwen |
262.144K | $0.3 | $2 | — | ||
| Kwaipilot: KAT-Coder-Pro V2.5kwaipilot/kat-coder-pro-v2.5 | 262.144K | $0.74 | $2.96 | — | |||
| Ling-3.0-flash (free)inclusionai/ling-3.0-flash:free | 262.144K | Free | Free | — | |||
| us-gov-east-1/anthropic.claude-opus-5bedrock/us-gov-east-1/anthropic.claude-opus-5 | 1M | $6 | $30 | — | |||
| accounts/fireworks/models/nemotron-3-ultra-nvfp4fireworks_ai/accounts/fireworks/models/nemotron-3-ultra-nvfp4 | Fireworks_Ai |
262.144K | $0.6 | $2.4 | — | ||
| Kwaipilot: KAT-Coder-Pro V2.5 (free)kwaipilot/kat-coder-pro-v2.5:free | 256K | Free | Free | — | |||
| Google: Gemini 3.5 Flash (batch)google/gemini-3.5-flash:batch | Google |
1.04858M | $0.75 | $4.5 | — | ||
| Thinking Machines: Inkling Small (batch)thinkingmachines/inkling-small:batch | Thinkingmachines |
524.288K | $0.5 | $1.2 | — | ||
| Amazon: Nova Lite 1.0amazon/nova-lite-v1 | Amazon |
300K | $0.06 | $0.24 | — | ||
| grok-4.3azure_ai/grok-4.3 | 200K | $1.25 | $2.5 | — |