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...
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
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...
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.
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...
No provider description is available for this model yet.
No provider description is available for this model yet.
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.
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.
No provider description is available for this model yet.
This model always redirects to the latest model in the Claude Sonnet family.
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.
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...
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...
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...
Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...
Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...
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.
This model always redirects to the latest model in the Gemini Flash family.
No provider description is available for this model yet.
No provider description is available for this model yet.
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...
No provider description is available for this model yet.
Ox Alpha is a reasoning model designed for coding, sustained agentic work, and production workloads. It is suited for long-horizon software engineering, complex reasoning, and workflows that combine text with...
This model always redirects to the latest model in the Kimi family.
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....
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.
GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...
No provider description is available for this model yet.
The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...
No provider description is available for this model yet.
No provider description is available for this model yet.
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,...
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...
| Model | Creator | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|
| Z.ai: GLM 4.5 Airz-ai/glm-4.5-air | Z Ai |
131.072K | $0.13 | $0.85 | — | ||
| Thinking Machines: Inkling Small (free)thinkingmachines/inkling-small:free | Thinkingmachines |
1.04858M | Free | Free | — | ||
| eu.anthropic.claude-sonnet-5bedrock_converse/eu.anthropic.claude-sonnet-5 | 1M | $2.2 | $11 | — | |||
| us/o3-2025-04-16azure/us/o3-2025-04-16 | Azure |
200K | $2.2 | $8.8 | — | ||
| us/o3-mini-2025-01-31azure/us/o3-mini-2025-01-31 | Azure |
200K | $1.21 | $4.84 | — | ||
| us/o4-mini-2025-04-16azure/us/o4-mini-2025-04-16 | Azure |
200K | $1.21 | $4.84 | — | ||
| Thinking Machines: Inkling Small (batch)thinkingmachines/inkling-small:batch | Thinkingmachines |
524.288K | $0.5 | $1.2 | — | ||
| Llama-3.2-11B-Vision-Instructazure_ai/llama-3.2-11b-vision-instruct | 128K | $0.37 | $0.37 | — | |||
| us.anthropic.claude-sonnet-5bedrock_converse/us.anthropic.claude-sonnet-5 | 1M | $2.2 | $11 | — | |||
| Qwen: Qwen Plus 0728 (thinking)qwen/qwen-plus-2025-07-28:thinking | Alibaba Qwen |
1M | $0.26 | $0.78 | — | ||
| Llama-3.3-70B-Instructazure_ai/llama-3.3-70b-instruct | 128K | $0.71 | $0.71 | — | |||
| Llama-4-Maverick-17B-128E-Instruct-FP8azure_ai/llama-4-maverick-17b-128e-instruct-fp8 | 1M | $1.41 | $0.35 | — | |||
| Llama-4-Scout-17B-16E-Instructazure_ai/llama-4-scout-17b-16e-instruct | 10M | $0.2 | $0.78 | — | |||
| Meta-Llama-3.1-405B-Instructazure_ai/meta-llama-3.1-405b-instruct | 128K | $5.33 | $16 | — | |||
| Meta-Llama-3.1-70B-Instructazure_ai/meta-llama-3.1-70b-instruct | 128K | $2.68 | $3.54 | — | |||
| Meta-Llama-3.1-8B-Instructazure_ai/meta-llama-3.1-8b-instruct | 128K | $0.3 | $0.61 | — | |||
| Phi-3-medium-128k-instructazure_ai/phi-3-medium-128k-instruct | 128K | $0.17 | $0.68 | — | |||
| Anthropic: Claude Sonnet Latest~anthropic/claude-sonnet-latest | Anthropic |
1M | $2 | $10 | — | ||
| Phi-3-mini-128k-instructazure_ai/phi-3-mini-128k-instruct | 128K | $0.13 | $0.52 | — | |||
| Phi-3-small-128k-instructazure_ai/phi-3-small-128k-instruct | 128K | $0.15 | $0.6 | — | |||
| Phi-3.5-MoE-instructazure_ai/phi-3.5-moe-instruct | 128K | $0.16 | $0.64 | — | |||
| Phi-3.5-mini-instructazure_ai/phi-3.5-mini-instruct | 128K | $0.13 | $0.52 | — | |||
| Mistral: Mistral Small 4mistralai/mistral-small-2603 | Mistral AI |
262.144K | $0.15 | $0.6 | — | ||
| Pareto Code Routeropenrouter/pareto-code | Openrouter |
2M | — | — | — | ||
| Qwen: Qwen3 30B A3B Thinking 2507qwen/qwen3-30b-a3b-thinking-2507 | Alibaba Qwen |
81.92K | $0.2 | $2.4 | — | ||
| MoonshotAI: Kimi K2 0905moonshotai/kimi-k2-0905 | Moonshot AI |
262.144K | $0.6 | $2.5 | — | ||
| Claude Opus 5 (batch)anthropic/claude-opus-5:batch | Anthropic |
1M | $2.5 | $12.5 | — | ||
| global.anthropic.claude-sonnet-5bedrock_converse/global.anthropic.claude-sonnet-5 | 1M | $2 | $10 | — | |||
| sa-east-1/minimax.minimax-m2.1bedrock/sa-east-1/minimax.minimax-m2.1 | 196K | $0.36 | $1.44 | — | |||
| anthropic.claude-sonnet-5bedrock_converse/anthropic.claude-sonnet-5 | 1M | $2 | $10 | — | |||
| jp.anthropic.claude-opus-4-7bedrock_converse/jp.anthropic.claude-opus-4-7 | 1M | $5.5 | $27.5 | — | |||
| deepseek-ai/DeepSeek-V3.2friendliai/deepseek-ai/deepseek-v3.2 | 163.84K | $0.5 | $1.5 | — | |||
| Google: Gemini Flash Latest~google/gemini-flash-latest | Google |
1.04858M | $0.75 | $3.75 | — | ||
| jp.anthropic.claude-opus-4-8bedrock_converse/jp.anthropic.claude-opus-4-8 | 1M | $5.5 | $27.5 | — | |||
| LGAI-EXAONE/K-EXAONE-2.0-750B-A37Bfriendliai/lgai-exaone/k-exaone-2.0-750b-a37b | 262.144K | $0.6 | $2.4 | — | |||
| Anthropic: Claude Opus 4anthropic/claude-opus-4 | Anthropic |
200K | $15 | $75 | — | ||
| au.anthropic.claude-opus-4-8bedrock_converse/au.anthropic.claude-opus-4-8 | 1M | $5.5 | $27.5 | — | |||
| Ox Alphastealth/ox-alpha | 1.04858M | — | — | — | |||
| MoonshotAI: Kimi Latest~moonshotai/kimi-latest | Moonshot AI |
1.04858M | $2.1 | $10.95 | — | ||
| inclusionAI: Ling-2.6-flashinclusionai/ling-2.6-flash | 262.144K | $0.01 | $0.03 | — | |||
| eu.anthropic.claude-opus-4-8bedrock_converse/eu.anthropic.claude-opus-4-8 | 1M | $5.5 | $27.5 | — | |||
| us.anthropic.claude-opus-4-8bedrock_converse/us.anthropic.claude-opus-4-8 | 1M | $5.5 | $27.5 | — | |||
| zai-org/GLM-5.2friendliai/zai-org/glm-5.2 | 1.04858M | $1.4 | $4.4 | — | |||
| Z.ai: GLM 5.2 (free)z-ai/glm-5.2:free | Z Ai |
256K | Free | Free | — | ||
| google/gemma-4-31B-itfriendliai/google/gemma-4-31b-it | 262.144K | $0.14 | $0.4 | — | |||
| Meta: Llama 3.3 70B Instruct (free)meta-llama/llama-3.3-70b-instruct:free | Meta |
65.536K | Free | Free | — | ||
| global.anthropic.claude-opus-4-8bedrock_converse/global.anthropic.claude-opus-4-8 | 1M | $5 | $25 | — | |||
| nvidia/nemotron-3.5-lightningopenrouter/nvidia/nemotron-3.5-lightning | Openrouter |
262.144K | $0.05 | $0.2 | — | ||
| Z.ai: GLM 4.5Vz-ai/glm-4.5v | Z Ai |
65.536K | $0.6 | $1.8 | — | ||
| Qwen: Qwen3.6 27Bqwen/qwen3.6-27b | Alibaba Qwen |
262.144K | $0.3 | $2 | — |