No provider description is available for this model yet.
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
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.
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.
No provider description is available for this model yet.
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...
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 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...
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,...
No provider description is available for this model yet.
Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file...
No provider description is available for this model yet.
Granite 4.2 8B is a dense reasoning model from IBM. It is suited for mathematics, code generation, multilingual dialogue, and agentic workflows that need multi-step reasoning. It supports full, low-effort,...
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.
No provider description is available for this model yet.
No provider description is available for this model yet.
GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon...
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.
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.
GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/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/reasoning#reasoning-mode
| Model | Creator | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|
| llama4-mavericksnowflake/llama4-maverick | 128K | $0.24 | $0.97 | — | |||
| Qwen/Qwen3.6-35B-A3Bwandb/qwen/qwen3.6-35b-a3b | Wandb |
262.144K | $0.25 | $1.25 | — | ||
| Qwen/Qwen3.8-27Bwandb/qwen/qwen3.8-27b | Wandb |
262.144K | $0.4 | $3 | — | ||
| databricks-glm-5-2databricks/databricks-glm-5-2 | Databricks |
1M | $1.4 | $4.4 | — | ||
| OpenPipe/Qwen3-14B-Instructwandb/openpipe/qwen3-14b-instruct | Wandb |
32.768K | $0.05 | $0.22 | — | ||
| openai-gpt-5-nanosnowflake/openai-gpt-5-nano | 5M | $0.15 | $0.6 | — | |||
| gemini-2.5-flash-native-audio-preview-12-2025gemini/gemini-2.5-flash-native-audio-preview-12-2025 | 1.04858M | $0.3 | $2.5 | — | |||
| gemma-4-31b-it-thinkinglibertai/gemma-4-31b-it-thinking | 262.144K | $0.15 | $0.4 | — | |||
| nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55Bwandb/nvidia/nvidia-nemotron-3-ultra-550b-a55b | Wandb |
262.144K | $0.75 | $2.75 | — | ||
| nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3Bwandb/nvidia/nvidia-nemotron-3.5-lightning-30b-a3b | Wandb |
262.144K | $0.1 | $0.25 | — | ||
| moonshotai/Kimi-K2.6wandb/moonshotai/kimi-k2.6 | Wandb |
262.144K | $0.65 | $3.41 | — | ||
| moonshotai/Kimi-K2.7-Codewandb/moonshotai/kimi-k2.7-code | Wandb |
262.144K | $0.71 | $3.5 | — | ||
| openai-gpt-5-minisnowflake/openai-gpt-5-mini | 1M | $0.3 | $1.2 | — | |||
| MiniMaxAI/MiniMax-M3wandb/minimaxai/minimax-m3 | Wandb |
262.144K | $0.23 | $0.96 | — | ||
| meta-llama/Llama-3.1-70B-Instructwandb/meta-llama/llama-3.1-70b-instruct | Wandb |
128K | $0.8 | $0.8 | — | ||
| JetBrains/Mellum2-12B-A2.5B-Instructwandb/jetbrains/mellum2-12b-a2.5b-instruct | Wandb |
131.072K | $0.05 | $0.1 | — | ||
| Qwen: Qwen3 Coder 480B A35Bqwen/qwen3-coder | Alibaba Qwen |
262.144K | $0.3 | $1 | — | ||
| openai-gpt-5snowflake/openai-gpt-5 | 300K | $1.25 | $10 | — | |||
| gemini-2.5-flash-native-audio-preview-09-2025gemini/gemini-2.5-flash-native-audio-preview-09-2025 | 1.04858M | $0.3 | $2.5 | — | |||
| ibm-granite/granite-4.1-8bwandb/ibm-granite/granite-4.1-8b | Wandb |
131.072K | $0.05 | $0.1 | — | ||
| google/gemma-4-31B-itwandb/google/gemma-4-31b-it | Wandb |
262.144K | $0.1 | $0.34 | — | ||
| Anthropic: Claude Opus 4.1 (batch)anthropic/claude-opus-4.1:batch | Anthropic |
200K | $7.5 | $37.5 | — | ||
| deepseek-ai/DeepSeek-V4-Prowandb/deepseek-ai/deepseek-v4-pro | Wandb |
1.04858M | $1.15 | $2.55 | — | ||
| Z.ai: GLM 4.5Vz-ai/glm-4.5v | Z Ai |
65.536K | $0.6 | $1.8 | — | ||
| openai-gpt-4.1snowflake/openai-gpt-4.1 | 300K | $2 | $8 | — | |||
| Nex AGI: Nex-N2.5-Pro (free)nex-agi/nex-n2.5-pro:free | 262.144K | Free | Free | — | |||
| deepseek-ai/DeepSeek-V4-Flash-0731wandb/deepseek-ai/deepseek-v4-flash-0731 | Wandb |
262.144K | $0.13 | $0.28 | — | ||
| IBM: Granite 4.2 8Bibm-granite/granite-4.2-8b | IBM |
131.072K | $0.06 | $0.25 | — | ||
| deepseek-ai/DeepSeek-V4-Flashwandb/deepseek-ai/deepseek-v4-flash | Wandb |
1.04858M | $0.14 | $0.28 | — | ||
| qwen-turbo-2024-11-01qwen_ai_platform/qwen-turbo-2024-11-01 | 1M | $0.05 | $0.2 | — | |||
| meta-llama/llama-3.2-1b-instructnovita/meta-llama/llama-3.2-1b-instruct | 131K | $0.02 | $0.02 | — | |||
| claude-3-7-sonnetsnowflake/claude-3-7-sonnet | 200K | $3 | $15 | — | |||
| gemini-2.5-flash-native-audio-latestgemini/gemini-2.5-flash-native-audio-latest | 1.04858M | $0.3 | $2.5 | — | |||
| gemma-4-31b-itlibertai/gemma-4-31b-it | 262.144K | $0.15 | $0.4 | — | |||
| openthinker-7bllamagate/openthinker-7b | 32.768K | $0.08 | $0.15 | — | |||
| thudm/glm-4-32b-0414novita/thudm/glm-4-32b-0414 | 32K | $0.55 | $1.66 | — | |||
| qwen-plus-2025-07-28qwen_ai_platform/qwen-plus-2025-07-28 | 997.952K | — | — | — | |||
| OpenAI: GPT-6 Astra (batch)openai/gpt-6-astra:batch | OpenAI |
1.05M | $5 | $25 | — | ||
| qwen-plus-2025-07-14qwen_ai_platform/qwen-plus-2025-07-14 | 129.024K | $0.4 | $1.2 | — | |||
| qwen-plus-2025-04-28qwen_ai_platform/qwen-plus-2025-04-28 | 129.024K | $0.4 | $1.2 | — | |||
| qwen-plus-2025-01-25qwen_ai_platform/qwen-plus-2025-01-25 | 129.024K | $0.4 | $1.2 | — | |||
| deepseek/deepseek-r1/communitynovita/deepseek/deepseek-r1/community | 64K | $4 | $4 | — | |||
| claude-haiku-4-5snowflake/claude-haiku-4-5 | 200K | $1 | $5 | — | |||
| qwen-plus-2025-09-11qwen_ai_platform/qwen-plus-2025-09-11 | 997.952K | — | — | — | |||
| qwen-plus-latestqwen_ai_platform/qwen-plus-latest | 997.952K | — | — | — | |||
| qwen-turboqwen_ai_platform/qwen-turbo | 129.024K | $0.05 | $0.2 | — | |||
| qwen-plusqwen_ai_platform/qwen-plus | 129.024K | $0.4 | $1.2 | — | |||
| qwen-turbo-2025-04-28qwen_ai_platform/qwen-turbo-2025-04-28 | 1M | $0.05 | $0.2 | — | |||
| deepseek/deepseek-v3/communitynovita/deepseek/deepseek-v3/community | 64K | $0.89 | $0.89 | — | |||
| OpenAI: GPT-5.6 Luna Pro (batch)openai/gpt-5.6-luna-pro:batch | OpenAI |
1.05M | $0.1 | $0.6 | — |