Ministral 8B is an 8B parameter model featuring a unique interleaved sliding-window attention pattern for faster, memory-efficient inference. Designed for edge use cases, it supports up to 128k context length...
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...
Fugu Max is the cost-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...
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...
No provider description is available for this model yet.
NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...
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,...
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...
GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...
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...
GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...
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...
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...
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.
GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/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/reasoning#reasoning-mode
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.
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...
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.
Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.
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.
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,...
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.
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](https://mistral.ai/news/codestral-25-08)
No provider description is available for this model yet.
No provider description is available for this model yet.
| Model | Creator | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|
| Mistral: Ministral 8Bmistralai/ministral-8b | Mistral AI |
128K | $0.11 | $0.11 | — | ||
| SpaceXAI: Grok 4.20x-ai/grok-4.20 | xAI |
2M | $1.25 | $2.5 | — | ||
| Sakana: Fugu Maxsakana/fugu-max | Sakana |
1M | $2 | $6 | — | ||
| Inception: Mercury 2inception/mercury-2 | Inception |
128K | $0.25 | $0.75 | — | ||
| openai/gpt-5.6-solopenrouter/openai/gpt-5.6-sol | Openrouter |
1.05M | $2 | $10 | — | ||
| NVIDIA: Nemotron 3.5 Lightning (free)nvidia/nemotron-3.5-lightning:free | NVIDIA |
1M | Free | Free | — | ||
| Z.ai: GLM 4.5Vz-ai/glm-4.5v | Z Ai |
65.536K | $0.6 | $1.8 | — | ||
| Google: Gemini 2.5 Pro (batch)google/gemini-2.5-pro:batch | Google |
1.04858M | $0.625 | $5 | — | ||
| OpenAI: GPT-4o-mini (batch)openai/gpt-4o-mini:batch | OpenAI |
128K | $0.075 | $0.3 | — | ||
| DeepSeek: DeepSeek V3.2 Expdeepseek/deepseek-v3.2-exp | DeepSeek |
163.84K | $0.27 | $0.41 | — | ||
| OpenAI: GPT-5.6 Sol (batch)openai/gpt-5.6-sol:batch | OpenAI |
1.05M | $1 | $5 | — | ||
| Qwen: Qwen3 Coder 480B A35Bqwen/qwen3-coder | Alibaba Qwen |
262.144K | $0.3 | $1 | — | ||
| Mistral: Mistral Medium 3.1mistralai/mistral-medium-3.1 | Mistral AI |
131.072K | $0.4 | $2 | — | ||
| Mistral: Mistral Large 3 2512mistralai/mistral-large-2512 | Mistral AI |
262.144K | $0.5 | $1.5 | — | ||
| OpenAI: GPT-5.6 Terra Pro (batch)openai/gpt-5.6-terra-pro:batch | OpenAI |
1.05M | $1 | $6 | — | ||
| databricks-glm-5-2databricks/databricks-glm-5-2 | Databricks |
1M | $1.4 | $4.4 | — | ||
| databricks-kimi-k3databricks/databricks-kimi-k3 | Databricks |
1M | $3 | $15 | — | ||
| accounts/fireworks/models/deepseek-v4-pro-0813fireworks_ai/accounts/fireworks/models/deepseek-v4-pro-0813 | Fireworks_Ai |
1.04858M | $1.32 | $3.96 | — | ||
| ministral-14b-2512mistral/ministral-14b-2512 | Mistral |
262.144K | $0.2 | $0.2 | — | ||
| ministral-14b-latestmistral/ministral-14b-latest | Mistral |
262.144K | $0.2 | $0.2 | — | ||
| ministral-3b-2512mistral/ministral-3b-2512 | Mistral |
131.072K | $0.1 | $0.1 | — | ||
| ministral-3b-latestmistral/ministral-3b-latest | Mistral |
131.072K | $0.1 | $0.1 | — | ||
| mistral-medium-3mistral/mistral-medium-3 | Mistral |
262.144K | $1.5 | $7.5 | — | ||
| voxtral-small-2507mistral/voxtral-small-2507 | Mistral |
32.768K | $0.1 | $0.4 | — | ||
| zai-org/GLM-5.3-Flashtogether_ai/zai-org/glm-5.3-flash | 1.04858M | $0.15 | $0.5 | — | |||
| MiniMax: MiniMax M1minimax/minimax-m1 | MiniMax |
1M | $0.55 | $2.2 | — | ||
| glm-5.3zai/glm-5.3 | Zai |
1M | $1.4 | $4.4 | — | ||
| minimax-m3tencent/minimax-m3 | Tencent |
1M | $0.3 | $1.2 | — | ||
| zai-org/glm-5.3novita/zai-org/glm-5.3 | 1.04858M | $1.4 | $4.4 | — | |||
| deepseek/deepseek-v4-pro-0813novita/deepseek/deepseek-v4-pro-0813 | 1.04858M | $1.32 | $3.96 | — | |||
| moonshotai/kimi-k3novita/moonshotai/kimi-k3 | 1.04858M | $3 | $15 | — | |||
| tencent/hy3novita/tencent/hy3 | 262.144K | $0.14 | $0.58 | — | |||
| zai-org/glm-5.2novita/zai-org/glm-5.2 | 1.04858M | $1.4 | $4.4 | — | |||
| moonshotai/kimi-k2.7-codenovita/moonshotai/kimi-k2.7-code | 262.144K | $0.95 | $4 | — | |||
| SpaceXAI: Grok 4.5x-ai/grok-4.5 | xAI |
500K | $2 | $6 | — | ||
| deepseek/deepseek-v4-flash-vision-expnovita/deepseek/deepseek-v4-flash-vision-exp | 1.04858M | $0.44 | $1.32 | — | |||
| deepseek/deepseek-v4-flash-0731novita/deepseek/deepseek-v4-flash-0731 | 1.04858M | $0.44 | $1.32 | — | |||
| mindai/macaron-v1-ventinovita/mindai/macaron-v1-venti | 1.04858M | $1.5 | $4.5 | — | |||
| minimax/minimax-m3novita/minimax/minimax-m3 | 1M | $0.3 | $1.2 | — | |||
| deepseek/deepseek-v4-flashnovita/deepseek/deepseek-v4-flash | 1.04858M | $0.14 | $0.28 | — | |||
| deepseek/deepseek-v4-pronovita/deepseek/deepseek-v4-pro | 1.04858M | $1.6 | $3.2 | — | |||
| Thinking Machines: Inkling (batch)thinkingmachines/inkling:batch | Thinkingmachines |
524.288K | $1 | $4.05 | — | ||
| inclusionai/ling-3.0-flash-fastnovita/inclusionai/ling-3.0-flash-fast | 262.144K | $0.06 | $0.18 | — | |||
| qwen/qwen3.8-maxnovita/qwen/qwen3.8-max | 1M | $2 | $6 | — | |||
| inclusionai/ling-3.0-flashnovita/inclusionai/ling-3.0-flash | 262.144K | $0.06 | $0.18 | — | |||
| mindai/macaron-v1-tallnovita/mindai/macaron-v1-tall | 262.144K | $0.45 | $2.6 | — | |||
| stepfun/step-3.7-flashnovita/stepfun/step-3.7-flash | 262.144K | $0.2 | $1.15 | — | |||
| Mistral: Codestral 2508 (batch)mistralai/codestral-2508:batch | Mistral AI |
256K | $0.15 | $0.45 | — | ||
| nvidia/nemotron-3-nano-30b-a3bnovita/nvidia/nemotron-3-nano-30b-a3b | 262.144K | $0.05 | $0.2 | — | |||
| baidu/cobuddynovita/baidu/cobuddy | 131.072K | $0.28 | $1.13 | — |