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.
Jamba Large 1.7 is the latest model in the Jamba open family, offering improvements in grounding, instruction-following, and overall efficiency. Built on a hybrid SSM-Transformer architecture with a 256K context...
DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.
Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design...
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.
Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts text, image, and video input and returns text,...
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 Pro is the same underlying model as [GPT-6 Astra](https://openrouter.ai/openai/gpt-6-astra), 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.
Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...
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.
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...
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.
The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.
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.
This model always redirects to the latest model in the Claude Fable 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.
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...
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...
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.
| Model | Creator | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|
| gpt-5.4-miniazure/gpt-5.4-mini | Azure |
272K | $0.75 | $4.5 | — | ||
| llama3.1-70bcerebras/llama3.1-70b | Cerebras |
128K | $0.6 | $0.6 | — | ||
| gpt-5.4-mini-2026-03-17azure/gpt-5.4-mini-2026-03-17 | Azure |
272K | $0.75 | $4.5 | — | ||
| AI21: Jamba Large 1.7ai21/jamba-large-1.7 | 256K | $2 | $8 | — | |||
| DeepSeek: DeepSeek V4 Pro 0813 (batch)deepseek/deepseek-v4-pro-0813:batch | DeepSeek |
1.04858M | $0.66 | $1.98 | — | ||
| Qwen: Qwen3.5-9B (batch)qwen/qwen3.5-9b:batch | Alibaba Qwen |
262.144K | $0.17 | $0.25 | — | ||
| gpt-5.4-nanoazure/gpt-5.4-nano | Azure |
272K | $0.2 | $1.25 | — | ||
| gpt-5.4-nano-2026-03-17azure/gpt-5.4-nano-2026-03-17 | Azure |
272K | $0.2 | $1.25 | — | ||
| mistral-large-2402azure/mistral-large-2402 | Azure |
32K | $8 | $24 | — | ||
| deepseek-ai/ESFT-token-math-litedeepseek-ai/ESFT-token-math-lite | DeepSeek |
Not documented | — | — | — | ||
| Qwen: Qwen3.8 Max (0902)qwen/qwen3.8-max-0902 | Alibaba Qwen |
1M | $2 | $6 | — | ||
| mistral-large-latestazure/mistral-large-latest | Azure |
32K | $8 | $24 | — | ||
| o1azure/o1 | Azure |
200K | $15 | $60 | — | ||
| o1-2024-12-17azure/o1-2024-12-17 | Azure |
200K | $15 | $60 | — | ||
| OpenAI: GPT-6 Astra Proopenai/gpt-6-astra-pro | OpenAI |
1.05M | $10 | $50 | — | ||
| o1-miniazure/o1-mini | Azure |
128K | $1.21 | $4.84 | — | ||
| o1-mini-2024-09-12azure/o1-mini-2024-09-12 | Azure |
128K | $1.1 | $4.4 | — | ||
| o1-previewazure/o1-preview | Azure |
128K | $15 | $60 | — | ||
| Qwen: Qwen3.8 27Bqwen/qwen3.8-27b | Alibaba Qwen |
262.144K | $0.214 | $2.55 | — | ||
| o1-preview-2024-09-12azure/o1-preview-2024-09-12 | Azure |
128K | $15 | $60 | — | ||
| llama3.1-8bcerebras/llama3.1-8b | Cerebras |
128K | $0.1 | $0.1 | — | ||
| o3azure/o3 | Azure |
200K | $2 | $8 | — | ||
| us-west-2/moonshotai.kimi-k2-thinkingbedrock/us-west-2/moonshotai.kimi-k2-thinking | 262.144K | $0.6 | $2.5 | — | |||
| o3-2025-04-16azure/o3-2025-04-16 | Azure |
200K | $2 | $8 | — | ||
| o3-miniazure/o3-mini | Azure |
200K | $1.1 | $4.4 | — | ||
| o3-mini-2025-01-31azure/o3-mini-2025-01-31 | Azure |
200K | $1.1 | $4.4 | — | ||
| nvidia/nemotron-3-ultra-550b-a55btogether_ai/nvidia/nemotron-3-ultra-550b-a55b | 512.288K | $0.6 | $3.6 | — | |||
| anthropic.claude-3-sonnet-20240229-v1:0bedrock/anthropic.claude-3-sonnet-20240229-v1:0 | 200K | $3 | $15 | — | |||
| Google: Gemma 4 31B (free)google/gemma-4-31b-it:free | Google |
262.144K | Free | Free | — | ||
| o4-mini-2025-04-16azure/o4-mini-2025-04-16 | Azure |
200K | $1.1 | $4.4 | — | ||
| us/gpt-4.1-2025-04-14azure/us/gpt-4.1-2025-04-14 | Azure |
1.04758M | $2.2 | $8.8 | — | ||
| us/gpt-4.1-mini-2025-04-14azure/us/gpt-4.1-mini-2025-04-14 | Azure |
1.04758M | $0.44 | $1.76 | — | ||
| us/gpt-4.1-nano-2025-04-14azure/us/gpt-4.1-nano-2025-04-14 | Azure |
1.04758M | $0.11 | $0.44 | — | ||
| us/gpt-4o-2024-08-06azure/us/gpt-4o-2024-08-06 | Azure |
128K | $2.75 | $11 | — | ||
| us/gpt-4o-2024-11-20azure/us/gpt-4o-2024-11-20 | Azure |
128K | $2.75 | $11 | — | ||
| Mistral: Ministral 3 3B 2512mistralai/ministral-3b-2512 | Mistral AI |
131.072K | $0.1 | $0.1 | — | ||
| Qwen: Qwen Plus 0728qwen/qwen-plus-2025-07-28 | Alibaba Qwen |
1M | $0.26 | $0.78 | — | ||
| us/gpt-4o-mini-2024-07-18azure/us/gpt-4o-mini-2024-07-18 | Azure |
128K | $0.165 | $0.66 | — | ||
| us/gpt-5-2025-08-07azure/us/gpt-5-2025-08-07 | Azure |
272K | $1.375 | $11 | — | ||
| @cf/meta/llama-3.3-70b-instruct-fp8-fastcloudflare/@cf/meta/llama-3.3-70b-instruct-fp8-fast | Cloudflare |
24K | $0.293 | $2.253 | — | ||
| us/gpt-5-mini-2025-08-07azure/us/gpt-5-mini-2025-08-07 | Azure |
272K | $0.275 | $2.2 | — | ||
| Anthropic: Claude Fable Latest~anthropic/claude-fable-latest | Anthropic |
1M | $10 | $50 | — | ||
| us/gpt-5-nano-2025-08-07azure/us/gpt-5-nano-2025-08-07 | Azure |
272K | $0.055 | $0.44 | — | ||
| us/gpt-5.1azure/us/gpt-5.1 | Azure |
272K | $1.38 | $11 | — | ||
| @cf/ibm-granite/granite-4.0-h-microcloudflare/@cf/ibm-granite/granite-4.0-h-micro | Cloudflare |
131K | $0.017 | $0.112 | — | ||
| Mistral: Mistral Medium 3mistralai/mistral-medium-3 | Mistral AI |
131.072K | $0.4 | $2 | — | ||
| Meta: Llama 3.2 1B Instructmeta-llama/llama-3.2-1b-instruct | Meta |
60K | $0.027 | $0.201 | — | ||
| us/o1-2024-12-17azure/us/o1-2024-12-17 | Azure |
200K | $16.5 | $66 | — | ||
| us/o1-mini-2024-09-12azure/us/o1-mini-2024-09-12 | Azure |
128K | $1.21 | $4.84 | — | ||
| gpt-5.2-chatazure/gpt-5.2-chat | Azure |
128K | $1.75 | $14 | — |