GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks. Training data up to Sep 2021.
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
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...
KAT-Coder-Pro V2 is the latest high-performance model in KwaiKAT’s KAT-Coder series, designed for complex enterprise-grade software engineering and SaaS integration. It builds on the agentic coding strengths of earlier versions,...
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...
Rocinante 12B is designed for engaging storytelling and rich prose. Early testers have reported: - Expanded vocabulary with unique and expressive word choices - Enhanced creativity for vivid narratives -...
NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and...
This model always redirects to the latest model in the DeepSeek V4 Flash family.
No provider description is available for this model yet.
No provider description is available for this model yet.
WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model. It demonstrates highly competitive performance compared to leading proprietary models, and it consistently outperforms all existing state-of-the-art opensource models. It is...
No provider description is available for this model yet.
Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding,...
Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length...
No provider description is available for this model yet.
No provider description is available for this model yet.
An attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory. Meant for use in roleplay/narrative situations.
No provider description is available for this model yet.
No provider description is available for this model yet.
Qwen2.5 7B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...
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...
This model always redirects to the latest model in the Claude Opus family.
No provider description is available for this model yet.
No provider description is available for this model yet.
This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://openrouter.ai/anthropic/claude-3-opus). The model is fine-tuned on top of [Qwen2.5 72B](https://openrouter.ai/qwen/qwen-2.5-72b-instruct).
No provider description is available for this model yet.
UnslopNemo v4.1 is the latest addition from the creator of Rocinante, designed for adventure writing and role-play scenarios.
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.
Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Significantly improvements in **code generation**, **code reasoning**...
No provider description is available for this model yet.
No provider description is available for this model yet.
This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)....
Euryale L3.3 70B is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.2](/models/sao10k/l3-euryale-70b).
[GPT-5.4](https://openrouter.ai/openai/gpt-5.4) Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multimodal workflows, allowing users to seamlessly move between reasoning, coding, and...
Fast-mode variant of [Opus 4.8](/anthropic/claude-opus-4.8) - identical capabilities with higher output speed at 2x pricing relative to regular Opus 4.8. Learn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode Note: As of September...
No provider description is available for this model yet.
No provider description is available for this model yet.
Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December...
No provider description is available for this model yet.
No provider description is available for this model yet.
This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up...
[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...
No provider description is available for this model yet.
No provider description is available for this model yet.
This model is a variant of GPT-3.5 Turbo tuned for instructional prompts and omitting chat-related optimizations. Training data: up to Sep 2021.
No provider description is available for this model yet.
No provider description is available for this model yet.
The Auto Router automatically selects the best model for your prompt, powered by the wisdom of the market. It routes you based on what the OpenRouter community collectively spends on...
MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billion parameters, with 45.9 billion parameters activated per inference, and can handle a context...
| Model | Creator | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|
| OpenAI: GPT-3.5 Turbo (older v0613)openai/gpt-3.5-turbo-0613 | OpenAI |
4.095K | $1 | $2 | — | ||
| Qwen: Qwen3.5 Plus 2026-04-20qwen/qwen3.5-plus-20260420 | Alibaba Qwen |
1M | $0.3 | $1.8 | — | ||
| Kwaipilot: KAT-Coder-Pro V2kwaipilot/kat-coder-pro-v2 | 262.144K | $0.3 | $1.2 | — | |||
| Kwaipilot: KAT-Coder-Air V2.5kwaipilot/kat-coder-air-v2.5 | 256K | $0.15 | $0.6 | — | |||
| TheDrummer: Rocinante 12Bthedrummer/rocinante-12b | 65.536K | $0.25 | $0.5 | — | |||
| NVIDIA: Nemotron Nano 9B V2 (free)nvidia/nemotron-nano-9b-v2:free | NVIDIA |
128K | Free | Free | — | ||
| DeepSeek: DeepSeek V4 Flash Latest~deepseek/deepseek-v4-flash-latest | Deepseek |
1.04858M | $0.03 | $0.07 | — | ||
| glm-5p2-fast-usfireworks_ai/glm-5p2-fast-us | Fireworks_Ai |
1.04858M | $2.1 | $6.6 | — | ||
| FW-Kimi-K2.5azure_ai/fw-kimi-k2.5 | 262.144K | $0.66 | $3.3 | — | |||
| WizardLM-2 8x22Bmicrosoft/wizardlm-2-8x22b | Microsoft |
65.535K | $0.62 | $0.62 | — | ||
| us-gov.nvidia.nemotron-nano-9b-v2bedrock_converse/us-gov.nvidia.nemotron-nano-9b-v2 | 128K | $0.072 | $0.276 | — | |||
| Mistral: Mixtral 8x22B Instructmistralai/mixtral-8x22b-instruct | Mistral AI |
65.536K | $2 | $6 | — | ||
| Amazon: Nova Micro 1.0amazon/nova-micro-v1 | Amazon |
128K | $0.035 | $0.14 | — | ||
| glm-5p2-fastfireworks_ai/glm-5p2-fast | Fireworks_Ai |
1.04858M | $2.1 | $6.6 | — | ||
| deepseek-v4-flash-0731fireworks_ai/deepseek-v4-flash-0731 | Fireworks_Ai |
1.04858M | $0.14 | $0.28 | — | ||
| Mancer: Weaver (alpha)mancer/weaver | 8K | $0.4 | $0.75 | — | |||
| FW-Inklingazure_ai/fw-inkling | 1.04858M | $1 | $4.05 | — | |||
| FW-GLM-5.2-Fastazure_ai/fw-glm-5.2-fast | 1.04858M | $2.1 | $6.6 | — | |||
| Qwen: Qwen2.5 7B Instructqwen/qwen-2.5-7b-instruct | Alibaba Qwen |
32.768K | $0.1 | $0.2 | — | ||
| Amazon: Nova Lite 1.0amazon/nova-lite-v1 | Amazon |
300K | $0.06 | $0.24 | — | ||
| Anthropic: Claude Opus Latest~anthropic/claude-opus-latest | Anthropic |
1M | $5 | $25 | — | ||
| us-gov.nvidia.nemotron-nano-12b-v2bedrock_converse/us-gov.nvidia.nemotron-nano-12b-v2 | 128K | $0.24 | $0.72 | — | |||
| us-gov.nvidia.nemotron-nano-3-30bbedrock_converse/us-gov.nvidia.nemotron-nano-3-30b | 262.144K | $0.072 | $0.288 | — | |||
| Magnum v4 72Banthracite-org/magnum-v4-72b | 32.768K | $2.5 | $5 | — | |||
| FW-GLM-5.2azure_ai/fw-glm-5.2 | 1.04858M | $1.54 | $4.84 | — | |||
| TheDrummer: UnslopNemo 12Bthedrummer/unslopnemo-12b | 1.024M | $0.4 | $0.4 | — | |||
| Meta: Llama 3.3 70B Instructmeta-llama/llama-3.3-70b-instruct | Meta |
131.072K | $0.1 | $0.32 | — | ||
| FW-GLM-5.1azure_ai/fw-glm-5.1 | 202.8K | $1.54 | $4.84 | — | |||
| accounts/fireworks/models/kimi-k3fireworks_ai/accounts/fireworks/models/kimi-k3 | Fireworks_Ai |
1.04858M | $3 | $15 | — | ||
| Qwen2.5 Coder 32B Instructqwen/qwen-2.5-coder-32b-instruct | Alibaba Qwen |
32.768K | $0.66 | $1 | — | ||
| accounts/fireworks/models/deepseek-v4-flash-0731fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-0731 | Fireworks_Ai |
1.04858M | $0.14 | $0.28 | — | ||
| gemini-3.5-live-translate-previewgemini/gemini-3.5-live-translate-preview | Not documented | $3.5 | $21 | — | |||
| Mistral Large 2407mistralai/mistral-large-2407 | Mistral AI |
131.072K | $2 | $6 | — | ||
| Sao10K: Llama 3.3 Euryale 70Bsao10k/l3.3-euryale-70b | 131.072K | $0.65 | $0.75 | — | |||
| OpenAI: GPT-5.4 Image 2openai/gpt-5.4-image-2 | OpenAI |
272K | $8 | $15 | — | ||
| Anthropic: Claude Opus 4.8 (Fast)anthropic/claude-opus-4.8-fast | Anthropic |
1M | $10 | $50 | — | ||
| us-gov.anthropic.claude-fable-5-1bedrock_converse/us-gov.anthropic.claude-fable-5-1 | 1M | $12 | $60 | — | |||
| swe-1.7cognition/swe-1.7 | Not documented | $2.5 | $12.5 | — | |||
| Amazon: Nova Pro 1.0amazon/nova-pro-v1 | Amazon |
300K | $0.8 | $3.2 | — | ||
| us-gov.anthropic.claude-opus-5bedrock_converse/us-gov.anthropic.claude-opus-5 | 1M | $6 | $30 | — | |||
| mistralollama/mistral | 8.192K | — | — | — | |||
| OpenAI: GPT-3.5 Turbo 16kopenai/gpt-3.5-turbo-16k | OpenAI |
16.385K | $3 | $4 | — | ||
| Microsoft: Phi 4microsoft/phi-4 | Microsoft |
16.384K | $0.07 | $0.14 | — | ||
| us-east-1/deepseek.v3.2bedrock/us-east-1/deepseek.v3.2 | 163.84K | $0.62 | $1.85 | — | |||
| us-east-1/mistral.mixtral-8x7b-instruct-v0:1bedrock/us-east-1/mistral.mixtral-8x7b-instruct-v0:1 | 32K | $0.45 | $0.7 | — | |||
| OpenAI: GPT-3.5 Turbo Instructopenai/gpt-3.5-turbo-instruct | OpenAI |
4.095K | $1.5 | $2 | — | ||
| swe-1.6cognition/swe-1.6 | Not documented | $0.5 | $2.5 | — | |||
| FW-GLM-5azure_ai/fw-glm-5 | 200K | $1.1 | $3.52 | — | |||
| Auto Routeropenrouter/auto | Openrouter |
2M | — | — | — | ||
| MiniMax: MiniMax-01minimax/minimax-01 | MiniMax |
1.00019M | $0.2 | $1.1 | — |