cognitivecomputations/dolphin3.0-mistral-24b:free

Controls the creativity of responses. Higher values (e.g., 0.7) increase creativity; lower values (e.g., 0.2) make responses more predictable.

Specifies the maximum number of text units (tokens) allowed in a response, limiting its length.

Focuses on the most likely words based on a percentage of probability.

If true, returns the log probabilities of each output token returned in the content of message.

The `frequency_penalty` controls how often the model repeats itself, with higher positive values reducing repetition and negative values encouraging it.

Discourages responses that are too similar to previous ones.

Sends the response in real-time as it's being generated.

DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team.

deepseek/deepseek-chat-v3-0324:free

This parameter tells the model to stop generating text when it reaches any of the specified sequences (like a word or punctuation)

Defines the format or type of the generated response.

Enables parallel execution of tools, allowing multiple tools to run simultaneously.

GPT-4o is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of GPT-4 Turbo while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.

openai/gpt-4o

Lists tool definitions or capabilities available to the model.

Decides whether to use tools or just the model for generating responses.

DeepSeek-R1-0528 is a lightly upgraded release of DeepSeek R1 that taps more compute and smarter post-training tricks, pushing its reasoning and inference to the brink of flagship models like O3 and Gemini 2.5 Pro.

deepseek/deepseek-r1-0528-qwen3-8b:free

DeepSeek R1 is here: Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass.

deepseek/deepseek-r1:free

google/gemma-3n-e2b-it:free

qwen/qwen3-coder:free

moonshotai/kimi-k2:free

tencent/hunyuan-a13b-instruct:free

mistralai/devstral-small-2505:free

z-ai/glm-4.5-air:free

cognitivecomputations/dolphin-mistral-24b-venice-edition:free

mistralai/mistral-small-3.2-24b-instruct:free

google/gemini-3-flash-preview

GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding, and tool use, while reducing latency and cost for large-scale deployments.

Model	Context	Max output	Input	Output	Capabilities
deepseek/deepseek-chat-v3-0324:free Chat	—	16K	Free	Free	System prompt
openai/gpt-4o Chat	128K	16K	$2.50	$10.00	Vision, Tools, System prompt
deepseek/deepseek-r1-0528-qwen3-8b:free Chat	—	16K	Free	Free	System prompt
deepseek/deepseek-r1:free Chat	164K	16K	Free	Free	System prompt
google/gemma-3n-e2b-it:free Chat	—	16K	Free	Free	System prompt
qwen/qwen3-coder:free Chat	—	16K	Free	Free	System prompt
moonshotai/kimi-k2:free Chat	—	16K	Free	Free	Vision, Tools, System prompt
tencent/hunyuan-a13b-instruct:free Chat	—	16K	Free	Free	Vision, Tools, System prompt
mistralai/devstral-small-2505:free Chat	—	16K	Free	Free	Vision, Tools, System prompt
z-ai/glm-4.5-air:free Chat	—	16K	$32.00	$22.998	Vision, System prompt
cognitivecomputations/dolphin-mistral-24b-venice-edition:free Chat	—	16K	Free	Free	Vision, Tools, System prompt
mistralai/mistral-small-3.2-24b-instruct:free Chat	—	—	Free	Free	Vision, System prompt
google/gemini-3-flash-preview Chat	—	16K	$0.01	$0.12	Vision, Tools, System prompt
openai/gpt-5.4-mini Chat	—	128K	$0.75	$4.50	Vision, Tools, System prompt

cognitivecomputations/dolphin3.0-mistral-24b:free

Start building today