Which AI model fits your task?

Find text, image and embedding recommendations, or browse video, speech and transcription models from the Ofox catalog. No login required.

Tap an answer to adjust

Top picks for Coding

6 models
1
MoonshotAI: Kimi K3Top pick
moonshotai/kimi-k3 · Moonshot
78Match
Intelligence Index 57Large context windowTop-tier qualityStrong reasoning
1M
Context
$3/M
Input
$15/M
Output
View details
2
Z.ai: GLM-5.2
z-ai/glm-5.2 · Zhipu
73Match
Intelligence Index 51Large context windowStrong reasoning
1M
Context
$1.4/M
Input
$4.4/M
Output
View details
3
Anthropic: Claude Sonnet 5
anthropic/claude-sonnet-5 · Anthropic
73Match
Intelligence Index 53Large context windowTop-tier qualityStrong reasoning
1M
Context
$2/M
Input
$10/M
Output
View details
4
Google: Gemini 3.5 Flash
google/gemini-3.5-flash · google
73Match
Intelligence Index 50Large context windowStrong reasoning
1M
Context
$1.5/M
Input
$9/M
Output
View details
5
OpenAI: GPT-6 Luna
openai/gpt-6-luna · OpenAI
72Match
Large context windowStrong reasoningNewly released
1M
Context
$0.1/M
Input
$0.5/M
Output
View details
6
Anthropic: Claude Haiku 5.5
anthropic/claude-haiku-5.5 · Anthropic
72Match
Large context windowStrong reasoningNewly released
1M
Context
$0.1/M
Input
$0.5/M
Output
View details

Found your model? Start building.

Compare first. Create an account when you are ready to use a model. API usage is billed according to the selected model and settings.

Create an Ofox account

Scores combine catalog data, benchmark references and estimates. Speed is estimated, not measured latency. Benchmark reference: 2026-07. Artificial Analysis

Browse models by task

Explore model shortlists for specific tasks and priorities.

Best LLM for CodingCode generation & agentic codingBest LLM for AI AgentsTool use & autonomous agentsBest LLM for RAGLong-context document Q&ABest Vision LLMImage & video understandingBest LLM for WritingContent & copywritingBest LLM for Data ExtractionStructured extraction at scaleBest LLM for TranslationMultilingual translationBest LLM for ChatbotsGeneral assistants & chatBest LLM for RoleplayCharacter & conversational roleplayCheapest LLM APILowest cost per tokenFastest LLM APILowest latency modelsBest AI Image ModelText-to-image generationBest Embedding ModelSemantic search & RAG retrievalBest LLM for ReasoningHard problems & deep reasoningBest Long-Context LLM1M+ token context windows

Frequently asked questions

How does the Model Finder pick models?+

Text, image and embedding candidates are scored using task-specific rules and available references. Video, speech and transcription candidates are listed by model ID without a comparative score; no cross-modal quality ranking is implied.

Is it free? Do I need an account?+

Yes, it's completely free and runs in your browser — no login or API key needed to get recommendations. You only need an Ofox account when you're ready to actually call a model.

Are these real, up-to-date models?+

Models come from the Ofox catalog. Availability and metadata can change; catalog refreshes do not refresh benchmark references. Check the model detail page before use.

Why doesn't the cheapest model always rank first?+

Unless you pick 'Lowest cost', the finder balances price against quality and capability. A model that costs a little more but is much more capable will often score higher — just like a person would choose.

Can I use the recommended models with my existing code?+

Integration depends on the model and task. Video, speech and transcription can use different endpoints, parameters and billing units. Follow the selected model’s documentation; changing only an API key and base URL may not be enough.

Found your model? Start building.

Compare first. Create an account when you are ready to use a model. API usage is billed according to the selected model and settings.

Create an Ofox account