Multimodal Kimi workhorse for agent loops, coding tasks, and visual context
69 providers
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
Earlier Kimi frontier model for long-context agents, coding, and multimodal work
47 providers
Default frontier GPT for coding, computer use, research, and knowledge work
50 providers
GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...
Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking
67 providers
Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...
Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...
GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading...
GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, complex coding,...
Coding-optimized GPT model for repository edits, reviews, and agentic software work
13 providers
GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning...
Sharper GPT-5 generation for coding, product work, and tool-assisted tasks
30 providers
GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while...
Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...
Reliable GPT generation for broad coding, writing, and tool-assisted product work
36 providers
GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly...
Reasoning-first Gemini preview for agentic coding and complex problem solving
37 providers
Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...
New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs
28 providers
Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...
Code-specialist GPT for repository edits, reviews, and long-running software agents
23 providers
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...
Agent-ready GPT for coding and computer-use workflows at a lower cost
46 providers
GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...
Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...
Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...
Coding-optimized GPT model for repository edits, reviews, and agentic software work
33 providers
| Model | Creator | Score | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|---|
| Kimi K2.6moonshotai/kimi-k2.6 | Moonshot AI |
1154.0 | 262.144K | $0.95 | $4 | 2026-04-20 | ||
| Kimi K2.5moonshotai/kimi-k2.5 | Moonshot AI |
1147.0 | 262.144K | $0.375 | $2 | 2026-01-27 | ||
| GPT-5.5openai/gpt-5.5 | OpenAI |
1142.0 | 1.05M | $5 | $30 | 2026-04-23 | ||
| OpenAI: GPT-5.5 (batch)openai/gpt-5.5:batch | OpenAI |
1142.0 | 1.05M | $2.5 | $15 | — | ||
| Kimi K2.7 Codemoonshotai/kimi-k2.7-code | Moonshot AI |
1141.0 | 262.144K | $0.95 | $4 | 2026-06-12 | ||
| Anthropic: Claude Sonnet 4.5anthropic/claude-sonnet-4.5 | Anthropic |
1135.0 | 1M | $3 | $15 | — | ||
| Anthropic: Claude Sonnet 4.5 (batch)anthropic/claude-sonnet-4.5:batch | Anthropic |
1135.0 | 1M | $1.5 | $7.5 | — | ||
| Z.ai: GLM 5z-ai/glm-5 | Z Ai |
1134.0 | 202.752K | $1 | $3.2 | — | ||
| Z.ai: GLM 5V Turboz-ai/glm-5v-turbo | Z Ai |
1134.0 | 202.752K | $1.2 | $4 | — | ||
| GPT-5-Codexopenai/gpt-5-codex | OpenAI |
1126.0 | 400K | $1.1 | $9 | 2025-09-15 | ||
| OpenAI: GPT-5.1 (batch)openai/gpt-5.1:batch | OpenAI |
1118.0 | 400K | $0.625 | $5 | — | ||
| GPT-5.1openai/gpt-5.1 | OpenAI |
1117.0 | 400K | $1.25 | $10 | 2025-11-13 | ||
| Z.ai: GLM 4.7z-ai/glm-4.7 | Z Ai |
1105.0 | 204.8K | $0.54 | $1.98 | — | ||
| Z.ai: GLM 4.6z-ai/glm-4.6 | Z Ai |
1096.0 | 204.8K | $0.55 | $2.2 | — | ||
| GPT-5.2openai/gpt-5.2 | OpenAI |
1093.0 | 400K | $1.75 | $14 | 2025-12-11 | ||
| OpenAI: GPT-5.2 (batch)openai/gpt-5.2:batch | OpenAI |
1093.0 | 400K | $0.875 | $7 | — | ||
| Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-preview | Google |
1092.0 | 1.04858M | $2 | $12 | 2026-02-19 | ||
| Google: Gemini 3.1 Pro Preview (batch)google/gemini-3.1-pro-preview:batch | Google |
1092.0 | 1.04858M | $1 | $6 | — | ||
| Gemini 3 Flash Previewgoogle/gemini-3-flash-preview | Google |
1090.0 | 1.04858M | $0.5 | $3 | 2025-12-17 | ||
| Google: Gemini 3 Flash Preview (batch)google/gemini-3-flash-preview:batch | Google |
1090.0 | 1.04858M | $0.25 | $1.5 | — | ||
| GPT-5.2 Codexopenai/gpt-5.2-codex | OpenAI |
1088.0 | 400K | $0.14 | $1.14 | 2025-12-11 | ||
| SpaceXAI: Grok 4.20x-ai/grok-4.20 | xAI |
1088.0 | 2M | $1.25 | $2.5 | — | ||
| GPT-5.4openai/gpt-5.4 | OpenAI |
1085.0 | 1.05M | $2.5 | $15 | 2026-03-05 | ||
| OpenAI: GPT-5.4 (batch)openai/gpt-5.4:batch | OpenAI |
1085.0 | 1.05M | $1.25 | $7.5 | — | ||
| SpaceXAI: Grok 4.3x-ai/grok-4.3 | xAI |
1056.0 | 1M | $1.25 | $2.5 | — | ||
| SpaceXAI: Grok 4.3 (batch)x-ai/grok-4.3:batch | xAI |
1056.0 | 1M | $1 | $2 | — | ||
| GPT-5.3 Codexopenai/gpt-5.3-codex | OpenAI |
1053.0 | 400K | $1.75 | $14 | 2026-02-05 |