StepFun flash lane for quick multimodal reasoning and coding assistance
15 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
Fast Grok model for responsive chat, reasoning, and tool-assisted work
2 providers
Fast Grok model for responsive chat, reasoning, and tool-assisted work
3 providers
MiMo flash model for fast multimodal assistance and agent workflows
7 providers
Reliable GPT generation for broad coding, writing, and tool-assisted product work
36 providers
Thinking Kimi model for slower research passes, planning, and hard technical questions
23 providers
Flagship Qwen3 model for coding agents, complex reasoning, and tool use
23 providers
September 2025 Kimi K2 instruction update with a 256K context and improved agentic coding
8 providers
Flagship Qwen model for complex reasoning, coding, and agentic workflows
3 providers
Fast Grok model for responsive chat, reasoning, and tool-assisted work
2 providers
Hybrid-reasoning DeepSeek model with thinking and non-thinking modes
13 providers
Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows
34 providers
Fast Gemini workhorse for multimodal apps where latency and price matter
32 providers
Google's proven reasoning model for coding, math, and multimodal analysis
31 providers
Dense open Qwen model for self-hosted chat, reasoning, and coding
16 providers
Sparse MoE Qwen model with 3B active parameters for efficient chat and reasoning
10 providers
Classic open reasoning model for transparent math, coding, and deliberate problem solving
16 providers
Open DeepSeek MoE chat model for coding, math, and general reasoning
10 providers
Earlier Gemini Flash workhorse for responsive multimodal apps and tool use
3 providers
| Model | Creator | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|
| Step 3.5 Flashstepfun/step-3.5-flash | StepFun |
256K | $0.105 | $0.314 | 2026-01-29 | ||
| Kimi K2.5moonshotai/kimi-k2.5 | Moonshot AI |
262.144K | $0.375 | $2 | 2026-01-27 | ||
| X-Ai/Grok-4-Fast-Reasoningxai/grok-4-fast-reasoning | xAI |
2M | $0.2 | $0.5 | 2025-12-18 | ||
| X-Ai/Grok-4-Fast-Non-Reasoningxai/grok-4-fast-non-reasoning | xAI |
2M | $0.2 | $0.5 | 2025-12-18 | ||
| MiMo-V2-Flashxiaomi/mimo-v2-flash | Xiaomi |
262.144K | — | — | 2025-12-16 | ||
| GPT-5.2openai/gpt-5.2 | OpenAI |
400K | $1.75 | $14 | 2025-12-11 | ||
| Kimi K2 Thinkingmoonshotai/kimi-k2-thinking | Moonshot AI |
262.144K | $0.4 | $2.5 | 2025-11-06 | ||
| Qwen3 Maxalibaba/qwen3-max | Alibaba Qwen |
262.144K | $1.2 | $6 | 2025-09-23 | ||
| Kimi K2 Instruct 0905moonshotai/kimi-k2-0905 | Moonshot AI |
262.144K | $0.6 | $2.5 | 2025-09-05 | ||
| Qwen3 Max Previewalibaba/qwen3-max-preview | Alibaba Qwen |
262.144K | $0.87 | $3.478 | 2025-09-05 | ||
| x-AI/Grok-Code-Fast 1xai/grok-code-fast-1 | xAI |
256K | $0.2 | $1.5 | 2025-09-02 | ||
| DeepSeek-V3.1deepseek/deepseek-v3.1 | DeepSeek |
131.072K | $0.19 | $0.71 | 2025-08-21 | ||
| GPT-5openai/gpt-5 | OpenAI |
400K | $1.25 | $10 | 2025-08-07 | ||
| Gemini 2.5 Flashgoogle/gemini-2.5-flash | Google |
1.04858M | $0.3 | $2.5 | 2025-06-17 | ||
| Gemini 2.5 Progoogle/gemini-2.5-pro | Google |
1.04858M | $1.25 | $10 | 2025-06-17 | ||
| Qwen3 32Balibaba/qwen3-32b | Alibaba Qwen |
131.072K | $0.7 | $2.8 | 2025-04-28 | ||
| Qwen3 30B A3Balibaba/qwen3-30b-a3b | Alibaba Qwen |
131.072K | $0.08 | $0.29 | 2025-04-28 | ||
| DeepSeek-R1deepseek/deepseek-r1 | DeepSeek |
128K | $0.58 | $2.319 | 2025-01-20 | ||
| DeepSeek-V3deepseek/deepseek-v3 | DeepSeek |
131.072K | $0.27 | $1.1 | 2024-12-26 | ||
| Gemini 2.0 Flashgoogle/gemini-2.0-flash | Google |
1.04858M | $0.1 | $0.42 | 2024-12-11 |