Earlier Kimi frontier model for long-context agents, coding, and multimodal work
47 providers
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows
34 providers
Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy
17 providers
Finance-enhanced model for financial research, multi-step investment workflows, and long-horizon planning and execution
4 providers
Fast Gemini model balancing multimodal reasoning, tool use, and cost
28 providers
Thinking Kimi model for slower research passes, planning, and hard technical questions
23 providers
High-effort o3 tier for difficult technical reasoning and careful answers
9 providers
Open MiMo model for multimodal coding agents and long-context automation
27 providers
Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use
28 providers
Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation
30 providers
Small GPT-5 for responsive agents, coding help, and everyday automation
32 providers
Coding-optimized GPT model for repository edits, reviews, and agentic software work
15 providers
Deliberate o-series reasoner for hard math, coding, and multi-step analysis
23 providers
Hybrid-linear MoE reasoning model with 124B total and 5.1B active parameters for efficient agents
5 providers
Newer StepFun flash model for faster agents, coding, and multimodal prompts
21 providers
Meituan LongCat-2.0, a reasoning model with tool calling and a 1M-token context window
6 providers
Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.
12 providers
StepFun flash lane for quick multimodal reasoning and coding assistance
15 providers
Open Gemma instruction model for efficient chat and self-hosted deployments
25 providers
Fast o-series model for compact reasoning, coding, and tool use
22 providers
Google's proven reasoning model for coding, math, and multimodal analysis
31 providers
Low-latency Gemini model for high-volume multimodal and agent workloads
15 providers
Fast Gemini workhorse for multimodal apps where latency and price matter
32 providers
September 2025 Kimi K2 instruction update with a 256K context and improved agentic coding
8 providers
O-series reasoning model for hard analysis, math, coding, and planning
17 providers
Largest Gemma 4 instruction model for open, self-hosted chat and reasoning
37 providers
DeepSeek chat model for instruction following, coding, and analysis
10 providers
Multimodal reasoning model for visual analysis, planning, and tool use
6 providers
Cohere command model for multilingual enterprise agents, tools, and chat
7 providers
May 2025 DeepSeek R1 update with improved mathematics, coding, and reasoning
10 providers
Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs
29 providers
Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads
13 providers
Nemotron middle tier for collaborative agents and high-volume reasoning workloads
17 providers
Kimi model for long-context chat, coding, and agentic reasoning
6 providers
Long-lived GPT workhorse for coding, instruction following, and production apps
31 providers
Smaller o-series reasoner for economical coding, math, and planning tasks
21 providers
O-series reasoning model for hard analysis, math, coding, and planning
8 providers
Reasoning model for deliberate analysis, multi-step problem solving, and tool use
6 providers
Web-grounded Sonar for multi-step research questions that need cited reasoning
9 providers
Open GPT reasoning model for self-hosted agents and controllable deployments
62 providers
Classic open reasoning model for transparent math, coding, and deliberate problem solving
16 providers
Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use
5 providers
Reasoning model for deliberate analysis, multi-step problem solving, and tool use
7 providers
Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents
19 providers
Affordable GPT-4.1 lane for fast coding help and structured extraction
28 providers
Open GPT reasoning model for self-hosted agents and controllable deployments
39 providers
DeepSeek chat model for instruction following, coding, and analysis
8 providers
Small Nemotron 3 MoE for efficient coding, math, and long-context agents
14 providers
GPT model for general reasoning, writing, coding, and tool-assisted tasks
9 providers
Tiny GPT-4.1 option for classification, routing, and very high-volume tasks
22 providers
| Model | Creator | Score | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|---|
| Kimi K2.5moonshotai/kimi-k2.5 | Moonshot AI |
23.5 | 262.144K | $0.375 | $2 | 2026-01-27 | ||
| GPT-5openai/gpt-5 | OpenAI |
23.0 | 400K | $1.25 | $10 | 2025-08-07 | ||
| Nemotron 3 Ultra 550B A55Bnvidia/nemotron-3-ultra-550b-a55b | NVIDIA |
22.9 | 1M | $0.1 | $0.1 | 2026-06-04 | ||
| Ling 3.0 Flash Fininclusionai/ling-3.0-flash-fin | 22.6 | 262.144K | $0.075 | $0.22 | 2026-08-27 | |||
| Gemini 3.5 Flash Litegoogle/gemini-3.5-flash-lite | Google |
22.2 | 1.04858M | $0.3 | $2.5 | 2026-07-21 | ||
| Kimi K2 Thinkingmoonshotai/kimi-k2-thinking | Moonshot AI |
22.0 | 262.144K | $0.4 | $2.5 | 2025-11-06 | ||
| o3-proopenai/o3-pro | OpenAI |
21.9 | 200K | $20 | $80 | 2025-06-10 | ||
| MiMo-V2.5xiaomi/mimo-v2.5 | Xiaomi |
21.8 | 1.04858M | $0.14 | $0.28 | 2026-04-22 | ||
| DeepSeek V3.2deepseek/deepseek-v3.2 | DeepSeek |
21.5 | 128K | $0.209 | $0.31 | 2025-12-01 | ||
| GPT-5.4 nanoopenai/gpt-5.4-nano | OpenAI |
20.7 | 400K | $0.2 | $1.25 | 2026-03-17 | ||
| GPT-5 Miniopenai/gpt-5-mini | OpenAI |
20.6 | 400K | $0.25 | $2 | 2025-08-07 | ||
| GPT-5.1 Codex miniopenai/gpt-5.1-codex-mini | OpenAI |
20.4 | 400K | $0.22 | $1.8 | 2025-11-13 | ||
| o3openai/o3 | OpenAI |
20.2 | 200K | $2 | $8 | 2025-04-16 | ||
| Ling 3.0 Flashinclusionai/ling-3.0-flash | 20.1 | 262.144K | $0.021 | $0.063 | 2026-07-23 | |||
| Step 3.7 Flashstepfun/step-3.7-flash | StepFun |
19.5 | 256K | $0.202 | $1.211 | 2026-05-29 | ||
| LongCat-2.0meituan/longcat-2.0 | 19.1 | 1M | $0.3 | $1.2 | 2026-06-30 | |||
| Muse Glimmer 30Bmeta/muse-glimmer-30b | Meta |
17.5 | 131.072K | $0.2 | $0.8 | 2026-08-10 | ||
| Step 3.5 Flashstepfun/step-3.5-flash | StepFun |
17.0 | 256K | $0.105 | $0.314 | 2026-01-29 | ||
| Gemma 4 26B A4B ITgoogle/gemma-4-26b-a4b-it | Google |
16.7 | 262.144K | $0.042 | $0.22 | 2026-04-02 | ||
| o4-miniopenai/o4-mini | OpenAI |
16.7 | 200K | $1.1 | $4.4 | 2025-04-16 | ||
| Gemini 2.5 Progoogle/gemini-2.5-pro | Google |
16.1 | 1.04858M | $1.25 | $10 | 2025-06-17 | ||
| Gemini 3.1 Flash Lite Previewgoogle/gemini-3.1-flash-lite-preview | Google |
15.6 | 1.04858M | $0.25 | $1.5 | 2026-03-03 | ||
| Gemini 2.5 Flashgoogle/gemini-2.5-flash | Google |
15.5 | 1.04858M | $0.3 | $2.5 | 2025-06-17 | ||
| Kimi K2 Instruct 0905moonshotai/kimi-k2-0905 | Moonshot AI |
15.3 | 262.144K | $0.6 | $2.5 | 2025-09-05 | ||
| o1openai/o1 | OpenAI |
15.2 | 200K | $15 | $60 | 2024-12-05 | ||
| Gemma 4 31B ITgoogle/gemma-4-31b-it | Google |
14.7 | 262.144K | $0.1 | $0.25 | 2026-04-02 | ||
| DeepSeek V3.1deepseek/deepseek-chat-v3.1 | DeepSeek |
13.7 | 163.84K | $0.19 | $0.79 | 2025-08-21 | ||
| Nova 2 Liteamazon/nova-2-lite-v1 | Amazon |
13.4 | 1M | $0.3 | $2.5 | 2025-12-02 | ||
| Command Acohere/command-a | Cohere |
13.1 | 256K | $2.5 | $10 | 2025-03-13 | ||
| DeepSeek R1 0528deepseek/deepseek-r1-0528 | DeepSeek |
13.1 | 163.84K | $0.2 | $0.8 | 2025-05-28 | ||
| GPT-5 Nanoopenai/gpt-5-nano | OpenAI |
13.0 | 400K | $0.05 | $0.4 | 2025-08-07 | ||
| Nemotron 3.5 Lightning 30B A3Bnvidia/nemotron-3.5-lightning | NVIDIA |
12.9 | 262.144K | $0.025 | $0.12 | 2026-08-11 | ||
| Nemotron 3 Super 120B A12Bnvidia/nemotron-3-super-120b-a12b | NVIDIA |
12.8 | 262.144K | $0.05 | $0.25 | 2026-03-11 | ||
| Kimi K2 0711moonshotai/kimi-k2 | Moonshot AI |
12.7 | 131.072K | $0.4 | $1.8 | 2025-07-11 | ||
| GPT-4.1openai/gpt-4.1 | OpenAI |
12.7 | 1.04758M | $2 | $8 | 2025-04-14 | ||
| o3-miniopenai/o3-mini | OpenAI |
12.5 | 200K | $1.1 | $4.4 | 2024-12-20 | ||
| o1-proopenai/o1-pro | OpenAI |
12.4 | 200K | $150 | $600 | 2025-03-19 | ||
| Mercury 2.5inception/mercury-2.5 | Inception |
12.3 | 260K | $0.2 | $0.75 | 2026-09-08 | ||
| Sonar Reasoning Properplexity/sonar-reasoning-pro | Perplexity |
11.8 | 128K | $2 | $8 | 2024-01-01 | ||
| GPT OSS 120Bopenai/gpt-oss-120b | OpenAI |
11.6 | 131.072K | $0.03 | $0.15 | 2025-08-05 | ||
| DeepSeek-R1deepseek/deepseek-r1 | DeepSeek |
11.4 | 128K | $0.58 | $2.319 | 2025-01-20 | ||
| Trinity Large Thinkingarcee-ai/trinity-large-thinking | 10.8 | 524.288K | $0.25 | $0.8 | 2026-04-01 | |||
| Mercury 2inception/mercury-2 | Inception |
10.8 | 128K | $0.25 | $0.75 | 2026-02-24 | ||
| Gemini 2.5 Flash-Litegoogle/gemini-2.5-flash-lite | Google |
10.4 | 1.04858M | $0.1 | $0.4 | 2025-06-17 | ||
| GPT-4.1 miniopenai/gpt-4.1-mini | OpenAI |
10.2 | 1.04758M | $0.4 | $1.6 | 2025-04-14 | ||
| GPT OSS 20Bopenai/gpt-oss-20b | OpenAI |
10.0 | 131.072K | $0.018 | $0.09 | 2025-08-05 | ||
| DeepSeek V3 0324deepseek/deepseek-chat-v3-0324 | DeepSeek |
9.7 | 163.84K | $0.2 | $0.8 | 2025-03-24 | ||
| Nemotron 3 Nano 30B A3Bnvidia/nemotron-3-nano-30b-a3b | NVIDIA |
8.9 | 262.144K | $0.05 | $0.2 | 2025-12-15 | ||
| GPT-4o (2024-11-20)openai/gpt-4o-2024-11-20 | OpenAI |
8.4 | 128K | $2.5 | $10 | 2024-11-20 | ||
| GPT-4.1 nanoopenai/gpt-4.1-nano | OpenAI |
7.8 | 1.04758M | $0.1 | $0.4 | 2025-04-14 |