Open Gemma instruction model for efficient chat and self-hosted deployments
25 providers
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
Largest Gemma 4 instruction model for open, self-hosted chat and reasoning
37 providers
Earlier Qwen multimodal workhorse for million-token agent and document tasks
25 providers
Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use
5 providers
Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks
10 providers
Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation
30 providers
Strong small GPT for coding subagents, quick tool use, and high-volume work
35 providers
Efficient Mistral model for fast chat, extraction, and production assistants
5 providers
Nemotron middle tier for collaborative agents and high-volume reasoning workloads
17 providers
More exact GPT-5.4 tier for demanding professional reasoning and agent tasks
22 providers
Agent-ready GPT for coding and computer-use workflows at a lower cost
46 providers
Low-latency Gemini model for high-volume multimodal and agent workloads
15 providers
Image model for prompt-driven generation, editing, and visual design workflows
9 providers
Reasoning model for deliberate analysis, multi-step problem solving, and tool use
7 providers
Qwen vision-language model for visual reasoning, documents, and agent tasks
10 providers
Reasoning-first Gemini preview for agentic coding and complex problem solving
37 providers
Claude workhorse for coding agents, careful analysis, and production cost control
49 providers
Qwen vision-language model for visual reasoning, documents, and agent tasks
16 providers
General GLM flagship for coding, analysis, and tool-heavy engineering workflows
41 providers
Coding-optimized GPT model for repository edits, reviews, and agentic software work
33 providers
High-end Claude for difficult coding, planning, and slower expert reasoning
40 providers
Open-weight Qwen coding model for agents, repository edits, and multi-turn tool use
15 providers
StepFun flash lane for quick multimodal reasoning and coding assistance
15 providers
Earlier Kimi frontier model for long-context agents, coding, and multimodal work
47 providers
ByteDance Seed model for multimodal reasoning, long-context analysis, and agent workflows
4 providers
MiMo flash model for fast multimodal assistance and agent workflows
7 providers
Small Nemotron 3 MoE for efficient coding, math, and long-context agents
14 providers
Code-specialist GPT for repository edits, reviews, and long-running software agents
23 providers
Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows
15 providers
Reliable GPT generation for broad coding, writing, and tool-assisted product work
36 providers
GLM vision model for visual reasoning, documents, and multimodal agents
12 providers
Multimodal reasoning model for visual analysis, planning, and tool use
5 providers
Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use
28 providers
Reasoning-tuned 26B MoE model with 3B active parameters for agents, tools, and multi-step workloads
2 providers
Flagship Claude model for deep reasoning, coding, and long-horizon agents
19 providers
Preview Gemini flagship for complex reasoning, coding, and rich multimodal prompts
10 providers
Coding-optimized GPT model for repository edits, reviews, and agentic software work
18 providers
Codex GPT for repository edits, code review, and practical software agents
19 providers
Coding-optimized GPT model for repository edits, reviews, and agentic software work
15 providers
Thinking Kimi model for slower research passes, planning, and hard technical questions
23 providers
Safety model for policy screening, moderation, and risk-aware routing workflows
9 providers
Safety model for policy screening, moderation, and risk-aware routing workflows
5 providers
Nemotron multimodal model for visual reasoning and agentic AI workflows
3 providers
Fast Claude model for responsive assistance, classification, and lightweight agents
23 providers
ByteDance Seed model for long-context reasoning, instruction following, and tool-assisted tasks
4 providers
Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning
16 providers
Balanced Claude model for coding, analysis, agent workflows, and cost control
20 providers
Flagship Qwen3 model for coding agents, complex reasoning, and tool use
23 providers
Coding-optimized GPT model for repository edits, reviews, and agentic software work
13 providers
Efficient Qwen thinking model for local reasoning, math, and coding agents
10 providers
| Model | Creator | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|
| Gemma 4 26B A4B ITgoogle/gemma-4-26b-a4b-it | Google |
262.144K | $0.042 | $0.22 | 2026-04-02 | ||
| Gemma 4 31B ITgoogle/gemma-4-31b-it | Google |
262.144K | $0.1 | $0.25 | 2026-04-02 | ||
| Qwen3.6 Plusalibaba/qwen3.6-plus | Alibaba Qwen |
1M | $0.5 | $3 | 2026-04-02 | ||
| Trinity Large Thinkingarcee-ai/trinity-large-thinking | 524.288K | $0.25 | $0.8 | 2026-04-01 | |||
| MiMo-V2-Proxiaomi/mimo-v2-pro | Xiaomi |
1.04858M | $1 | $3 | 2026-03-18 | ||
| GPT-5.4 nanoopenai/gpt-5.4-nano | OpenAI |
400K | $0.2 | $1.25 | 2026-03-17 | ||
| GPT-5.4 miniopenai/gpt-5.4-mini | OpenAI |
400K | $0.75 | $4.5 | 2026-03-17 | ||
| Mistral Small (latest)mistral/mistral-small-latest | Mistral AI |
256K | $0.15 | $0.6 | 2026-03-16 | ||
| Nemotron 3 Super 120B A12Bnvidia/nemotron-3-super-120b-a12b | NVIDIA |
262.144K | $0.05 | $0.25 | 2026-03-11 | ||
| GPT-5.4 Proopenai/gpt-5.4-pro | OpenAI |
1.05M | $30 | $180 | 2026-03-05 | ||
| GPT-5.4openai/gpt-5.4 | OpenAI |
1.05M | $2.5 | $15 | 2026-03-05 | ||
| Gemini 3.1 Flash Lite Previewgoogle/gemini-3.1-flash-lite-preview | Google |
1.04858M | $0.25 | $1.5 | 2026-03-03 | ||
| Nano Banana 2 Previewgoogle/gemini-3.1-flash-image-preview | Google |
65.536K | $0.5 | $3 | 2026-02-26 | ||
| Mercury 2inception/mercury-2 | Inception |
128K | $0.25 | $0.75 | 2026-02-24 | ||
| Qwen3.5 Flashalibaba/qwen3.5-flash | Alibaba Qwen |
1M | $0.1 | $0.4 | 2026-02-23 | ||
| Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-preview | Google |
1.04858M | $2 | $12 | 2026-02-19 | ||
| Claude Sonnet 4.6anthropic/claude-sonnet-4-6 | Anthropic |
1M | $3 | $15 | 2026-02-17 | ||
| Qwen3.5 Plusalibaba/qwen3.5-plus | Alibaba Qwen |
1M | $0.4 | $2.4 | 2026-02-16 | ||
| GLM-5zhipuai/glm-5 | Zhipu AI |
204.8K | $0.598 | $2.689 | 2026-02-12 | ||
| GPT-5.3 Codexopenai/gpt-5.3-codex | OpenAI |
400K | $1.75 | $14 | 2026-02-05 | ||
| Claude Opus 4.6anthropic/claude-opus-4-6 | Anthropic |
1M | $5 | $25 | 2026-02-05 | ||
| Qwen3 Coder Nextalibaba/qwen3-coder-next | Alibaba Qwen |
262.144K | $0.108 | $0.675 | 2026-02-03 | ||
| 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 | ||
| Seed 1.8bytedance-seed/seed-1-8 | 256K | $0.119 | $1.187 | 2025-12-28 | |||
| MiMo-V2-Flashxiaomi/mimo-v2-flash | Xiaomi |
262.144K | — | — | 2025-12-16 | ||
| Nemotron 3 Nano 30B A3Bnvidia/nemotron-3-nano-30b-a3b | NVIDIA |
262.144K | $0.05 | $0.2 | 2025-12-15 | ||
| GPT-5.2 Codexopenai/gpt-5.2-codex | OpenAI |
400K | $0.14 | $1.14 | 2025-12-11 | ||
| GPT-5.2 Proopenai/gpt-5.2-pro | OpenAI |
400K | $21 | $168 | 2025-12-11 | ||
| GPT-5.2openai/gpt-5.2 | OpenAI |
400K | $1.75 | $14 | 2025-12-11 | ||
| GLM-4.6Vzhipuai/glm-4.6v | Zhipu AI |
128K | $0.149 | $0.448 | 2025-12-08 | ||
| Nova 2 Liteamazon/nova-2-lite | Amazon |
1M | $0.33 | $2.75 | 2025-12-02 | ||
| DeepSeek V3.2deepseek/deepseek-v3.2 | DeepSeek |
128K | $0.209 | $0.31 | 2025-12-01 | ||
| Trinity Miniarcee-ai/trinity-mini | 131.072K | $0.045 | $0.15 | 2025-12-01 | |||
| Claude Opus 4.5anthropic/claude-opus-4-5-20251101 | Anthropic |
200K | $5 | $25 | 2025-11-24 | ||
| Gemini 3 Pro Previewgoogle/gemini-3-pro-preview | Google |
1.04858M | $0.57 | $3.43 | 2025-11-18 | ||
| GPT-5.1 Codex Maxopenai/gpt-5.1-codex-max | OpenAI |
400K | $1.1 | $9 | 2025-11-13 | ||
| GPT-5.1 Codexopenai/gpt-5.1-codex | OpenAI |
400K | $1.07 | $8.5 | 2025-11-13 | ||
| GPT-5.1 Codex miniopenai/gpt-5.1-codex-mini | OpenAI |
400K | $0.22 | $1.8 | 2025-11-13 | ||
| Kimi K2 Thinkingmoonshotai/kimi-k2-thinking | Moonshot AI |
262.144K | $0.4 | $2.5 | 2025-11-06 | ||
| GPT OSS Safeguard 20Bopenai/gpt-oss-safeguard-20b | OpenAI |
131.072K | $0.07 | $0.2 | 2025-10-29 | ||
| GPT OSS Safeguard 120Bopenai/gpt-oss-safeguard-120b | OpenAI |
131.072K | $0.15 | $0.6 | 2025-10-29 | ||
| Nemotron Nano 12B v2 VLnvidia/nemotron-nano-12b-v2-vl | NVIDIA |
128K | $0.2 | $0.6 | 2025-10-28 | ||
| Claude Haiku 4.5anthropic/claude-haiku-4-5-20251001 | Anthropic |
200K | $1 | $5 | 2025-10-15 | ||
| Seed 1.6bytedance-seed/seed-1-6 | 256K | $0.119 | $1.187 | 2025-10-15 | |||
| GPT-5 Proopenai/gpt-5-pro | OpenAI |
400K | $15 | $120 | 2025-10-06 | ||
| Claude Sonnet 4.5anthropic/claude-sonnet-4-5-20250929 | Anthropic |
200K | $3 | $15 | 2025-09-29 | ||
| Qwen3 Maxalibaba/qwen3-max | Alibaba Qwen |
262.144K | $1.2 | $6 | 2025-09-23 | ||
| GPT-5-Codexopenai/gpt-5-codex | OpenAI |
400K | $1.1 | $9 | 2025-09-15 | ||
| Qwen3-Next 80B-A3B (Thinking)alibaba/qwen3-next-80b-a3b-thinking | Alibaba Qwen |
262.144K | $0.5 | $6 | 2025-09 |