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
StepFun flash model for efficient multimodal reasoning, coding, and tool use
6 providers
Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use
5 providers
MiMo omni model for text, image, video, audio, and agents
4 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
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
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
18 providers
Qwen instruction model for multilingual chat, reasoning, and tool use
17 providers
Qwen vision-language model for visual reasoning, documents, and agent tasks
10 providers
Advanced Gemini model for complex reasoning, coding, and multimodal analysis
13 providers
Reasoning-first Gemini preview for agentic coding and complex problem solving
37 providers
Flagship Indian-language reasoning model for enterprise multilingual applications
2 providers
Efficient Indian-language reasoning model for chat, coding, and multilingual work
2 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
Cost-efficient ByteDance Seed 2.0 model for production chat, analysis, and structured generation
9 providers
ByteDance Seed coding model for multimodal software engineering and long-running agents
11 providers
Coding-optimized GPT model for repository edits, reviews, and agentic software work
33 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
Flagship model for demanding analysis, coding, and production agent workflows
4 providers
Reasoning model for deliberate analysis, multi-step problem solving, and tool use
3 providers
New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs
28 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
Multimodal reasoning model for visual analysis, planning, and tool use
6 providers
Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use
28 providers
DeepSeek reasoning model for multi-step analysis, math, coding, and tools
5 providers
Coding-optimized GPT model for repository edits, reviews, and agentic software work
18 providers
Sharper GPT-5 generation for coding, product work, and tool-assisted tasks
30 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
Fast Claude model for responsive assistance, classification, and lightweight agents
23 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
Qwen vision-language thinking model for visual reasoning, documents, and agent tasks
8 providers
Coding-optimized GPT model for repository edits, reviews, and agentic software work
13 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 | ||
| Step 3.5 Flash 2603stepfun/step-3.5-flash-2603 | StepFun |
256K | $0.105 | $0.314 | 2026-04-02 | ||
| Trinity Large Thinkingarcee-ai/trinity-large-thinking | 524.288K | $0.25 | $0.8 | 2026-04-01 | |||
| MiMo-V2-Omnixiaomi/mimo-v2-omni | Xiaomi |
262.144K | — | — | 2026-03-18 | ||
| 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 | ||
| 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 | ||
| Mercury 2inception/mercury-2 | Inception |
128K | $0.25 | $0.75 | 2026-02-24 | ||
| Qwen3.5 27Balibaba/qwen3.5-27b | Alibaba Qwen |
262.144K | $0.3 | $2.4 | 2026-02-23 | ||
| Qwen3.5 9Balibaba/qwen3.5-9b | Alibaba Qwen |
262.144K | $0.05 | $0.15 | 2026-02-23 | ||
| Qwen3.5 Flashalibaba/qwen3.5-flash | Alibaba Qwen |
1M | $0.1 | $0.4 | 2026-02-23 | ||
| Gemini 3.1 Pro Preview Custom Toolsgoogle/gemini-3.1-pro-preview-customtools | Google |
1.04858M | $2 | $12 | 2026-02-19 | ||
| Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-preview | Google |
1.04858M | $2 | $12 | 2026-02-19 | ||
| Sarvam 105Bsarvam/sarvam-105b | Sarvam |
131.072K | $0.04 | $0.16 | 2026-02-18 | ||
| Sarvam 30Bsarvam/sarvam-30b | Sarvam |
128K | — | — | 2026-02-18 | ||
| 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 | ||
| Seed 2.0 Litebytedance-seed/seed-2.0-lite | 256K | $0.089 | $0.534 | 2026-02-14 | |||
| Seed 2.0 Codebytedance-seed/seed-2.0-code | 262.144K | $0.4 | $2.4 | 2026-02-14 | |||
| GPT-5.3 Codexopenai/gpt-5.3-codex | OpenAI |
400K | $1.75 | $14 | 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 | ||
| Solar Pro 3upstage/solar-pro3 | Upstage |
131.072K | $0.15 | $0.6 | 2026-01-26 | ||
| Aion-2.0aion-labs/aion-2.0 | 131.072K | $0.8 | $1.6 | 2025-12-21 | |||
| Gemini 3 Flash Previewgoogle/gemini-3-flash-preview | Google |
1.04858M | $0.5 | $3 | 2025-12-17 | ||
| 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 | ||
| Nova 2 Liteamazon/nova-2-lite-v1 | Amazon |
1M | $0.3 | $2.5 | 2025-12-02 | ||
| DeepSeek V3.2deepseek/deepseek-v3.2 | DeepSeek |
128K | $0.209 | $0.31 | 2025-12-01 | ||
| DeepSeek Reasonerdeepseek/deepseek-reasoner | DeepSeek |
1M | $0.242 | $0.726 | 2025-12-01 | ||
| GPT-5.1 Codex Maxopenai/gpt-5.1-codex-max | OpenAI |
400K | $1.1 | $9 | 2025-11-13 | ||
| GPT-5.1openai/gpt-5.1 | OpenAI |
400K | $1.25 | $10 | 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 | ||
| Claude Haiku 4.5anthropic/claude-haiku-4-5-20251001 | Anthropic |
200K | $1 | $5 | 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 | ||
| Qwen3 VL 235B A22B Thinkingalibaba/qwen3-vl-235b-a22b-thinking | Alibaba Qwen |
131.072K | $0.4 | $4 | 2025-09-23 | ||
| GPT-5-Codexopenai/gpt-5-codex | OpenAI |
400K | $1.1 | $9 | 2025-09-15 |