LLMAtlas

Workspace

  • Overview

Develop

  • Playground
  • Code
    Soon
  • Projects
    Soon
  • Compare
  • Prompts

Research

  • Models
  • Cost Calculator
  • Leaderboard
  • API Status

Learn

  • Learn
    New

Account

  • Settings
Sign in free

Save prompts, track progress, and sync your workspace across devices.

Sign in· Register
LLMAtlas

Workspace

  • Overview

Develop

  • Playground
  • Code
    Soon
  • Projects
    Soon
  • Compare
  • Prompts

Research

  • Models
  • Cost Calculator
  • Leaderboard
  • API Status

Learn

  • Learn
    New

Account

  • Settings
Sign in free

Save prompts, track progress, and sync your workspace across devices.

Sign in· Register
⌘K
Model Tracker

Every LLM in one catalogue

201 models across 13 providers. 153 free · 47 vision-capable · all accessible today.

Showing 201 of 201 models

PO

Claude Opus 4.8 (keyless)

Anthropic

FRONTIER

Claude Opus 4.8 — Anthropic's flagship, served keyless via Pollinations. No user API key needed.

96
Quality
62
Speed
200K
Context
vision
frontier-free
keyless
TryKey
PO

GPT-5.5 (keyless)

OpenAI

FRONTIER

GPT-5.5 — OpenAI's frontier reasoning model with 1M context, keyless via Pollinations.

95
Quality
70
Speed
1.0M
Context
vision
frontier-free
keyless
TryKey
GI

Claude Opus 4 (free via GitHub)

Anthropic

FRONTIER

Claude Opus 4 — Anthropic's most capable model, frontier on all benchmarks, free via GitHub PAT.

95
Quality
60
Speed
200K
Context
vision
frontier-free
frontier
API key
TryKey
DE

DeepSeek V4 Pro

DeepSeek

PAID

DeepSeek's flagship V4 Pro — frontier reasoning, 256K context, top benchmark scores.

94
Quality
72
Speed
262K
Context
open-source
frontier
reasoning
API key
TryKey
OP

DeepSeek V4 Pro

DeepSeek

PAID

DeepSeek V4 Pro — flagship model, 1M context, top benchmarks.

94
Quality
60
Speed
1.0M
Context
open-source
frontier
reasoning
API key
TryKey
GI

Claude Sonnet 4.5 (free via GitHub)

Anthropic

FRONTIER

Claude Sonnet 4.5 — latest hybrid reasoning Sonnet, fast and frontier, free via GitHub PAT.

94
Quality
82
Speed
200K
Context
vision
frontier-free
frontier
API key
TryKey
GI

o3 (free via GitHub)

OpenAI

FRONTIER

o3 — OpenAI's most powerful reasoning model, extended chain-of-thought, free via GitHub PAT.

94
Quality
42
Speed
200K
Context
frontier-free
frontier
API key
TryKey
GI

DeepSeek V4 Pro (free via GitHub)

DeepSeek

FRONTIER

DeepSeek V4 Pro — flagship model, free via GitHub PAT.

94
Quality
60
Speed
262K
Context
open-source
frontier-free
frontier
API key
TryKey
NV

DeepSeek V4 Pro (NVIDIA)

DeepSeek

FREE

DeepSeek V4 Pro on NVIDIA NIM — flagship model, free tier.

94
Quality
65
Speed
262K
Context
open-source
frontier
reasoning
API key
TryKey
TO

DeepSeek V4 Pro (Together)

DeepSeek

PAID

DeepSeek V4 Pro on Together AI — flagship reasoning at scale.

94
Quality
62
Speed
262K
Context
open-source
frontier
reasoning
API key
TryKey
OP

Nemotron 3 Ultra (free)

Nvidia

FRONTIER

NVIDIA Nemotron 3 Ultra — 253B flagship, top-tier reasoning & code, free on OpenRouter.

93
Quality
55
Speed
131K
Context
open-source
frontier
frontier-free
API key
TryKey
GO

Gemini 2.5 Pro

Google

FREE

Google's most capable Gemini yet — frontier reasoning, 1M context, free via AI Studio.

93
Quality
65
Speed
1.0M
Context
vision
frontier
reasoning
TryKey
GI

Claude 4 Sonnet (free via GitHub)

Anthropic

FRONTIER

Claude 4 Sonnet — Anthropic's flagship coding & reasoning model, free via GitHub PAT.

93
Quality
78
Speed
200K
Context
vision
frontier-free
frontier
API key
TryKey
GI

Nemotron 3 Ultra (free via GitHub)

Nvidia

FRONTIER

NVIDIA Nemotron 3 Ultra — 253B flagship with elite reasoning & code, free via GitHub PAT.

93
Quality
55
Speed
131K
Context
open-source
frontier-free
frontier
API key
TryKey
PO

Claude (keyless)

Anthropic

FRONTIER

Claude (large tier) — balanced Anthropic model, keyless via Pollinations.

93
Quality
78
Speed
200K
Context
vision
frontier-free
keyless
TryKey
PO

Nemotron 3 Ultra (keyless)

Nvidia

FRONTIER

NVIDIA Nemotron 3 Ultra — 253B flagship reasoning & code, keyless via Pollinations.

93
Quality
55
Speed
131K
Context
open-source
frontier-free
keyless
TryKey
PO

DeepSeek Pro (keyless)

DeepSeek

FRONTIER

DeepSeek Pro — frontier reasoning & coding, keyless via Pollinations.

93
Quality
70
Speed
164K
Context
open-source
frontier-free
keyless
TryKey
PO

Grok 4.3 (keyless)

xAI

FRONTIER

Grok 4.3 — xAI's frontier model, keyless via Pollinations.

93
Quality
72
Speed
256K
Context
vision
frontier-free
keyless
TryKey
DE

DeepSeek R1-0528

DeepSeek

PAID

DeepSeek R1-0528 — updated R1 with improved reasoning and fewer hallucinations.

93
Quality
58
Speed
131K
Context
open-source
frontier
reasoning
API key
TryKey
OP

DeepSeek R1-0528

DeepSeek

PAID

Updated DeepSeek R1 — improved reasoning, fewer hallucinations.

93
Quality
48
Speed
164K
Context
open-source
frontier
reasoning
API key
TryKey
NV

DeepSeek R1-0528 (NVIDIA)

DeepSeek

FREE

Updated DeepSeek R1 on NVIDIA NIM — improved reasoning, free tier.

93
Quality
52
Speed
131K
Context
open-source
frontier
reasoning
API key
TryKey
NV

Nemotron 3 Ultra (NVIDIA)

Nvidia

FREE

NVIDIA Nemotron 3 Ultra — 253B parameter flagship, best-in-class reasoning & code generation, free on NIM.

93
Quality
55
Speed
131K
Context
open-source
frontier
reasoning
API key
TryKey
GI

GPT-4.1 (free via GitHub)

OpenAI

FRONTIER

GPT-4.1 — OpenAI's flagship 2025 model, free via GitHub Models PAT (rate-limited).

92
Quality
78
Speed
1.0M
Context
vision
frontier
frontier-free
API key
TryKey
GI

o1 (free via GitHub)

OpenAI

FRONTIER

o1 — frontier reasoning model with extended chain-of-thought, free via GitHub PAT.

92
Quality
45
Speed
200K
Context
frontier-free
reasoning
API key
TryKey
XA

Grok 4 (free credits via xAI)

xAI

FRONTIER

Grok 4 — xAI's frontier model. Free monthly credits for new accounts.

92
Quality
75
Speed
256K
Context
vision
frontier-free
chat
API key
TryKey
DE

DeepSeek R1

DeepSeek

PAID

DeepSeek R1 full — frontier reasoning with chain-of-thought, 671B MoE.

92
Quality
55
Speed
131K
Context
open-source
frontier
reasoning
API key
TryKey
OP

DeepSeek R1

DeepSeek

PAID

Full DeepSeek R1 671B MoE — frontier reasoning with chain-of-thought.

92
Quality
45
Speed
164K
Context
open-source
frontier
reasoning
API key
TryKey
GI

DeepSeek R1 (free via GitHub)

DeepSeek

FRONTIER

DeepSeek R1 — full 671B reasoning model, free via GitHub PAT.

92
Quality
50
Speed
131K
Context
open-source
frontier-free
reasoning
API key
TryKey
NV

Qwen 3.6 (NVIDIA)

Alibaba

FREE

Qwen 3.6 on NVIDIA NIM — latest Alibaba flagship, free tier.

92
Quality
68
Speed
262K
Context
open-source
frontier
reasoning
API key
TryKey
TO

Qwen 3.6 (Together)

Alibaba

PAID

Qwen 3.6 on Together AI — Alibaba's latest frontier model.

92
Quality
68
Speed
262K
Context
open-source
frontier
reasoning
API key
TryKey
TO

DeepSeek R1 (Together)

DeepSeek

PAID

Full DeepSeek R1 on Together AI — 671B MoE reasoning model.

92
Quality
50
Speed
131K
Context
open-source
frontier
reasoning
API key
TryKey
TO

Qwen3 235B A22B

Alibaba

PAID

Qwen3 235B MoE — best open reasoning model at scale via Together AI.

91
Quality
70
Speed
131K
Context
open-source
frontier
moe
API key
TryKey
GI

o3-mini (free via GitHub)

OpenAI

FRONTIER

o3-mini — OpenAI's reasoning model with visible chain-of-thought, free via GitHub.

91
Quality
55
Speed
200K
Context
frontier-free
reasoning
API key
TryKey
GI

Claude 3.5 Sonnet (free via GitHub)

Anthropic

FRONTIER

Claude 3.5 Sonnet — proven flagship, strong on code, free via GitHub PAT.

91
Quality
80
Speed
200K
Context
vision
frontier-free
chat
API key
TryKey
OP

Qwen 3.6 Plus

Alibaba

PAID

Qwen 3.6 Plus — premium Alibaba model, 1M context, top reasoning.

91
Quality
72
Speed
1.0M
Context
open-source
frontier
reasoning
API key
TryKey
OP

Qwen3 235B A22B

Alibaba

PAID

Qwen3 235B MoE — largest open Qwen, frontier quality.

91
Quality
62
Speed
131K
Context
open-source
frontier
moe
API key
TryKey
GR

Llama 4 Maverick (Groq)

Meta

FREE

Llama 4 Maverick 128E MoE on Groq — 1M context, vision, frontier quality.

90
Quality
88
Speed
1.0M
Context
vision
open-source
frontier
moe
TryKey
TO

Llama 4 Maverick

Meta

PAID

Llama 4 Maverick on Together AI — 128E MoE with 512K context.

90
Quality
82
Speed
524K
Context
vision
open-source
frontier
moe
API key
TryKey
NV

Llama 4 Maverick 17B (128E)

Meta

FREE

Llama 4 Maverick 128E MoE — frontier capability, 1M context, free on NVIDIA NIM.

90
Quality
84
Speed
1.0M
Context
vision
open-source
frontier
moe
API key
TryKey
NV

Mistral Large 3 675B

Mistral

FREE

Mistral's largest model on NVIDIA NIM — 675B parameter frontier reasoning.

90
Quality
50
Speed
131K
Context
frontier
reasoning
API key
TryKey
GI

Llama 4 Maverick (free via GitHub)

Meta

FRONTIER

Llama 4 Maverick — 1M context MoE, free via GitHub PAT.

90
Quality
80
Speed
1.0M
Context
vision
open-source
frontier-free
moe
API key
TryKey
PO

GPT (large, keyless)

OpenAI

FRONTIER

OpenAI large tier with reasoning — keyless via Pollinations.

90
Quality
74
Speed
400K
Context
vision
frontier-free
keyless
TryKey
PO

MiniMax M3 (keyless)

MiniMax

FRONTIER

MiniMax M3 — 1M context, vision + reasoning, keyless via Pollinations.

90
Quality
68
Speed
1.0M
Context
vision
frontier-free
keyless
TryKey
PO

Qwen Large (keyless)

Alibaba

FRONTIER

Qwen large tier — frontier Alibaba reasoning, keyless via Pollinations.

90
Quality
72
Speed
262K
Context
open-source
frontier-free
keyless
TryKey
PO

Llama 4 Maverick (keyless)

Meta

FRONTIER

Llama 4 Maverick 128E MoE — 1M context, keyless via Pollinations.

90
Quality
74
Speed
1.0M
Context
vision
open-source
frontier-free
keyless
TryKey
DE

DeepSeek V4

DeepSeek

PAID

DeepSeek V4 — strong general reasoning and coding, 128K context.

90
Quality
80
Speed
131K
Context
open-source
frontier
reasoning
API key
TryKey
OP

MiniMax M3

MiniMax

PAID

MiniMax M3 — latest flagship, 1M context, frontier reasoning.

90
Quality
68
Speed
1.0M
Context
frontier
long-context
API key
TryKey
OP

Llama 4 Maverick

Meta

PAID

Llama 4 Maverick 128E MoE — 1M context, frontier quality.

90
Quality
74
Speed
1.0M
Context
vision
open-source
frontier
moe
API key
TryKey
GI

o4-mini (free via GitHub)

OpenAI

FRONTIER

o4-mini — fast reasoning model with vision, free via GitHub PAT.

90
Quality
78
Speed
200K
Context
vision
frontier-free
reasoning
API key
TryKey
GI

GPT-4.5 Preview (free via GitHub)

OpenAI

FRONTIER

GPT-4.5 Preview — creative and nuanced responses, free via GitHub PAT.

90
Quality
70
Speed
128K
Context
vision
frontier-free
chat
API key
TryKey
OP

Nemotron 3 Super 120B (free)

Nvidia

FREE

NVIDIA's largest Nemotron 3 MoE — 120B total, frontier OSS performance.

89
Quality
65
Speed
131K
Context
open-source
frontier
moe
API key
TryKey
GI

GPT-4o (free via GitHub)

OpenAI

FRONTIER

GPT-4o — proven multimodal flagship, free via GitHub PAT.

89
Quality
85
Speed
128K
Context
vision
frontier-free
chat
API key
TryKey
PO

Gemini 3.5 Flash (keyless)

Google

FRONTIER

Gemini 3.5 Flash — fast multimodal Google model, 1M context, keyless via Pollinations.

89
Quality
88
Speed
1.0M
Context
vision
frontier-free
keyless
TryKey
OP

GPT-OSS 120B (free)

OpenAI

FREE

OpenAI's open-source GPT 120B — frontier quality released as OSS.

88
Quality
60
Speed
131K
Context
open-source
frontier
reasoning
API key
TryKey
OP

Kimi K2.6 (free)

Moonshot AI

FREE

Moonshot AI's Kimi K2.6 — 1T+ MoE, frontier coding & agentic tasks, free on OpenRouter.

88
Quality
68
Speed
262K
Context
frontier
reasoning
API key
TryKey
TO

Llama 3.1 405B Turbo

Meta

PAID

Meta's massive 405B — frontier open model via Together AI.

88
Quality
62
Speed
131K
Context
open-source
frontier
chat
API key
TryKey
NV

GPT-OSS 120B (NVIDIA)

OpenAI

FREE

OpenAI's open-source GPT 120B on NVIDIA NIM — frontier OSS quality.

88
Quality
60
Speed
131K
Context
open-source
frontier
reasoning
API key
TryKey
PO

GPT-5.4 Mini (keyless)

OpenAI

FRONTIER

GPT-5.4 Mini — fast multimodal OpenAI model, keyless via Pollinations.

88
Quality
88
Speed
400K
Context
vision
frontier-free
keyless
TryKey
PO

DeepSeek (keyless)

DeepSeek

FRONTIER

DeepSeek V3-class chat & code model, keyless via Pollinations.

88
Quality
80
Speed
131K
Context
open-source
frontier-free
keyless
TryKey
PO

Kimi K2.6 (keyless)

Moonshot AI

FRONTIER

Kimi K2.6 — Moonshot's frontier MoE for coding & agentic tasks, keyless via Pollinations.

88
Quality
68
Speed
262K
Context
frontier-free
keyless
TryKey
XA

Grok 3 (free credits via xAI)

xAI

FRONTIER

Grok 3 — strong general capability, real-time X data, free monthly credits.

88
Quality
78
Speed
131K
Context
frontier-free
chat
API key
TryKey
DE

DeepSeek Prover V2

DeepSeek

PAID

DeepSeek Prover V2 — formal mathematics and theorem proving specialist.

88
Quality
50
Speed
66K
Context
open-source
math
reasoning
API key
TryKey
DE

DeepSeek V3.1

DeepSeek

PAID

DeepSeek V3.1 — refined V3 with better instruction following and coding.

88
Quality
80
Speed
131K
Context
open-source
chat
reasoning
API key
TryKey
OP

DeepSeek V3.2

DeepSeek

PAID

DeepSeek V3.2 — fast, capable chat model at very low cost.

88
Quality
80
Speed
131K
Context
open-source
chat
reasoning
API key
TryKey
OP

MiniMax M2.7

MiniMax

PAID

MiniMax M2.7 — 200K context, strong reasoning at low cost.

88
Quality
70
Speed
205K
Context
frontier
long-context
API key
TryKey
OP

Qwen 3.6 Flash

Alibaba

PAID

Qwen 3.6 Flash — 1M context, fast and cheap Alibaba flagship.

88
Quality
82
Speed
1.0M
Context
open-source
frontier
reasoning
API key
TryKey
GR

Llama 4 Scout (Groq)

Meta

FREE

Llama 4 Scout 16E MoE on Groq LPU — 512K context, vision-capable, blazing fast.

87
Quality
95
Speed
524K
Context
vision
open-source
frontier
moe
TryKey
CE

GPT-OSS 120B (Cerebras)

OpenAI

FREE

OpenAI's open-source GPT 120B on Cerebras CS-3 — frontier quality at record speed.

87
Quality
100
Speed
33K
Context
open-source
frontier
chat
TryKey
NV

Llama 3.3 Nemotron Super 49B

Nvidia

FREE

NVIDIA's flagship Nemotron Super — Llama-base with elite RLHF.

87
Quality
85
Speed
131K
Context
open-source
chat
rlhf
API key
TryKey
GI

Llama 4 Scout (free via GitHub)

Meta

FRONTIER

Llama 4 Scout 17B-16E — 512K context MoE, free via GitHub PAT.

87
Quality
84
Speed
524K
Context
vision
open-source
frontier-free
moe
API key
TryKey
PO

Llama 4 Scout (keyless)

Meta

FRONTIER

Llama 4 Scout 16E MoE — long-context, vision, keyless via Pollinations.

87
Quality
82
Speed
524K
Context
vision
open-source
frontier-free
keyless
TryKey
OP

Qwen3 Coder Flash

Alibaba

PAID

Qwen3 Coder Flash — fast code-specialised model with 1M context.

87
Quality
78
Speed
1.0M
Context
open-source
code
developer
API key
TryKey
OP

Llama 4 Scout

Meta

PAID

Llama 4 Scout MoE — massive 10M context, vision-capable, very affordable.

87
Quality
82
Speed
10.0M
Context
vision
open-source
frontier
moe
API key
TryKey
GR

Llama 3.3 70B (Versatile)

Meta

FREE

Meta's flagship 70B served via Groq — best free balance of quality and speed.

86
Quality
97
Speed
128K
Context
open-source
chat
reasoning
TryKey
OP

DeepSeek V4 Flash

DeepSeek

PAID

DeepSeek V4 Flash — 1M context, extremely cheap on OpenRouter.

86
Quality
82
Speed
1.0M
Context
open-source
frontier
reasoning
API key
TryKey
TO

Llama 3.3 70B Turbo (free)

Meta

FREE

Llama 3.3 70B Turbo on Together AI — genuinely free (no token cost).

86
Quality
90
Speed
131K
Context
open-source
chat
reasoning
API key
TryKey
CL

Llama 3.3 70B FP8 (Cloudflare)

Meta

FREE

Llama 3.3 70B FP8 quantized on Cloudflare edge — quality at edge speed.

86
Quality
80
Speed
8K
Context
open-source
chat
reasoning
API key
TryKey
NV

Llama 3.3 70B (NVIDIA)

Meta

FREE

Meta's latest 70B on NVIDIA's GPU cloud — 128K context.

86
Quality
86
Speed
131K
Context
open-source
chat
reasoning
API key
TryKey
NV

DeepSeek V4 Flash (NVIDIA)

DeepSeek

FREE

DeepSeek V4 Flash on NVIDIA NIM — fast frontier reasoning, free tier.

86
Quality
82
Speed
131K
Context
open-source
frontier
reasoning
API key
TryKey
GI

o1-mini (free via GitHub)

OpenAI

FRONTIER

o1-mini — faster reasoning variant, free via GitHub PAT.

86
Quality
65
Speed
128K
Context
frontier-free
reasoning
API key
TryKey
GI

Llama 3.3 70B (free via GitHub)

Meta

FRONTIER

Llama 3.3 70B on GitHub Models — Meta's flagship 70B, free via GitHub PAT.

86
Quality
80
Speed
131K
Context
open-source
frontier-free
chat
API key
TryKey
GI

Mistral Large 2411 (free via GitHub)

Mistral

FRONTIER

Mistral Large 2 — top multilingual reasoning, free via GitHub PAT.

86
Quality
75
Speed
131K
Context
frontier-free
chat
API key
TryKey
PO

Qwen Coder (keyless)

Alibaba

FREE

Qwen Coder — code-specialised Qwen, keyless via Pollinations.

86
Quality
80
Speed
262K
Context
open-source
keyless
code
TryKey
PO

Mistral Large (keyless)

Mistral

FREE

Mistral Large — top multilingual reasoning, keyless via Pollinations.

86
Quality
74
Speed
131K
Context
keyless
chat
TryKey
DE

DeepSeek V4 Flash

DeepSeek

FREE

DeepSeek V4 Flash — fast and free via DeepSeek's direct API.

86
Quality
88
Speed
131K
Context
open-source
frontier
reasoning
API key
TryKey
DE

DeepSeek V3

DeepSeek

PAID

DeepSeek V3 via direct API — proven MoE backbone for chat and code.

86
Quality
78
Speed
131K
Context
open-source
chat
reasoning
API key
TryKey
OP

Kimi K2 Thinking

Moonshot AI

PAID

Kimi K2 Thinking — extended chain-of-thought reasoning variant.

86
Quality
60
Speed
262K
Context
reasoning
thinking
API key
TryKey
OP

Hermes 3 405B (free)

NousResearch

FREE

Meta's Llama 3.1 405B fine-tuned by NousResearch — massive but free.

85
Quality
55
Speed
131K
Context
open-source
frontier
chat
API key
TryKey
DE

DeepSeek Coder V3

DeepSeek

PAID

DeepSeek Coder V3 — code-specialised model, strong on HumanEval and SWE-bench.

85
Quality
82
Speed
131K
Context
open-source
code
developer
API key
TryKey
OP

MiMo V2.5 Pro

Xiaomi

PAID

MiMo V2.5 Pro — Xiaomi's pro-tier, 1M context, enhanced agentic coding.

85
Quality
75
Speed
1.0M
Context
open-source
frontier
reasoning
API key
TryKey
NV

Kimi K2 (NVIDIA)

Moonshot AI

FREE

Moonshot AI's Kimi K2 on NVIDIA NIM — strong coding MoE, free tier.

85
Quality
68
Speed
131K
Context
frontier
reasoning
API key
TryKey
GR

DeepSeek R1 Distill Llama 70B

DeepSeek

FREE

Llama 70B distilled from DeepSeek R1 — fast reasoning on Groq's LPU (Qwen 32B variant was retired by Groq).

84
Quality
95
Speed
128K
Context
open-source
reasoning
math
TryKey
OP

Qwen3 Next 80B A3B (free)

Alibaba

FREE

Qwen3 Next 80B MoE with 3B active — strong reasoning, free on OpenRouter.

84
Quality
80
Speed
131K
Context
open-source
frontier
moe
API key
TryKey
GO

Gemini 2.5 Flash

Google

FREE

Fast Gemini 2.5 Flash with thinking mode — best speed/quality for free.

84
Quality
88
Speed
1.0M
Context
vision
frontier
fast
TryKey
MI

Mistral Large 2

Mistral

PAID

Flagship Mistral Large 2 — top-tier multilingual reasoning.

84
Quality
72
Speed
131K
Context
chat
frontier
API key
TryKey
NV

Qwen3 Next 80B A3B (NVIDIA)

Alibaba

FREE

Qwen3 Next 80B MoE on NVIDIA — 3B active, strong reasoning.

84
Quality
80
Speed
131K
Context
open-source
frontier
moe
API key
TryKey
NV

Mistral Large 2

Mistral

FREE

Mistral Large 2 hosted free on NVIDIA NIM — top multilingual reasoning.

84
Quality
72
Speed
131K
Context
chat
frontier
API key
TryKey
GI

GPT-4.1 mini (free via GitHub)

OpenAI

FRONTIER

GPT-4.1 mini — fast multimodal model, free via GitHub PAT.

84
Quality
90
Speed
1.0M
Context
vision
frontier-free
chat
API key
TryKey
GI

Claude 4.5 Haiku (free via GitHub)

Anthropic

FRONTIER

Claude 4.5 Haiku — fast & cheap Claude tier, free via GitHub PAT.

84
Quality
92
Speed
200K
Context
vision
frontier-free
chat
API key
TryKey
PO

GLM (keyless)

ZAI

FREE

ZAI GLM — bilingual Chinese/English model, keyless via Pollinations.

84
Quality
80
Speed
131K
Context
open-source
keyless
chat
TryKey
OP

Qwen3 Coder (free)

Alibaba

FREE

Qwen3's code-specialized model — top OSS coding performance.

83
Quality
78
Speed
131K
Context
open-source
code
developer
API key
TryKey
HU

Llama 3.1 70B Instruct

Meta

FREE

Meta's flagship Llama 3.1 70B hosted on HuggingFace Inference API.

83
Quality
63
Speed
131K
Context
open-source
chat
reasoning
API key
TryKey
TO

Llama 3.1 70B Turbo

Meta

PAID

Llama 3.1 70B with optimized Turbo serving on Together AI.

83
Quality
87
Speed
131K
Context
open-source
chat
reasoning
API key
TryKey
TO

DeepSeek V3

DeepSeek

PAID

DeepSeek V3 on Together AI — frontier open reasoning model.

83
Quality
75
Speed
66K
Context
open-source
chat
reasoning
API key
TryKey
NV

Llama 3.1 70B (NVIDIA)

Meta

FREE

Battle-tested Llama 3.1 70B — proven workhorse with 128K context.

83
Quality
86
Speed
131K
Context
open-source
chat
reasoning
API key
TryKey
OP

Kimi K2.5

Moonshot AI

PAID

Kimi K2.5 — Moonshot AI's refined model with strong coding and reasoning.

83
Quality
72
Speed
262K
Context
frontier
reasoning
API key
TryKey
GR

Llama 3.2 90B Vision

Meta

FREE

Large multimodal Llama 90B on Groq — powerful vision + reasoning.

82
Quality
85
Speed
128K
Context
vision
open-source
vision
multimodal
TryKey
GR

Llama 3 70B (Groq)

Meta

FREE

Meta's classic Llama 3 70B on Groq's LPU — reliable 8K context, proven quality.

82
Quality
93
Speed
8K
Context
open-source
chat
reasoning
TryKey
OP

Llama 3.3 70B Instruct (free)

Meta

FREE

Meta's Llama 3.3 70B — top OSS quality with 128K context, free on OpenRouter.

82
Quality
78
Speed
131K
Context
open-source
frontier
chat
API key
TryKey
OP

MiniMax M2.5

MiniMax

PAID

MiniMax M2.5 — 200K context, very affordable on OpenRouter.

82
Quality
72
Speed
205K
Context
frontier
long-context
API key
TryKey
CL

DeepSeek R1 Distill 32B (Cloudflare)

DeepSeek

FREE

DeepSeek R1 Qwen 32B distill on Cloudflare — edge reasoning model.

82
Quality
80
Speed
8K
Context
open-source
reasoning
math
API key
TryKey
NV

Llama 3.2 90B Vision

Meta

FREE

Multimodal Llama 3.2 — sees images in 128K context on NVIDIA GPUs.

82
Quality
78
Speed
131K
Context
vision
open-source
vision
multimodal
API key
TryKey
GI

Codestral 2501 (free via GitHub)

Mistral

FRONTIER

Codestral — Mistral's code-specialised model, free via GitHub PAT.

82
Quality
85
Speed
262K
Context
frontier-free
code
API key
TryKey
GI

Command R+ 08-2024 (free via GitHub)

Cohere

FRONTIER

Cohere Command R+ — RAG-optimised flagship, free via GitHub PAT.

82
Quality
75
Speed
131K
Context
frontier-free
chat
API key
TryKey
PO

Qwen Vision (keyless)

Alibaba

FREE

Qwen Vision — multimodal Qwen, keyless via Pollinations.

82
Quality
78
Speed
131K
Context
vision
open-source
keyless
vision
TryKey
XA

Grok 2 Vision (free credits via xAI)

xAI

FRONTIER

Grok 2 with vision — multimodal Grok, free monthly credits.

82
Quality
78
Speed
33K
Context
vision
frontier-free
chat
API key
TryKey
OP

Qwen3 32B

Alibaba

PAID

Qwen3 32B dense — strong reasoning at very low cost.

82
Quality
80
Speed
131K
Context
open-source
chat
reasoning
API key
TryKey
OP

Hy3 Preview

Tencent

PAID

Tencent Hy3 — 256K context reasoning model, very affordable.

82
Quality
78
Speed
262K
Context
reasoning
long-context
API key
TryKey
GR

Qwen3 32B (Groq)

Alibaba

FREE

Qwen3 32B on Groq LPU — blazing fast thinking model.

82
Quality
96
Speed
128K
Context
open-source
chat
reasoning
TryKey
CE

Qwen3 32B (Cerebras)

Alibaba

FREE

Qwen3 32B on Cerebras CS-3 — record inference speed for thinking models.

82
Quality
100
Speed
33K
Context
open-source
chat
reasoning
TryKey
GR

QwQ 32B

Alibaba

FREE

Alibaba's thinking model — surprisingly strong at reasoning for 32B.

81
Quality
94
Speed
128K
Context
open-source
reasoning
math
TryKey
MI

Mixtral 8x22B

Mistral

PAID

Larger MoE with 8x22B experts — strong coding, math, and reasoning.

81
Quality
70
Speed
66K
Context
open-source
chat
moe
API key
TryKey
TO

Mixtral 8x22B Instruct

Mistral

PAID

Mixtral 8x22B on Together AI — highest quality MoE open model.

81
Quality
72
Speed
66K
Context
open-source
chat
reasoning
API key
TryKey
OP

Gemma 4 31B (free)

Google

FREE

Google's Gemma 4 31B — latest open Gemma with vision and strong reasoning.

80
Quality
77
Speed
131K
Context
vision
open-source
chat
vision
API key
TryKey
GO

Gemini 2.0 Flash

Google

FREE

Gemini 2.0 Flash stable release — multimodal, great free tier.

80
Quality
92
Speed
1.0M
Context
vision
chat
multimodal
TryKey
CE

GLM-4.7 (Cerebras)

ZAI

FREE

ZAI GLM-4.7 on Cerebras wafer-scale silicon — fast bilingual model.

80
Quality
99
Speed
33K
Context
open-source
chat
fastest
TryKey
HU

Qwen 2.5 72B Instruct

Alibaba

FREE

Large Qwen 2.5 72B via HuggingFace inference API — free tier.

80
Quality
65
Speed
33K
Context
open-source
chat
reasoning
API key
TryKey
TO

Qwen 2.5 72B Turbo

Alibaba

PAID

Qwen 2.5 72B Turbo optimized serving on Together AI.

80
Quality
82
Speed
33K
Context
open-source
chat
reasoning
API key
TryKey
GI

AI21 Jamba 1.5 Large (free via GitHub)

AI21

FRONTIER

AI21 Jamba 1.5 Large — SSM-transformer hybrid, 256K context, free via GitHub.

80
Quality
78
Speed
262K
Context
frontier-free
chat
API key
TryKey
XA

Grok 3 mini (free credits via xAI)

xAI

FRONTIER

Grok 3 mini — efficient Grok tier, free monthly credits.

80
Quality
88
Speed
131K
Context
frontier-free
chat
API key
TryKey
OP

MiMo V2.5

Xiaomi

PAID

Xiaomi MiMo V2.5 — 1M context reasoning MoE, very cheap on OpenRouter.

80
Quality
82
Speed
1.0M
Context
open-source
reasoning
math
API key
TryKey
NV

MiMo 2.5 (NVIDIA)

Xiaomi

FREE

Xiaomi MiMo 2.5 on NVIDIA NIM — reasoning MoE, free tier.

80
Quality
84
Speed
131K
Context
open-source
reasoning
math
API key
TryKey
GR

DeepSeek R1 Distill Qwen 32B (Groq)

DeepSeek

FREE

DeepSeek R1 distilled into Qwen 32B — fast reasoning on Groq LPU.

80
Quality
97
Speed
128K
Context
open-source
reasoning
math
TryKey
CE

DeepSeek R1 Distill Qwen 32B (Cerebras)

DeepSeek

FREE

DeepSeek R1 distilled Qwen 32B on Cerebras wafer-scale — fastest reasoning.

80
Quality
100
Speed
33K
Context
open-source
reasoning
math
TryKey
OP

GPT-OSS 20B (free)

OpenAI

FREE

OpenAI's open-source GPT 20B — efficient frontier quality for free.

79
Quality
83
Speed
131K
Context
open-source
frontier
reasoning
API key
TryKey
TO

Qwen 2.5 Coder 32B

Alibaba

PAID

Best coding model via Together AI — 32B Qwen Coder for serious dev work.

79
Quality
83
Speed
33K
Context
open-source
code
developer
API key
TryKey
NV

GPT-OSS 20B (NVIDIA)

OpenAI

FREE

OpenAI's open-source GPT 20B on NVIDIA NIM — efficient frontier quality.

79
Quality
83
Speed
131K
Context
open-source
frontier
reasoning
API key
TryKey
PO

GPT-OSS 20B Reasoning (Pollinations, keyless)

OpenAI

FRONTIER

GPT-OSS 20B Reasoning via Pollinations — completely keyless, no signup needed.

79
Quality
84
Speed
128K
Context
open-source
frontier-free
keyless
TryKey
PO

GPT-OSS 20B Fast (Pollinations, keyless)

OpenAI

FRONTIER

GPT-OSS 20B via Pollinations fast lane — minimum latency, completely keyless.

79
Quality
96
Speed
128K
Context
open-source
frontier-free
keyless
TryKey
OP

Qwen3 30B A3B

Alibaba

PAID

Qwen3 30B MoE with 3B active — efficient reasoning, very cheap.

79
Quality
86
Speed
131K
Context
open-source
chat
moe
API key
TryKey
OP

Nemotron 3 Nano Omni 30B (free)

Nvidia

FREE

NVIDIA Nemotron 3 Nano Omni — reasoning-specialized MoE variant.

78
Quality
82
Speed
131K
Context
open-source
reasoning
moe
API key
TryKey
OP

GLM-4.5 Air (free)

ZAI

FREE

ZAI's GLM-4.5 Air — bilingual Chinese/English model, fast and free.

78
Quality
84
Speed
131K
Context
open-source
chat
multilingual
API key
TryKey
MI

Codestral (latest)

Mistral

PAID

Mistral's code-first model — 80+ languages, fill-in-middle support.

78
Quality
87
Speed
33K
Context
code
developer
API key
TryKey
HU

Zephyr ORPO 141B (free)

HuggingFace H4

FREE

Massive 141B MoE Zephyr trained with ORPO — excellent instruction following.

78
Quality
55
Speed
66K
Context
open-source
chat
large
API key
TryKey
GI

GPT-4o mini (free via GitHub)

OpenAI

FRONTIER

GPT-4o mini — fast, capable, free via GitHub PAT.

78
Quality
92
Speed
128K
Context
vision
frontier-free
chat
API key
TryKey
OP

Gemma 4 26B A4B MoE (free)

Google

FREE

Gemma 4 MoE variant — 26B total with only 4B active, efficient and fast.

77
Quality
82
Speed
131K
Context
vision
open-source
chat
vision
API key
TryKey
OP

Nemotron 3 Nano 30B (free)

Nvidia

FREE

NVIDIA Nemotron 3 Nano 30B MoE — efficient inference with 3B active parameters.

76
Quality
84
Speed
131K
Context
open-source
chat
moe
API key
TryKey
MI

Mixtral 8x7B (Mistral)

Mistral

FREE

Direct from Mistral API — sparse MoE with 8 experts, 32K context.

76
Quality
82
Speed
33K
Context
open-source
chat
moe
API key
TryKey
GI

GPT-4.1 nano (free via GitHub)

OpenAI

FRONTIER

Smallest GPT-4.1 — ultra-fast, free via GitHub PAT.

76
Quality
95
Speed
1.0M
Context
vision
frontier-free
chat
API key
TryKey
GI

Claude 3 Haiku (free via GitHub)

Anthropic

FRONTIER

Claude 3 Haiku — fastest classic Claude, free via GitHub PAT.

76
Quality
95
Speed
200K
Context
vision
frontier-free
chat
API key
TryKey
GI

Mistral Small (free via GitHub)

Mistral

FRONTIER

Mistral Small 3 — efficient and capable, free via GitHub PAT.

76
Quality
88
Speed
131K
Context
open-source
frontier-free
chat
API key
TryKey
GI

Command R 08-2024 (free via GitHub)

Cohere

FRONTIER

Cohere Command R — efficient RAG and tools, free via GitHub PAT.

76
Quality
84
Speed
131K
Context
frontier-free
chat
API key
TryKey
OP

Qwen3 14B

Alibaba

PAID

Qwen3 14B — mid-size thinking model, great speed/quality balance.

76
Quality
88
Speed
131K
Context
open-source
chat
reasoning
API key
TryKey
TO

Gemma 2 27B

Google

PAID

Largest open Gemma model — strong instruction following.

75
Quality
80
Speed
8K
Context
open-source
chat
general
API key
TryKey
GI

Phi-3.5 MoE (free via GitHub)

Microsoft

FRONTIER

Phi-3.5 MoE — 16x3.8B sparse, free via GitHub PAT.

75
Quality
88
Speed
131K
Context
open-source
frontier-free
moe
API key
TryKey
GR

Llama 3.2 11B Vision

Meta

FREE

Multimodal Llama 3.2 11B — sees images at Groq speed.

74
Quality
92
Speed
128K
Context
vision
open-source
vision
multimodal
TryKey
OP

Nemotron Nano 12B VL (free)

Nvidia

FREE

NVIDIA Nemotron Nano 12B with vision — compact multimodal model.

74
Quality
86
Speed
131K
Context
vision
open-source
vision
multimodal
API key
TryKey
GO

Gemini 2.0 Flash Lite

Google

FREE

Lightest Gemini 2.0 — extremely fast for high-volume tasks.

74
Quality
96
Speed
1.0M
Context
vision
chat
fast
TryKey
MI

Mistral Small

Mistral

FREE

Mistral's Small — free experimental tier, balanced quality.

74
Quality
86
Speed
33K
Context
chat
efficient
API key
TryKey
TO

Llama 3.2 11B Vision

Meta

PAID

Llama 3.2 11B multimodal via Together AI — vision + text.

74
Quality
90
Speed
131K
Context
vision
open-source
vision
multimodal
API key
TryKey
NV

Nemotron Nano 9B v2

Nvidia

FREE

Compact NVIDIA Nemotron Nano — punches above weight at high speed.

74
Quality
95
Speed
131K
Context
open-source
chat
nemotron
API key
TryKey
NV

Phi-4 Multimodal (NVIDIA)

Microsoft

FREE

Microsoft Phi-4 with multimodal vision on NVIDIA — compact image understanding.

73
Quality
88
Speed
131K
Context
vision
open-source
vision
multimodal
API key
TryKey
GI

Phi-4 (free via GitHub)

Microsoft

FRONTIER

Phi-4 — Microsoft's efficient 14B with strong reasoning, free via GitHub PAT.

73
Quality
90
Speed
16K
Context
open-source
frontier-free
chat
API key
TryKey
GR

Gemma 2 9B

Google

FREE

Google's open Gemma 2 9B on Groq — strong small-model quality.

72
Quality
96
Speed
8K
Context
open-source
chat
small
TryKey
OP

Dolphin Mistral 24B (free)

CogComp

FREE

Dolphin Mistral 24B Venice Edition — creative fine-tune, free on OpenRouter.

72
Quality
80
Speed
131K
Context
open-source
chat
creative
API key
TryKey
HU

Nous Hermes 2 Mixtral 8x7B

NousResearch

FREE

Mixtral fine-tuned with DPO by NousResearch — excellent creative tasks.

72
Quality
68
Speed
33K
Context
open-source
chat
creative
API key
TryKey
NV

Llama 3.1 Nemotron Nano 8B

Nvidia

FREE

Nano-sized Nemotron — ultra-fast, Llama-base RLHF tuned.

72
Quality
96
Speed
131K
Context
open-source
chat
nano
API key
TryKey
GI

AI21 Jamba 1.5 Mini (free via GitHub)

AI21

FRONTIER

AI21 Jamba 1.5 Mini — efficient Jamba variant, free via GitHub PAT.

72
Quality
86
Speed
262K
Context
frontier-free
chat
API key
TryKey
OP

Qwen3 8B

Alibaba

PAID

Qwen3 8B — compact but capable with dual thinking modes.

72
Quality
92
Speed
131K
Context
open-source
chat
fast
API key
TryKey
OP

Nemotron Nano 9B (free)

Nvidia

FREE

NVIDIA Nemotron Nano 9B v2 — fast and capable small model.

71
Quality
88
Speed
131K
Context
open-source
chat
small
API key
TryKey
NV

Phi-4 Mini (NVIDIA)

Microsoft

FREE

Microsoft Phi-4 Mini on NVIDIA NIM — tiny but capable 3.8B model.

71
Quality
92
Speed
131K
Context
open-source
chat
reasoning
API key
TryKey
GR

Llama 3.1 8B Instant

Meta

FREE

Fast lightweight Llama 3.1 on Groq's LPU — ideal for high-volume tasks.

70
Quality
99
Speed
128K
Context
open-source
chat
fast
TryKey
CL

Llama 3.1 8B (Cloudflare)

Meta

FREE

Edge-hosted Llama 8B — ultra-low latency from any region globally.

70
Quality
85
Speed
8K
Context
open-source
chat
edge
API key
TryKey
NV

Llama 3.1 8B (NVIDIA)

Meta

FREE

Lightweight Llama 8B on NVIDIA — fast and free, 128K context.

70
Quality
94
Speed
131K
Context
open-source
chat
fast
API key
TryKey
GI

Phi-3.5 vision (free via GitHub)

Microsoft

FRONTIER

Phi-3.5 vision — multimodal Phi, free via GitHub PAT.

70
Quality
88
Speed
131K
Context
vision
open-source
frontier-free
vision
API key
TryKey
HU

Falcon 180B

TII

FREE

TII's massive 180B open model — one of the largest OSS LLMs.

69
Quality
45
Speed
4K
Context
open-source
chat
large
API key
TryKey
MI

Mistral Nemo 12B

Mistral

FREE

12B model jointly trained with NVIDIA — 128K context, multilingual.

68
Quality
88
Speed
131K
Context
open-source
chat
multilingual
API key
TryKey
HU

OpenChat 3.5

OpenChat

FREE

OpenChat 3.5 — top of HuggingFace open-chat leaderboard on release.

68
Quality
75
Speed
8K
Context
open-source
chat
instruction
API key
TryKey
CL

OpenChat 3.5 (Cloudflare)

OpenChat

FREE

OpenChat 3.5 at the edge — previously #1 open-chat model.

68
Quality
88
Speed
8K
Context
open-source
chat
instruction
API key
TryKey
HU

Phi-3.5 Mini Instruct

Microsoft

FREE

Tiny Phi-3.5 Mini with 128K context — Microsoft's efficient SLM.

67
Quality
78
Speed
131K
Context
open-source
chat
tiny
API key
TryKey
CL

Qwen 2.5 7B (Cloudflare)

Alibaba

FREE

Qwen 2.5 7B on Cloudflare edge — strong coding for a small model.

65
Quality
87
Speed
8K
Context
open-source
chat
code
API key
TryKey
CL

SQL Coder 7B (Cloudflare)

Defog

FREE

Specialized SQL generation model on Cloudflare — text-to-SQL.

65
Quality
88
Speed
8K
Context
open-source
code
sql
API key
TryKey
MI

Mistral 7B

Mistral

FREE

Original Mistral 7B — the model that sparked the OSS revolution.

64
Quality
90
Speed
33K
Context
open-source
chat
classic
API key
TryKey
HU

Mistral 7B v0.3

Mistral

FREE

Mistral 7B v0.3 via HuggingFace — free inference API.

64
Quality
72
Speed
33K
Context
open-source
chat
classic
API key
TryKey
TO

Mistral 7B Instruct

Mistral

PAID

Classic Mistral 7B via Together AI — reliable small model.

64
Quality
90
Speed
33K
Context
open-source
chat
small
API key
TryKey
CL

Mistral 7B (Cloudflare)

Mistral

FREE

Original Mistral 7B on Cloudflare Workers AI — fast edge inference.

64
Quality
88
Speed
8K
Context
open-source
chat
classic
API key
TryKey
HU

CodeLlama 34B Instruct

Meta

FREE

Meta's CodeLlama 34B — strong code generation and debugging.

63
Quality
65
Speed
16K
Context
open-source
code
developer
API key
TryKey
CL

Gemma 7B (Cloudflare)

Google

FREE

Google's Gemma 7B on Cloudflare edge — reliable global inference.

63
Quality
86
Speed
8K
Context
open-source
chat
small
API key
TryKey
HU

Zephyr 7B Beta

HuggingFace H4

FREE

Beloved 7B fine-tune of Mistral from HuggingFace H4 team.

62
Quality
70
Speed
4K
Context
open-source
chat
classic
API key
TryKey
GI

Ministral 3B (free via GitHub)

Mistral

FRONTIER

Ministral 3B — ultra-light Mistral, free via GitHub PAT.

62
Quality
96
Speed
131K
Context
open-source
frontier-free
chat
API key
TryKey
GR

Llama 3.2 3B

Meta

FREE

Compact 3B with strong quality-speed trade-off on Groq's LPU hardware.

58
Quality
100
Speed
128K
Context
open-source
chat
tiny
TryKey
OP

Llama 3.2 3B (free)

Meta

FREE

Tiny 3B Llama — fast, free, fine for simple tasks.

58
Quality
90
Speed
131K
Context
open-source
chat
tiny
API key
TryKey
OP

LFM 2.5 1.2B Thinking (free)

Liquid AI

FREE

Liquid Foundation Model 2.5 tiny with thinking — novel non-transformer architecture.

58
Quality
94
Speed
33K
Context
tiny
fast
API key
TryKey
CL

Llama 3.2 3B (Cloudflare)

Meta

FREE

Tiny Llama 3B on Cloudflare edge — global, fast, free.

58
Quality
92
Speed
8K
Context
open-source
chat
tiny
API key
TryKey
NV

Llama 3.2 3B (NVIDIA)

Meta

FREE

Tiny Llama 3.2 on NVIDIA — ideal for high-volume edge workloads.

58
Quality
97
Speed
131K
Context
open-source
chat
tiny
API key
TryKey
CL

Phi-2 (Cloudflare)

Microsoft

FREE

Microsoft's Phi-2 on Cloudflare — efficient 2.7B model.

57
Quality
92
Speed
4K
Context
open-source
chat
tiny
API key
TryKey
OP

LFM 2.5 1.2B Instruct (free)

Liquid AI

FREE

Liquid Foundation Model 2.5 tiny instruct — blazing fast novel architecture.

55
Quality
95
Speed
33K
Context
tiny
fast
API key
TryKey
CL

Llama 2 13B AWQ (Cloudflare)

Meta

FREE

Llama 2 13B quantized at the edge — classic, reliable baseline.

55
Quality
88
Speed
4K
Context
open-source
chat
classic
API key
TryKey
GR

Llama 3.2 1B

Meta

FREE

Ultra-tiny 1B model — blazing speed for simple classification/extraction tasks.

45
Quality
100
Speed
128K
Context
open-source
chat
tiny
TryKey
CL

Llama 3.2 1B (Cloudflare)

Meta

FREE

Smallest Llama on Cloudflare — for global edge classification tasks.

45
Quality
96
Speed
8K
Context
open-source
chat
micro
API key
TryKey
CL

TinyLlama 1.1B (Cloudflare)

Zhang Peiyuan

FREE

Tiny 1.1B model — fastest possible inference for simple tasks.

38
Quality
99
Speed
2K
Context
open-source
chat
micro
API key
TryKey