Directory · 99 models reviewed
Every model, measured the same way
Local and cloud, all on one scale. Filter by what your project actually needs, then open any model for the full review.
Showing 99 of 99
Model
Task tags
Context
Price /M
Tooling
Deploy
C
Claude Fable 5
claude-fable-5
creativereasoning
1M
$10 / $50
Cloud
C
Claude Fable 5 (batch)
claude-fable-5-batch
creativereasoning
1M
$5 / $25
Cloud
C
Claude Haiku 4.5
claude-haiku-4-5
extractionspeed
200K
$1 / $5
Cloud
C
Claude Opus 4.8
claude-opus-4-8
agenticreasoning
1M
$5 / $25
Cloud
C
Claude Opus 5
claude-opus-5
agenticreasoning
1M
$5 / $25
Cloud
C
Claude Opus 5 (batch)
claude-opus-5-batch
agenticreasoning
1M
$2.5 / $12.5
Cloud
C
Claude Sonnet 4.6
claude-sonnet-4-6
agenticcoding
1M
$3 / $15
Cloud
C
Claude Sonnet 5
claude-sonnet-5
agenticcoding
1M
$2 / $10
Cloud
C
Claude Sonnet 5 (batch)
claude-sonnet-5-batch
agenticcoding
1M
$1 / $5
Cloud
C
CodeLlama 34B
codellama-34b
coding
16K
Free
Local
C
Codestral 2508
codestral-2508
coding
256K
$0.3 / $0.9
Cloud
C
Command A
command-a
ragagentic
256K
$2.5 / $10
Cloud
C
Command R+ (08-2024)
command-r-08-2024
ragagentic
128K
$2.5 / $10
Cloud
D
DeepSeek Coder V2 Lite
deepseek-coder-v2-lite
coding
128K
Free
Local
D
DeepSeek V4 Flash
deepseek-v4-flash
speedreasoning
1.05M
$0.0868 / $0.1736
Cloud
D
DeepSeek V4 Pro
deepseek-v4-pro
reasoningcoding
1.05M
$0.751854 / $1.503708
Cloud
D
DeepSeek-R1 32B (Qwen distill)
deepseek-r1-32b-qwen-distill
reasoningcoding
128K
Free
Local
D
DeepSeek-R1 8B (Llama distill)
deepseek-r1-8b-llama-distill
reasoning
128K
Free
Local
G
Gemini 2.5 Flash Lite
gemini-2-5-flash-lite
speedlong-context
1.05M
$0.1 / $0.4
Cloud
G
Gemini 2.5 Pro
gemini-2-5-pro
long-contextvision
1.05M
$1.25 / $10
Cloud
G
Gemini 3.1 Flash Lite
gemini-3-1-flash-lite
speedlong-context
1.05M
$0.25 / $1.5
Cloud
G
Gemini 3.1 Pro Preview
gemini-3-1-pro-preview
long-contextreasoning
1.05M
$2 / $12
Cloud
G
Gemini 3.5 Flash
gemini-3-5-flash
speedlong-context
1.05M
$1.5 / $9
Cloud
G
Gemini 3.6 Flash
gemini-3-6-flash
speedlong-context
1.05M
$0.75 / $3.75
Cloud
G
Gemma 3 27B
gemma-3-27b
reasoningcoding
128K
Free
Local
G
Gemma 3 9B
gemma-3-9b
speedlong-context
128K
Free
Local
G
GLM 5.2
glm-5-2
agenticcoding
1.05M
$1.19 / $3.74
Cloud
G
GLM 5.2 (batch)
glm-5-2-batch
agenticcoding
1.05M
$1.4 / $4.4
Cloud
G
GPT-4o
gpt-4o
agenticcoding
128K
$2.5 / $10
Cloud
G
GPT-4o-mini
gpt-4o-mini
extractionspeed
128K
$0.15 / $0.6
Cloud
G
GPT-5.2-Codex
gpt-5-2-codex
codingagentic
400K
$1.75 / $14
Cloud
G
GPT-5.4 Mini
gpt-5-4-mini
codingextraction
400K
$0.75 / $4.5
Cloud
G
GPT-5.4 Nano
gpt-5-4-nano
speedextraction
400K
$0.2 / $1.25
Cloud
G
GPT-5.5
gpt-5-5
agenticcoding
1.05M
$5 / $30
Cloud
G
GPT-5.5 Pro
gpt-5-5-pro
agenticreasoning
1.05M
$30 / $180
Cloud
G
GPT-5.6 Luna
gpt-5-6-luna
agenticcoding
1.05M
$0.2 / $1.2
Cloud
G
GPT-5.6 Luna (batch)
gpt-5-6-luna-batch
agenticcoding
1.05M
$0.1 / $0.6
Cloud
G
GPT-5.6 Luna Pro
gpt-5-6-luna-pro
agenticreasoning
1.05M
$0.2 / $1.2
Cloud
G
GPT-5.6 Luna Pro (batch)
gpt-5-6-luna-pro-batch
agenticreasoning
1.05M
$0.1 / $0.6
Cloud
G
GPT-5.6 Sol
gpt-5-6-sol
agenticreasoning
1.05M
$2 / $10
Cloud
G
GPT-5.6 Sol (batch)
gpt-5-6-sol-batch
agenticreasoning
1.05M
$1 / $5
Cloud
G
GPT-5.6 Sol Pro
gpt-5-6-sol-pro
agenticreasoning
1.05M
$2 / $10
Cloud
G
GPT-5.6 Sol Pro (batch)
gpt-5-6-sol-pro-batch
agenticreasoning
1.05M
$1 / $5
Cloud
G
GPT-5.6 Terra
gpt-5-6-terra
agenticcoding
1.05M
$2 / $12
Cloud
G
GPT-5.6 Terra (batch)
gpt-5-6-terra-batch
agenticcoding
1.05M
$1 / $6
Cloud
G
GPT-5.6 Terra Pro
gpt-5-6-terra-pro
agenticreasoning
1.05M
$2 / $12
Cloud
G
GPT-5.6 Terra Pro (batch)
gpt-5-6-terra-pro-batch
agenticreasoning
1.05M
$1 / $6
Cloud
G
gpt-oss-120b
gpt-oss-120b
reasoningcoding
131K
$0.037 / $0.17
Cloud
G
Grok 4.20 Multi-Agent
grok-4-20-multi-agent
agenticreasoning
2M
$1.25 / $2.5
Cloud
G
Grok 4.3
grok-4-3
reasoningagentic
1M
$1.25 / $2.5
Cloud
G
Grok 4.5
grok-4-5
agenticreasoning
500K
$2 / $6
Cloud
G
Grok 4.6
grok-4-6
agenticreasoning
500K
$2 / $6
Cloud
H
Hermes 3 8B (Llama)
hermes-3-8b-llama
agenticextraction
128K
Free
Local
H
Hy3
hy3
agenticcoding
262K
$0.0825 / $0.33
Cloud
K
Kimi K2.6
kimi-k2-6
agenticcoding
262K
$0.95 / $4
Cloud
K
Kimi K2.7 Code
kimi-k2-7-code
codingagentic
262K
$0.66 / $3.4
Cloud
K
Kimi K3
kimi-k3
agenticcoding
1.05M
$3 / $15
Cloud
L
Laguna S 2.1
laguna-s-2-1
codingagentic
1.05M
$0.09 / $0.18
Cloud
L
Ling-2.6-flash
ling-2-6-flash
speedlong-context
262K
$0.01 / $0.03
Cloud
L
Llama 3.1 70B
llama-3-1-70b
reasoningcoding
128K
Free
Local
L
Llama 3.1 8B
llama-3-1-8b
speedextraction
128K
Free
Local
L
Llama 3.2 3B
llama-3-2-3b
speed
128K
Free
Local
L
Llama 3.3 70B
llama-3-3-70b
agenticreasoning
128K
Free
Local
L
Llama 3.3 70B Instruct
llama-3-3-70b-instruct
agenticreasoning
131K
$0.71 / $0.71
Cloud
L
Llama 4 Maverick
llama-4-maverick
agenticcoding
1.05M
$0.2 / $0.8
Cloud
L
Llama 4 Scout
llama-4-scout
long-contextspeed
1.31M
$0.11 / $0.34
Cloud
L
LLaVA 34B (Vision)
llava-34b-vision
vision
4K
Free
Local
M
MiniMax M3
minimax-m3
agenticcoding
1.05M
$0.3 / $1.2
Cloud
M
MiniMax M3 (batch)
minimax-m3-batch
agenticcoding
524K
$0.3 / $1.2
Cloud
M
Mistral 7B
mistral-7b
speedextraction
32K
Free
Local
M
Mistral Large 3 2512
mistral-large-3-2512
codingreasoning
262K
$0.5 / $1.5
Cloud
M
Mistral Medium 3.5
mistral-medium-3-5
codingreasoning
262K
$1.5 / $7.5
Cloud
M
Mistral Nemo
mistral-nemo
speedextraction
131K
$0.019 / $0.03
Cloud
M
Mistral Nemo 12B
mistral-nemo-12b
codingextraction
128K
Free
Local
M
Mistral Small 4
mistral-small-4
speedextraction
262K
$0.15 / $0.6
Cloud
M
Mixtral 8x7B (MoE)
mixtral-8x7b-moe
codingreasoning
32K
Free
Local
N
Nemotron 3 Super
nemotron-3-super
reasoningcoding
1M
$0.085 / $0.4
Cloud
N
Nemotron 3 Ultra
nemotron-3-ultra
reasoningcoding
262K
$0.5 / $2.2
Cloud
N
Nemotron 3 Ultra (batch)
nemotron-3-ultra-batch
reasoningcoding
512K
$0.6 / $3.6
Cloud
N
Nemotron 3.5 Lightning
nemotron-3-5-lightning
reasoningcoding
262K
$0.08 / $0.2
Cloud
O
o3
o3
reasoningcoding
200K
$2 / $8
Cloud
O
o4 Mini
o4-mini
reasoningcoding
200K
$1.1 / $4.4
Cloud
P
Phi-3.5 Mini
phi-3-5-mini
speed
128K
Free
Local
P
Phi-4 14B
phi-4-14b
reasoningcoding
16K
Free
Local
Q
Qwen 2.5 32B
qwen-2-5-32b
codingreasoning
128K
Free
Local
Q
Qwen 2.5 72B
qwen-2-5-72b
codingreasoning
128K
Free
Local
Q
Qwen 2.5 7B
qwen-2-5-7b
codingextraction
128K
Free
Local
Q
Qwen 2.5 Coder 32B
qwen-2-5-coder-32b
coding
32K
Free
Local
Q
Qwen 2.5 Coder 7B
qwen-2-5-coder-7b
coding
32K
Free
Local
Q
Qwen2-VL 7B (Vision)
qwen2-vl-7b-vision
vision
32K
Free
Local
Q
Qwen3 30B-A3B (MoE)
qwen3-30b-a3b-moe
agenticcoding
32K
Free
Local
Q
Qwen3 8B
qwen3-8b
reasoningcoding
32K
Free
Local
Q
Qwen3 Coder Plus
qwen3-coder-plus
codingagentic
1M
$0.65 / $3.25
Cloud
Q
Qwen3.7 Max
qwen3-7-max
agenticcoding
1M
$1.475 / $4.425
Cloud
Q
Qwen3.7 Plus
qwen3-7-plus
codingreasoning
1M
$0.32 / $1.28
Cloud
Q
Qwen3.8 2.4T A95B
qwen3-8-2-4t-a95b
agenticcoding
1.05M
$2 / $6
Cloud
Q
Qwen3.8 Max
qwen3-8-max
agenticcoding
1M
$2 / $6
Cloud
R
R1 0528
r1-0528
reasoningcoding
164K
$0.5 / $2.15
Cloud
S
Step 3.7 Flash
step-3-7-flash
speedagentic
262K
$0.2 / $1.15
Cloud