← Home

oss-llms

OSS model pricing and availability across inference providers

Updated 10h 49m ago · 1066 entries

sort:
A

Allam 2 7b

other· ctx 4K· free
Groq—
B

Baichuan M2 32b

other· ctx 131K
Novita AI★$0.070 / $0.070
C

Cogito V1 Llama 70B

llama· ctx 131K
Together AI★freeNovita AI$0.80 / $0.80

Cogito V1 Llama 8B

llama· ctx 131K
Together AI★free

Cogito V1 Qwen 14B

qwen· ctx 131K
Together AI★free
nextbit$0.100 / $0.22
DeepInfra$0.12 / $0.24Novita AI$0.15 / $0.15
alibaba$0.23 / $0.91

Cogito V1 Qwen 32B

qwen· ctx 131K
Together AI★freeDeepInfra$0.080 / $0.28Nebius AI Studio$0.100 / $0.30Novita AI$0.10 / $0.45
alibaba$0.10 / $0.42

Cydonia 24b V4.1

other· ctx 131K
Parasail★$0.30 / $0.50
D

DeepCoder 14B

other· ctx 131K
Together AI★free

Deepseek Coder 33b

deepseek· ctx 16K
Together AI★$0.80 / $0.80

DeepSeek OCR 2

deepseek· ctx 1M
Together AI★freeNovita AI$0.030 / $0.030
openinference$0.050 / $0.16
sail-research$0.065 / $0.18
akashml$0.065 / $0.18

Deepseek Prover V2 671b

deepseek· ctx 160K
Novita AI★$0.70 / $2.50

Deepseek R1/community

deepseek· ctx 64K
Novita AI★$4.00 / $4.00

Deepseek V3/community

deepseek· ctx 64K
Novita AI★$0.89 / $0.89

Devstral Small 2505

mistral· ctx 262K
Together AI★freeNovita AI$0.040 / $0.17
mistral$0.15 / $0.60
venice$0.19 / $0.75
E

Ernie 4.5 21B A3b Thinking

other· ctx 131K
Novita AI★$0.070 / $0.28

Ernie 4.5 300b A47b Paddle

other· ctx 123K
Novita AI★$0.28 / $1.10

Ernie 4.5 Vl 28b A3b

other· ctx 30K
Novita AI★$0.14 / $0.56

Ernie 4.5 Vl 424b A47b

other· ctx 123K
Novita AI★$0.42 / $1.25
F

Fireworks/models/kimi K2p6

other· ctx 262K
Fireworks AI—

Fireworks/models/qwen3p7 Plus

qwen
Fireworks AI—

Fireworks/models/qwen3p8 2p4t A95b

qwen· ctx 262K
Fireworks AI—

FLUX 2 Klein 4b

other
DeepInfra—
G

Gemma 2 27b

gemma· ctx 8K
Together AI★$0.80 / $0.80

Gemma 2 9b

gemma· ctx 8K
Together AI★free

Gemma 2b

gemma· ctx 8K
Together AI★free

Gemma 3 12b

gemma· ctx 131K
Novita AI★$0.050 / $0.10

Gemma 3 1b

gemma· ctx 33K
Together AI★free

Gemma 3 270m

gemma· ctx 33K
Together AI★free

Gemma 3 27b

gemma· ctx 98K
Together AI★freeNovita AI$0.12 / $0.20

Gemma 3 4b

gemma· ctx 66K
Together AI★free

Gemma 4 12B

gemma· ctx 262K
Together AI★free

Gemma 4 26B A4B

gemma· ctx 262K· free
google-ai-studio★free
Together AI★free
darkbloom$0.042 / $0.22
DeepInfra$0.070 / $0.34
cloudflare$0.100 / $0.30

Gemma 4 31B Lora

gemma· ctx 262K· free
google-ai-studio★free
Together AI★freeDeepInfra$0.090 / $0.34
coreweave$0.100 / $0.34
venice$0.12 / $0.36

Gemma 4 E2B

gemma· ctx 131K
Together AI★free

Gemma 4 E4B

gemma· ctx 131K
Together AI★free

Glm 4 32b 0414

other· ctx 32K
Novita AI★$0.55 / $1.66

GLM 4.5V

other· ctx 131K
Together AI★freeNovita AI$0.13 / $0.85
siliconflow$0.14 / $0.86
zai$0.20 / $1.10

GLM 4.6

other· ctx 203K
Novita AI★$0.30 / $0.90
zai★$0.30 / $0.90
venice$0.43 / $1.75
DeepInfra$0.50 / $2.00Together AI$0.60 / $2.20

GLM 4.7 Fp4

other· ctx 203K
Together AI★freeDeepInfra$0.060 / $0.40
venice$0.060 / $0.40
cloudflare$0.061 / $0.40
Novita AI$0.070 / $0.40

GLM 5.1

other· ctx 205K
gmicloud★$0.91 / $2.86
streamlake$0.97 / $3.04
Chutes$0.98 / $3.08DeepInfra$1.05 / $3.50
siliconflow$1.19 / $3.74

GLM 5.2 FP8

other· ctx 1M
Together AI★freeDeepInfra$0.49 / $1.56
sail-research$0.50 / $3.15
ambient$0.60 / $2.00
decart$0.68 / $2.28

GLM 5.3 Flash

other· ctx 1M
relace★$0.071 / $0.24
DeepInfra$0.075 / $0.25Novita AI$0.075 / $0.25
zai$0.075 / $0.25
gmicloud$0.075 / $0.25

Gpt Oss 120b

other· ctx 131K
akashml★$0.030 / $0.17
coreweave★$0.030 / $0.17
DeepInfra★$0.037 / $0.17
siliconflow$0.050 / $0.45
Novita AI$0.050 / $0.25

Gpt Oss 20b

other· ctx 131K
darkbloom★$0.020 / $0.100
coreweave$0.030 / $0.13
DeepInfra$0.030 / $0.14Parasail$0.030 / $0.15Novita AI$0.040 / $0.15

Granite 4.0 H Micro

other· ctx 131K
cloudflare★$0.017 / $0.11

Granite 4.1 8b

other· ctx 131K
coreweave★$0.050 / $0.100

Granite 4.2 8b

other· ctx 131K
coreweave★$0.100 / $0.15
H

Hermes 4 405b

nous· ctx 131K
Nebius AI Studio★$1.00 / $3.00

Hermes 4 70b

nous· ctx 131K
Nebius AI Studio★$0.13 / $0.40

Holo3 35B A3B

other· ctx 262K
Together AI★free

Hunyuan A13b

other· ctx 131K
siliconflow★$0.14 / $0.57

Hy Mt2 1.8b

other· ctx 8K
tencent★$0.044 / $0.18
L

L3 70b Euryale V2.1

other· ctx 8K
Novita AI★$1.48 / $1.48

L3 8b Lunaris

other· ctx 8K
Novita AI★$0.050 / $0.050

Laguna Xs 2.1

other· ctx 262K
poolside★$0.060 / $0.12

Lfm 2.5 2.6b

other· ctx 66K· free
liquid★free

Ling 2.6 Flash

other· ctx 262K
Novita AI★$0.10 / $0.30

Ling 3.0 Flash Fin

other· ctx 262K
Novita AI★freeDeepInfra$0.060 / $0.18

Llama 2 7b

llama· ctx 4K
Together AI★free

Llama 3 8b

llama· ctx 8K
Novita AI★$0.040 / $0.040Together AI$0.20 / $0.20

Llama 3.1 405B

llama· ctx 131K
Together AI★free

Llama 3.2 1B

llama· ctx 131K
Together AI★freeNovita AI$0.020 / $0.020

Llama 3.2 3B

llama· ctx 131K
Together AI★freeNovita AI$0.030 / $0.050

Llama 4 Maverick

llama· ctx 1M
DeepInfra★$0.100 / $0.30Novita AI$0.18 / $0.59
digitalocean$0.20 / $0.70
google$0.25 / $0.70
Parasail$0.35 / $1.00

Llama 4 Scout 17B 16E

llama· ctx 262K
Together AI★freeNovita AI$0.18 / $0.59

Llama Guard 4 12b

llama· ctx 164K
DeepInfra★$0.18 / $0.18

Longcat 2.0

other· ctx 1M
atlascloud★$0.30 / $1.20
M

Medgemma 27b Text

gemma· ctx 131K
Together AI★free

Meta Llama 3 70B

llama· ctx 8K
Novita AI★$0.51 / $0.74Together AI$0.88 / $0.88

Meta Llama/llama Prompt Guard 2 22m

llama· ctx 512· free
Groq—

Meta Llama/llama Prompt Guard 2 86m

llama· ctx 512· free
Groq—

Meta/llama 3.1 8b

llama· ctx 16K
Together AI★freeNovita AI$0.020 / $0.050

Meta/llama 3.2 11b Vision

llama· ctx 16K
Together AI★free

Meta/llama 3.2 90b Vision

llama· ctx 16K
Together AI★free

Meta/llama 3.3 70b

llama· ctx 131K
Together AI★freeNovita AI$0.14 / $0.40SambaNova$0.60 / $1.20

Minimax M3:batch

other· ctx 524K
Together AI★$0.30 / $1.20

Ministral 14b 2512

mistral· ctx 262K
mistral★$0.20 / $0.20

Ministral 3 14B 2512

mistral· ctx 262K
Together AI★$0.20 / $0.20

Ministral 3b 2512

mistral· ctx 131K
mistral★$0.100 / $0.100

Ministral 8b 2512

mistral· ctx 262K
mistral★$0.15 / $0.15

Mistral 7B V0.1

mistral· ctx 33K
Together AI★free

Mistral Small 24B 2501

mistral· ctx 128K
mistral★$0.100 / $0.30
Together AI★$0.10 / $0.30
venice$0.20 / $0.90

Mistral Small 3.2 24b

mistral· ctx 131K
DeepInfra★$0.075 / $0.20Parasail$0.090 / $0.30

Mistralai/mixtral 8x22b V01

mistral· ctx 16K
Together AI★free

Mistralai/mixtral 8x7b V01

mistral· ctx 16K
Together AI★free

Molmo 7B D 0924

other· ctx 8K
Together AI★free
tencent$0.074 / $0.29

Muse Glimmer 30B

other· ctx 131K
Phala★$0.30 / $1.10Parasail★$0.30 / $1.10DeepInfra★$0.30 / $1.20Together AI$0.35 / $1.50Fireworks AI$0.35 / $1.50

Mythomax L2 13b

other· ctx 4K
Novita AI★$0.090 / $0.090
N

Nemotron 3 Ultra 550b A55b

other· ctx 1M· free
nvidia★free
DeepInfra$0.50 / $2.20Together AI$0.60 / $3.60
baseten$0.60 / $2.40
venice$0.63 / $3.13

Nemotron 3.5 Lightning

other· ctx 1M· free
nvidia★free
DeepInfra$0.080 / $0.20
coreweave$0.100 / $0.25
siliconflow$0.100 / $0.30

Nous Hermes Llama2 13b

llama· ctx 4K
Novita AI★$0.17 / $0.17

Nv Mistralai/mistral Nemo 12b

mistral· ctx 16K
Together AI★free

NVIDIA Nemotron 3 Nano 30B A3B

other· ctx 262K· free
nvidia★free
Together AI★freeDeepInfra$0.050 / $0.20Crusoe$0.050 / $0.20Novita AI$0.050 / $0.20

NVIDIA Nemotron 3 Super 120B A12B FP8

other· ctx 1M· free
nvidia★free
Together AI★freeDeepInfra$0.085 / $0.40
digitalocean$0.30 / $0.65

NVIDIA Nemotron Nano 9B V2

other· ctx 131K
Novita AI★$0.035 / $0.14Together AI$0.060 / $0.25DeepInfra—

Nvidia/llama 3.1 Nemotron 70b

llama· ctx 16K
Together AI★free

Nvidia/llama 3.3 Nemotron Super 49b V1

llama· ctx 16K
Together AI★free
O

Openchat 7b

openchat· ctx 4K
Novita AI★$0.060 / $0.060

Openhermes 2.5 Mistral 7b

mistral· ctx 4K
Novita AI★$0.17 / $0.17
Q

Qwen 2 1.5b

qwen· ctx 33K
Together AI★$0.10 / $0.10

Qwen 2 7b

qwen· ctx 33K
Novita AI★$0.054 / $0.054

Qwen 2.5 72b

qwen· ctx 32K
Novita AI★$0.38 / $0.40

Qwen/qwen3.6 27b

qwen· ctx 262K· free
alibaba★$0.20 / $1.56
siliconflow$0.25 / $2.00
DeepInfra$0.26 / $2.60
atlascloud$0.27 / $2.16
Novita AI$0.30 / $2.40

Qwen2 1.5B

qwen· ctx 33K
Together AI★free

Qwen2 72B

qwen· ctx 33K
Together AI★freeNovita AI$0.45 / $0.45

Qwen2 7B

qwen· ctx 33K
Together AI★freeNovita AI$0.070 / $0.070

Qwen2.5 3B

qwen· ctx 33K
Together AI★free

Qwen3 0.6B

qwen· ctx 41K
Together AI★free

Qwen3 1.7B

qwen· ctx 41K
Together AI★free

Qwen3 235B A22B 2507 FP8

qwen· ctx 262K
Together AI★free
gmicloud$0.087 / $0.35
Novita AI$0.090 / $0.58DeepInfra$0.090 / $0.55Parasail$0.14 / $0.80

Qwen3 30B A3B

qwen· ctx 262K
Together AI★free
streamlake$0.048 / $0.19
Novita AI$0.070 / $0.27
siliconflow$0.070 / $0.28
coreweave$0.100 / $0.30

Qwen3 4B Base

qwen· ctx 128K
Together AI★freeNovita AI$0.030 / $0.030

Qwen3 8B Lora

qwen· ctx 262K
Together AI★freeNovita AI$0.035 / $0.14
alibaba$0.12 / $0.45
Parasail$0.25 / $0.75Fireworks AI—

Qwen3 Coder 480B A35B FP8

qwen· ctx 262K
Novita AI★$0.38 / $1.55Together AI$2.00 / $2.00

Qwen3 Next 80B A3B FP8

qwen· ctx 262K
Together AI★freeDeepInfra$0.090 / $1.10
alibaba$0.098 / $0.78
Parasail$0.100 / $1.10Novita AI$0.15 / $1.50

Qwen3.5 122B A10B FP8

qwen· ctx 262K
Together AI★free
siliconflow$0.26 / $2.08
alibaba$0.26 / $2.08
DeepInfra$0.29 / $2.40
atlascloud$0.30 / $2.40

Qwen3.5 2B Lora

qwen· ctx 262K
Together AI★free

Qwen3.5 35B A3B

qwen· ctx 262K
Together AI★free
darkbloom$0.050 / $0.70
DeepInfra$0.100 / $0.95
akashml$0.100 / $0.90
venice$0.100 / $1.00

Qwen3.5 397B A17B

qwen· ctx 262K
alibaba★$0.39 / $2.34
DeepInfra$0.45 / $3.00Parasail$0.50 / $3.60
digitalocean$0.55 / $3.50
atlascloud$0.55 / $3.50

Qwen3.5 9B FP8

qwen· ctx 262K
Together AI★freeDeepInfra$0.100 / $0.15
siliconflow$0.100 / $0.15
venice$0.100 / $0.15
Parasail$0.100 / $0.25

Qwen3.8 2.4T A95B

qwen· ctx 1M
DeepInfra★$2.00 / $6.00Novita AI★$2.00 / $6.00
modal★$2.00 / $6.00
alibaba★$2.00 / $6.00
siliconflow★$2.00 / $6.00

Qwen3.8 Flash

qwen· ctx 1M
Novita AI★freeParasail$0.12 / $0.80Together AI$0.15 / $0.47
alibaba$0.15 / $0.47
streamlake$0.18 / $0.90
S

Sarvam M

other· ctx 1M· free
thinking-machines★free
cohere★free
Together AI★freeNovita AI★free
nex-agi$0.025 / $0.100

Step 3.7 Flash

other· ctx 262K
stepfun★$0.20 / $1.15
DeepInfra★$0.20 / $1.15Novita AI★$0.20 / $1.15
T

Ternary Bonsai 27B

other· ctx 262K
Together AI★free
U

Ui Tars 1.5 7b

other· ctx 128K
Parasail★$0.100 / $0.20
W

Wizardlm 2 8x22b

wizard· ctx 66K
Novita AI★$0.62 / $0.62