| 01-ai/yi-large |
fireworks |
retired |
— |
| agentica-org/deepcoder-14b-preview |
chutes |
retired |
— |
| agentica-org/deepcoder-14b-preview:free |
chutes |
retired |
— |
| alibaba/tongyi-deepresearch-30b-a3b |
ncompass/bf16 |
— |
retired (stalled) |
| alpindale/goliath-120b |
mancer/int4 |
retired |
— |
| amazon/nova-lite-v1 |
amazon-bedrock |
— |
retired (stalled) |
| amazon/nova-micro-v1 |
amazon-bedrock |
— |
retired (stalled) |
| anthracite-org/magnum-v4-72b |
mancer/fp8 |
retired |
— |
| anthropic/claude-haiku-4.5 |
anthropic |
— |
retired (stalled) |
| anthropic/claude-sonnet-4.5 |
anthropic |
— |
retired (stalled) |
| arliai/qwq-32b-arliai-rpr-v1 |
chutes |
retired |
— |
| arliai/qwq-32b-arliai-rpr-v1:free |
chutes |
retired |
— |
| bytedance/ui-tars-1.5-7b |
parasail/bf16 |
monitoring |
— |
| cognitivecomputations/dolphin3.0-mistral-24b |
chutes |
retired |
— |
| cognitivecomputations/dolphin3.0-mistral-24b:free |
chutes |
retired |
— |
| cognitivecomputations/dolphin3.0-r1-mistral-24b |
chutes |
retired |
— |
| cognitivecomputations/dolphin3.0-r1-mistral-24b:free |
chutes |
retired |
— |
| cohere/command-r-08-2024 |
cohere |
— |
retired (stalled) |
| deepseek/deepseek-chat |
fireworks |
retired |
— |
| deepseek/deepseek-chat |
chutes |
retired |
— |
| deepseek/deepseek-chat |
nebius/fp8 |
retired |
— |
| deepseek/deepseek-chat-v3-0324 |
chutes/fp8 |
retired |
— |
| deepseek/deepseek-chat-v3-0324 |
modelrun/fp4 |
retired |
— |
| deepseek/deepseek-chat-v3-0324 |
baseten/fp8 |
— |
retired (stalled) |
| deepseek/deepseek-chat-v3-0324 |
lambda/fp8 |
retired |
— |
| deepseek/deepseek-chat-v3-0324 |
deepseek/fp8 |
retired |
— |
| deepseek/deepseek-chat-v3-0324 |
fireworks |
retired |
retired (stalled) |
| deepseek/deepseek-chat-v3-0324 |
klusterai |
retired |
— |
| deepseek/deepseek-chat-v3-0324 |
nebius/fp8 |
retired |
— |
| deepseek/deepseek-chat-v3-0324 |
crusoe/fp8 |
retired |
— |
| deepseek/deepseek-chat-v3-0324 |
atlas-cloud/fp8 |
— |
retired (stalled) |
| deepseek/deepseek-chat-v3-0324 |
hyperbolic/fp8 |
retired |
retired (stalled) |
| deepseek/deepseek-chat-v3-0324:free |
chutes/fp8 |
retired |
— |
| deepseek/deepseek-chat-v3.1 |
fireworks |
retired |
— |
| deepseek/deepseek-chat-v3.1 |
gmicloud/fp8 |
retired |
— |
| deepseek/deepseek-chat-v3.1 |
sambanova/fp8 |
— |
retired (stalled) |
| deepseek/deepseek-chat-v3.1 |
deepseek |
retired |
— |
| deepseek/deepseek-chat-v3.1 |
wandb/fp8 |
monitoring |
— |
| deepseek/deepseek-chat-v3.1 |
byteplus |
retired |
— |
| deepseek/deepseek-chat-v3.1 |
mara |
monitoring |
— |
| deepseek/deepseek-chat-v3.1 |
google-vertex/us-west2 |
monitoring |
— |
| deepseek/deepseek-chat-v3.1 |
parasail/fp8 |
retired |
— |
| deepseek/deepseek-chat-v3.1 |
chutes |
retired |
— |
| deepseek/deepseek-chat:free |
chutes |
retired |
— |
| deepseek/deepseek-r1 |
fireworks/fp8 |
retired |
— |
| deepseek/deepseek-r1 |
nebius/fast |
retired |
— |
| deepseek/deepseek-r1 |
nebius/base |
retired |
— |
| deepseek/deepseek-r1 |
lambda/fp8 |
retired |
— |
| deepseek/deepseek-r1-0528 |
nebius/fp8 |
retired |
— |
| deepseek/deepseek-r1-0528 |
fireworks |
retired |
— |
| deepseek/deepseek-r1-0528 |
klusterai |
retired |
— |
| deepseek/deepseek-r1-0528 |
lambda/fp8 |
retired |
— |
| deepseek/deepseek-r1-0528 |
chutes |
retired |
— |
| deepseek/deepseek-r1-0528 |
crusoe/fp8 |
retired |
— |
| deepseek/deepseek-r1-0528-qwen3-8b |
chutes |
retired |
— |
| deepseek/deepseek-r1-0528-qwen3-8b:free |
chutes |
retired |
— |
| deepseek/deepseek-r1-0528:free |
chutes |
retired |
— |
| deepseek/deepseek-r1-distill-llama-70b |
lambda/fp8 |
retired |
— |
| deepseek/deepseek-r1-distill-llama-70b |
nebius/fp8 |
retired |
— |
| deepseek/deepseek-r1-distill-llama-70b |
chutes |
retired |
— |
| deepseek/deepseek-r1-distill-llama-70b:free |
chutes |
retired |
— |
| deepseek/deepseek-v3.2 |
deepseek |
retired |
— |
| deepseek/deepseek-v3.2 |
streamlake/fp8 |
retired |
— |
| deepseek/deepseek-v3.2 |
google-vertex |
monitoring |
— |
| deepseek/deepseek-v3.2 |
sambanova |
monitoring |
— |
| deepseek/deepseek-v3.2 |
digitalocean |
monitoring |
— |
| deepseek/deepseek-v3.2 |
phala |
— |
retired (stalled) |
| deepseek/deepseek-v3.2 |
streamlake |
retired |
— |
| deepseek/deepseek-v3.2 |
atlas-cloud/fp8 |
retired |
— |
| deepseek/deepseek-v3.2 |
parasail/fp8 |
— |
retired (stalled) |
| deepseek/deepseek-v3.2 |
friendli |
monitoring |
— |
| deepseek/deepseek-v3.2-exp |
atlas-cloud/fp8 |
retired |
— |
| deepseek/deepseek-v4-flash |
gmicloud/fp8 |
— |
monitoring |
| deepseek/deepseek-v4-flash |
venice |
— |
monitoring |
| deepseek/deepseek-v4-flash |
atlas-cloud/fp4 |
— |
monitoring |
| deepseek/deepseek-v4-flash |
parasail/fp8 |
— |
monitoring |
| deepseek/deepseek-v4-flash |
wandb/fp8 |
monitoring |
monitoring |
| deepseek/deepseek-v4-flash |
nextbit/fp8 |
monitoring |
monitoring |
| deepseek/deepseek-v4-flash |
baidu/fp8 |
— |
monitoring |
| deepseek/deepseek-v4-flash |
cloudflare |
retired |
— |
| deepseek/deepseek-v4-flash |
streamlake/fp8 |
— |
monitoring |
| deepseek/deepseek-v4-flash |
alibaba |
— |
monitoring |
| deepseek/deepseek-v4-flash |
wafer/fp4 |
retired |
— |
| deepseek/deepseek-v4-flash |
deepseek |
— |
monitoring |
| deepseek/deepseek-v4-flash |
deepinfra/fp4 |
— |
monitoring |
| deepseek/deepseek-v4-flash |
akashml/fp8 |
monitoring |
monitoring |
| deepseek/deepseek-v4-flash |
streamlake |
— |
monitoring |
| deepseek/deepseek-v4-flash |
morph |
monitoring |
monitoring |
| deepseek/deepseek-v4-flash |
fireworks |
— |
monitoring |
| deepseek/deepseek-v4-flash |
digitalocean |
monitoring |
monitoring |
| deepseek/deepseek-v4-pro |
novita/fp8 |
— |
monitoring |
| deepseek/deepseek-v4-pro |
parasail/fp8 |
— |
monitoring |
| deepseek/deepseek-v4-pro |
streamlake/fp8 |
— |
monitoring |
| deepseek/deepseek-v4-pro |
baseten/fp4 |
— |
monitoring |
| deepseek/deepseek-v4-pro |
wandb/fp8 |
monitoring |
monitoring |
| deepseek/deepseek-v4-pro |
together |
— |
monitoring |
| deepseek/deepseek-v4-pro |
deepinfra/fp4 |
— |
monitoring |
| deepseek/deepseek-v4-pro |
deepseek |
— |
monitoring |
| deepseek/deepseek-v4-pro |
fireworks |
— |
monitoring |
| deepseek/deepseek-v4-pro |
gmicloud/fp8 |
— |
monitoring |
| deepseek/deepseek-v4-pro |
venice |
— |
monitoring |
| deepseek/deepseek-v4-pro |
streamlake |
— |
monitoring |
| deepseek/deepseek-v4-pro |
digitalocean |
monitoring |
monitoring |
| google/gemma-2-9b-it |
chutes |
retired |
— |
| google/gemma-2-9b-it:free |
chutes |
retired |
— |
| google/gemma-3-12b-it |
chutes/bf16 |
retired |
retired (stalled) |
| google/gemma-3-12b-it |
deepinfra/bf16 |
— |
retired (stalled) |
| google/gemma-3-12b-it |
novita/bf16 |
— |
retired (stalled) |
| google/gemma-3-12b-it |
crusoe/bf16 |
— |
retired (stalled) |
| google/gemma-3-12b-it:free |
chutes/bf16 |
retired |
— |
| google/gemma-3-27b-it |
parasail/fp8 |
monitoring |
— |
| google/gemma-3-27b-it |
phala |
— |
retired (stalled) |
| google/gemma-3-27b-it |
klusterai |
retired |
— |
| google/gemma-3-27b-it |
nebius/fp8 |
retired |
— |
| google/gemma-3-27b-it |
chutes/bf16 |
retired |
retired (stalled) |
| google/gemma-3-27b-it:free |
chutes/bf16 |
retired |
— |
| google/gemma-3-4b-it |
deepinfra/bf16 |
— |
retired (stalled) |
| google/gemma-3-4b-it |
chutes |
— |
retired (stalled) |
| google/gemma-4-26b-a4b-it |
novita/bf16 |
monitoring |
— |
| google/gemma-4-26b-a4b-it |
parasail/bf16 |
monitoring |
— |
| google/gemma-4-26b-a4b-it |
venice/bf16 |
monitoring |
— |
| google/gemma-4-26b-a4b-it |
nextbit/bf16 |
monitoring |
— |
| google/gemma-4-26b-a4b-it |
cloudflare |
monitoring |
— |
| google/gemma-4-26b-a4b-it |
dekallm/bf16 |
monitoring |
— |
| google/gemma-4-26b-a4b-it |
wafer/fp8 |
monitoring |
— |
| google/gemma-4-26b-a4b-it |
google-vertex/global |
monitoring |
— |
| google/gemma-4-26b-a4b-it |
ambient |
retired |
— |
| google/gemma-4-31b-it |
wandb/bf16 |
monitoring |
— |
| google/gemma-4-31b-it |
parasail/fp8 |
monitoring |
— |
| google/gemma-4-31b-it |
novita/bf16 |
monitoring |
— |
| google/gemma-4-31b-it |
ambient |
retired |
— |
| google/gemma-4-31b-it |
venice/bf16 |
monitoring |
— |
| gryphe/mythomax-l2-13b |
mancer/fp8 |
retired |
— |
| gryphe/mythomax-l2-13b |
nextbit/int4 |
monitoring |
— |
| ibm-granite/granite-4.0-h-micro |
cloudflare |
monitoring |
— |
| ibm-granite/granite-4.1-8b |
wandb/bf16 |
monitoring |
— |
| inclusionai/ling-2.6-1t |
novita |
monitoring |
— |
| inclusionai/ling-2.6-flash |
novita |
monitoring |
— |
| inflection/inflection-3-pi |
inflection |
— |
retired (stalled) |
| kwaipilot/kat-coder-pro |
streamlake/fp16 |
— |
retired (stalled) |
| kwaipilot/kat-coder-pro-v2 |
streamlake |
monitoring |
— |
| mancer/weaver |
mancer/fp8 |
retired |
— |
| meta-llama/llama-3.1-405b-instruct |
lambda/fp8 |
retired |
— |
| meta-llama/llama-3.1-405b-instruct |
fireworks/fp8 |
retired |
— |
| meta-llama/llama-3.1-405b-instruct |
nebius/fp8 |
retired |
— |
| meta-llama/llama-3.1-70b-instruct |
fireworks |
retired |
— |
| meta-llama/llama-3.1-70b-instruct |
wandb/bf16 |
monitoring |
— |
| meta-llama/llama-3.1-70b-instruct |
nebius/fp8 |
retired |
— |
| meta-llama/llama-3.1-70b-instruct |
lambda/fp8 |
retired |
— |
| meta-llama/llama-3.1-8b-instruct |
cerebras/fp16 |
retired |
— |
| meta-llama/llama-3.1-8b-instruct |
fireworks |
retired |
— |
| meta-llama/llama-3.1-8b-instruct |
novita/fp8 |
monitoring |
— |
| meta-llama/llama-3.1-8b-instruct |
nebius/fp8 |
retired |
— |
| meta-llama/llama-3.1-8b-instruct |
wandb/bf16 |
monitoring |
— |
| meta-llama/llama-3.1-8b-instruct |
klusterai/fp8 |
retired |
— |
| meta-llama/llama-3.1-8b-instruct |
lambda/bf16 |
retired |
— |
| meta-llama/llama-3.2-11b-vision-instruct |
lambda/bf16 |
retired |
— |
| meta-llama/llama-3.2-3b-instruct |
parasail/bf16 |
monitoring |
— |
| meta-llama/llama-3.2-3b-instruct |
lambda/bf16 |
retired |
— |
| meta-llama/llama-3.3-70b-instruct |
akashml/fp8 |
monitoring |
— |
| meta-llama/llama-3.3-70b-instruct |
crusoe/int8 |
retired |
— |
| meta-llama/llama-3.3-70b-instruct |
fireworks/fp16 |
retired |
— |
| meta-llama/llama-3.3-70b-instruct |
wandb/fp16 |
monitoring |
— |
| meta-llama/llama-3.3-70b-instruct |
crusoe/bf16 |
retired |
— |
| meta-llama/llama-3.3-70b-instruct |
sambanova/bf16 |
retired |
— |
| meta-llama/llama-3.3-70b-instruct |
lambda/fp8 |
retired |
— |
| meta-llama/llama-3.3-70b-instruct |
novita/bf16 |
monitoring |
— |
| meta-llama/llama-3.3-70b-instruct |
cerebras/fp16 |
retired |
— |
| meta-llama/llama-3.3-70b-instruct |
nebius/fp8 |
retired |
— |
| meta-llama/llama-3.3-70b-instruct |
hyperbolic/fp8 |
retired |
— |
| meta-llama/llama-3.3-70b-instruct |
klusterai/fp8 |
retired |
— |
| meta-llama/llama-3.3-70b-instruct |
parasail/fp8 |
monitoring |
— |
| meta-llama/llama-4-maverick |
parasail/fp8 |
monitoring |
— |
| meta-llama/llama-4-maverick |
digitalocean |
monitoring |
— |
| meta-llama/llama-4-maverick |
klusterai/fp8 |
retired |
— |
| meta-llama/llama-4-maverick |
lambda/fp8 |
retired |
— |
| meta-llama/llama-4-maverick:free |
chutes/fp8 |
retired |
— |
| meta-llama/llama-4-scout |
lambda/fp8 |
retired |
— |
| meta-llama/llama-4-scout |
klusterai |
retired |
— |
| meta-llama/llama-4-scout:free |
chutes/bf16 |
retired |
— |
| meta-llama/llama-guard-2-8b |
together |
— |
retired (stalled) |
| meta-llama/llama-guard-3-8b |
fireworks |
retired |
— |
| meta-llama/llama-guard-3-8b |
nebius |
retired |
— |
| microsoft/mai-ds-r1 |
chutes/fp8 |
retired |
— |
| microsoft/phi-4 |
nextbit/int4 |
retired |
retired (stalled) |
| microsoft/phi-4 |
deepinfra/bf16 |
— |
retired (stalled) |
| microsoft/phi-4 |
nebius/fp8 |
retired |
— |
| microsoft/phi-4-mini-instruct |
wandb/bf16 |
retired |
— |
| microsoft/phi-4-multimodal-instruct |
deepinfra/bf16 |
— |
retired (stalled) |
| minimax/minimax-m1:extended |
chutes |
retired |
— |
| minimax/minimax-m2 |
fireworks |
retired |
— |
| minimax/minimax-m2.1 |
nebius/fp8 |
retired |
— |
| minimax/minimax-m2.1 |
fireworks |
retired |
— |
| minimax/minimax-m2.5 |
fireworks |
retired |
— |
| minimax/minimax-m2.5 |
inceptron/fp8 |
retired |
— |
| minimax/minimax-m3 |
morph |
retired |
— |
| minimax/minimax-m3 |
together |
— |
monitoring |
| minimax/minimax-m3 |
venice/fp8 |
— |
retired (no_bis) |
| mistralai/devstral-medium |
mistral |
— |
retired (stalled) |
| mistralai/devstral-small |
nebius/fp8 |
retired |
— |
| mistralai/devstral-small-2505 |
chutes |
retired |
— |
| mistralai/devstral-small-2505 |
deepinfra/bf16 |
— |
retired (stalled) |
| mistralai/devstral-small-2505 |
nebius/fp8 |
retired |
— |
| mistralai/devstral-small-2505:free |
chutes |
retired |
— |
| mistralai/devstral-small:free |
chutes |
retired |
— |
| mistralai/ministral-14b-2512 |
nextbit/fp8 |
monitoring |
— |
| mistralai/ministral-3b |
mistral |
— |
retired (stalled) |
| mistralai/ministral-3b-2512 |
mistral |
— |
retired (stalled) |
| mistralai/ministral-3b-2512 |
nextbit/fp8 |
monitoring |
— |
| mistralai/ministral-8b |
mistral |
— |
retired (stalled) |
| mistralai/ministral-8b-2512 |
mistral |
— |
retired (stalled) |
| mistralai/ministral-8b-2512 |
nextbit/fp8 |
monitoring |
— |
| mistralai/mistral-7b-instruct-v0.3 |
together |
— |
retired (stalled) |
| mistralai/mistral-nemo |
nebius/fp8 |
retired |
— |
| mistralai/mistral-nemo |
deepinfra/fp8 |
— |
retired (stalled) |
| mistralai/mistral-nemo |
novita/fp8 |
monitoring |
— |
| mistralai/mistral-nemo |
chutes |
retired |
— |
| mistralai/mistral-nemo |
mistral |
— |
retired (stalled) |
| mistralai/mistral-nemo |
chutes/bf16 |
— |
retired (stalled) |
| mistralai/mistral-nemo |
azure |
— |
retired (stalled) |
| mistralai/mistral-nemo |
klusterai |
retired |
— |
| mistralai/mistral-nemo:free |
chutes |
retired |
— |
| mistralai/mistral-small-24b-instruct-2501 |
klusterai |
retired |
— |
| mistralai/mistral-small-24b-instruct-2501 |
chutes |
retired |
— |
| mistralai/mistral-small-24b-instruct-2501:free |
chutes |
retired |
— |
| mistralai/mistral-small-3.1-24b-instruct |
nebius/fp8 |
retired |
— |
| mistralai/mistral-small-3.1-24b-instruct |
chutes |
retired |
— |
| mistralai/mistral-small-3.1-24b-instruct:free |
chutes |
retired |
— |
| mistralai/mistral-small-3.2-24b-instruct |
parasail/bf16 |
monitoring |
retired (stalled) |
| mistralai/mistral-small-3.2-24b-instruct |
chutes |
retired |
— |
| mistralai/mistral-small-3.2-24b-instruct:free |
chutes |
retired |
— |
| mistralai/mixtral-8x22b-instruct |
fireworks |
retired |
— |
| mistralai/pixtral-12b |
mistral |
— |
retired (stalled) |
| mistralai/pixtral-12b |
hyperbolic/bf16 |
retired |
— |
| moonshotai/kimi-dev-72b:free |
chutes/bf16 |
retired |
— |
| moonshotai/kimi-k2 |
nebius/fp4 |
retired |
— |
| moonshotai/kimi-k2 |
chutes/fp8 |
retired |
— |
| moonshotai/kimi-k2 |
moonshotai/fp8 |
retired |
— |
| moonshotai/kimi-k2 |
fireworks/fp8 |
retired |
— |
| moonshotai/kimi-k2-0905 |
fireworks/fp8 |
retired |
— |
| moonshotai/kimi-k2-0905 |
byteplus |
retired |
— |
| moonshotai/kimi-k2-0905:exacto |
moonshotai |
— |
retired (stalled) |
| moonshotai/kimi-k2-thinking |
nebius/fp8 |
retired |
— |
| moonshotai/kimi-k2-thinking |
parasail/int4 |
retired |
— |
| moonshotai/kimi-k2.5 |
streamlake |
monitoring |
— |
| moonshotai/kimi-k2.5 |
inceptron/int4 |
retired |
— |
| moonshotai/kimi-k2.5 |
streamlake/fp8 |
monitoring |
— |
| moonshotai/kimi-k2.6 |
streamlake |
monitoring |
— |
| moonshotai/kimi-k2.6 |
streamlake/fp8 |
monitoring |
— |
| moonshotai/kimi-k2:free |
chutes/fp8 |
retired |
— |
| moonshotai/kimi-linear-48b-a3b-instruct |
parasail/bf16 |
retired |
— |
| moonshotai/kimi-vl-a3b-thinking |
chutes |
retired |
— |
| moonshotai/kimi-vl-a3b-thinking:free |
chutes |
retired |
— |
| morph/morph-v3-large |
morph |
monitoring |
— |
| neversleep/llama-3.1-lumimaid-8b |
nextbit/int4 |
retired |
— |
| neversleep/llama-3.1-lumimaid-8b |
mancer/fp16 |
retired |
— |
| neversleep/noromaid-20b |
mancer/fp8 |
retired |
— |
| nousresearch/deephermes-3-llama-3-8b-preview:free |
chutes/bf16 |
retired |
— |
| nousresearch/deephermes-3-mistral-24b-preview |
chutes |
retired |
— |
| nousresearch/hermes-2-pro-llama-3-8b |
nextbit/int4 |
— |
retired (stalled) |
| nousresearch/hermes-2-pro-llama-3-8b |
lambda/bf16 |
retired |
— |
| nousresearch/hermes-3-llama-3.1-405b |
nebius/fp8 |
retired |
— |
| nousresearch/hermes-3-llama-3.1-405b |
lambda/fp8 |
retired |
— |
| nousresearch/hermes-3-llama-3.1-70b |
hyperbolic/fp8 |
retired |
— |
| nousresearch/hermes-3-llama-3.1-70b |
nextbit/fp8 |
retired |
— |
| nousresearch/hermes-3-llama-3.1-70b |
lambda/fp8 |
retired |
— |
| nousresearch/hermes-4-405b |
nebius/fp8 |
retired |
— |
| nousresearch/hermes-4-405b |
chutes/fp8 |
retired |
— |
| nousresearch/hermes-4-70b |
nebius/fp8 |
retired |
— |
| nousresearch/hermes-4-70b |
chutes |
retired |
— |
| nvidia/llama-3.1-nemotron-70b-instruct |
lambda/fp8 |
retired |
— |
| nvidia/llama-3.1-nemotron-ultra-253b-v1 |
nebius/fp8 |
retired |
— |
| nvidia/llama-3.3-nemotron-super-49b-v1 |
nebius/fp8 |
retired |
— |
| nvidia/llama-3.3-nemotron-super-49b-v1:free |
chutes/bf16 |
retired |
— |
| openai/chatgpt-4o-latest |
openai |
retired |
— |
| openai/gpt-3.5-turbo |
openai |
monitoring |
— |
| openai/gpt-3.5-turbo-0613 |
azure |
monitoring |
— |
| openai/gpt-3.5-turbo-16k |
azure |
monitoring |
— |
| openai/gpt-3.5-turbo-16k |
openai |
monitoring |
— |
| openai/gpt-4.1 |
openai |
retired |
— |
| openai/gpt-4.1-mini |
openai |
retired |
— |
| openai/gpt-4.1-nano |
openai |
retired |
— |
| openai/gpt-4o |
azure |
monitoring |
— |
| openai/gpt-4o |
openai |
monitoring |
retired (stalled) |
| openai/gpt-4o-2024-05-13 |
azure |
monitoring |
— |
| openai/gpt-4o-2024-05-13 |
openai |
monitoring |
— |
| openai/gpt-4o-2024-08-06 |
azure |
monitoring |
— |
| openai/gpt-4o-2024-08-06 |
openai |
monitoring |
— |
| openai/gpt-4o-2024-11-20 |
openai |
monitoring |
— |
| openai/gpt-4o-mini |
azure |
monitoring |
retired (stalled) |
| openai/gpt-4o-mini |
azure/swedencentral |
monitoring |
— |
| openai/gpt-4o-mini |
openai |
monitoring |
retired (stalled) |
| openai/gpt-4o-mini-2024-07-18 |
openai |
monitoring |
— |
| openai/gpt-4o:extended |
openai |
retired |
— |
| openai/gpt-oss-120b |
chutes |
retired |
— |
| openai/gpt-oss-120b |
crusoe/bf16 |
retired |
— |
| openai/gpt-oss-120b |
mara |
monitoring |
— |
| openai/gpt-oss-120b |
crusoe |
retired |
— |
| openai/gpt-oss-120b |
nebius/fp4 |
retired |
— |
| openai/gpt-oss-20b |
nebius/fp4 |
retired |
— |
| qwen/qwen-2.5-72b-instruct |
hyperbolic/bf16 |
— |
retired (stalled) |
| qwen/qwen-2.5-72b-instruct |
fireworks |
retired |
— |
| qwen/qwen-2.5-72b-instruct |
nebius/fp8 |
retired |
— |
| qwen/qwen-2.5-72b-instruct |
chutes/bf16 |
retired |
— |
| qwen/qwen-2.5-72b-instruct:free |
chutes/bf16 |
retired |
— |
| qwen/qwen-2.5-7b-instruct |
phala |
monitoring |
— |
| qwen/qwen-2.5-coder-32b-instruct |
nebius/fp8 |
retired |
— |
| qwen/qwen-2.5-coder-32b-instruct |
hyperbolic/fp8 |
retired |
— |
| qwen/qwen-2.5-coder-32b-instruct |
chutes |
retired |
— |
| qwen/qwen-2.5-coder-32b-instruct |
lambda/bf16 |
retired |
— |
| qwen/qwen-2.5-coder-32b-instruct |
chutes/fp8 |
— |
retired (stalled) |
| qwen/qwen-2.5-coder-32b-instruct:free |
chutes |
retired |
— |
| qwen/qwen-2.5-vl-7b-instruct |
klusterai |
retired |
— |
| qwen/qwen-2.5-vl-7b-instruct |
hyperbolic/bf16 |
retired |
— |
| qwen/qwen2.5-vl-32b-instruct |
fireworks |
retired |
— |
| qwen/qwen2.5-vl-32b-instruct |
chutes/bf16 |
retired |
— |
| qwen/qwen2.5-vl-72b-instruct |
chutes |
retired |
— |
| qwen/qwen2.5-vl-72b-instruct |
nebius/fp8 |
monitoring |
— |
| qwen/qwen2.5-vl-72b-instruct |
hyperbolic |
retired |
— |
| qwen/qwen2.5-vl-72b-instruct |
parasail/fp8 |
monitoring |
— |
| qwen/qwen3-14b |
nebius/fp8 |
retired |
— |
| qwen/qwen3-14b:free |
chutes |
retired |
— |
| qwen/qwen3-235b-a22b |
klusterai/fp8 |
retired |
— |
| qwen/qwen3-235b-a22b |
nebius/fp8 |
retired |
— |
| qwen/qwen3-235b-a22b-2507 |
gmicloud/fp8 |
monitoring |
— |
| qwen/qwen3-235b-a22b-2507 |
chutes |
retired |
— |
| qwen/qwen3-235b-a22b-2507 |
streamlake |
monitoring |
— |
| qwen/qwen3-235b-a22b-2507 |
crusoe/bf16 |
— |
retired (stalled) |
| qwen/qwen3-235b-a22b-2507 |
cerebras/fp16 |
retired |
— |
| qwen/qwen3-235b-a22b-2507 |
cerebras |
retired |
retired (stalled) |
| qwen/qwen3-235b-a22b-2507 |
parasail/fp8 |
monitoring |
— |
| qwen/qwen3-235b-a22b-2507 |
nebius/fp8 |
retired |
— |
| qwen/qwen3-235b-a22b-2507 |
friendli |
monitoring |
— |
| qwen/qwen3-235b-a22b-2507 |
google-vertex/us-south1 |
monitoring |
— |
| qwen/qwen3-235b-a22b-2507 |
wandb/bf16 |
retired |
retired (stalled) |
| qwen/qwen3-235b-a22b:free |
chutes |
retired |
— |
| qwen/qwen3-30b-a3b |
nebius/fp8 |
retired |
— |
| qwen/qwen3-30b-a3b |
chutes |
retired |
— |
| qwen/qwen3-30b-a3b-instruct-2507 |
nebius/fp8 |
retired |
— |
| qwen/qwen3-30b-a3b-instruct-2507 |
wandb/bf16 |
monitoring |
— |
| qwen/qwen3-30b-a3b-instruct-2507 |
streamlake |
monitoring |
— |
| qwen/qwen3-30b-a3b-instruct-2507 |
atlas-cloud/fp8 |
retired |
— |
| qwen/qwen3-30b-a3b:free |
chutes |
retired |
— |
| qwen/qwen3-32b |
lambda/fp8 |
retired |
— |
| qwen/qwen3-32b |
nebius/fast |
retired |
— |
| qwen/qwen3-32b |
chutes |
retired |
— |
| qwen/qwen3-32b |
nebius/fp8 |
retired |
— |
| qwen/qwen3-32b |
nebius/base |
retired |
— |
| qwen/qwen3-32b |
cerebras/fp16 |
retired |
— |
| qwen/qwen3-32b |
cerebras |
retired |
— |
| qwen/qwen3-32b:free |
chutes |
retired |
— |
| qwen/qwen3-8b:free |
chutes |
retired |
— |
| qwen/qwen3-coder |
chutes |
retired |
— |
| qwen/qwen3-coder |
nebius/fp8 |
retired |
— |
| qwen/qwen3-coder |
fireworks |
retired |
— |
| qwen/qwen3-coder |
google-vertex/us-south1 |
monitoring |
— |
| qwen/qwen3-coder |
chutes/fp8 |
retired |
— |
| qwen/qwen3-coder |
hyperbolic/fp8 |
retired |
— |
| qwen/qwen3-coder |
wandb/bf16 |
monitoring |
— |
| qwen/qwen3-coder-30b-a3b-instruct |
digitalocean |
monitoring |
— |
| qwen/qwen3-coder-next |
ionstream/fp8 |
monitoring |
— |
| qwen/qwen3-coder-next |
parasail/bf16 |
monitoring |
— |
| qwen/qwen3-next-80b-a3b-instruct |
novita/bf16 |
monitoring |
— |
| qwen/qwen3-next-80b-a3b-instruct |
google-vertex/global |
monitoring |
— |
| qwen/qwen3-next-80b-a3b-instruct |
ambient |
retired |
— |
| qwen/qwen3-next-80b-a3b-instruct |
parasail/fp8 |
monitoring |
— |
| qwen/qwen3-next-80b-a3b-thinking |
nebius/fp8 |
retired |
— |
| qwen/qwen3-vl-235b-a22b-instruct |
fireworks |
— |
retired (stalled) |
| qwen/qwen3-vl-235b-a22b-instruct |
parasail/fp8 |
monitoring |
— |
| qwen/qwen3-vl-30b-a3b-instruct |
novita/bf16 |
monitoring |
— |
| qwen/qwen3-vl-30b-a3b-instruct |
fireworks |
— |
retired (stalled) |
| qwen/qwen3-vl-8b-instruct |
parasail/bf16 |
monitoring |
— |
| qwen/qwen3.5-9b |
parasail/bf16 |
monitoring |
— |
| qwen/qwq-32b |
hyperbolic/bf16 |
retired |
— |
| qwen/qwq-32b |
nebius/fp8 |
retired |
— |
| qwen/qwq-32b |
nextbit/int4 |
retired |
— |
| qwen/qwq-32b |
fireworks |
retired |
— |
| qwen/qwq-32b:free |
chutes/bf16 |
retired |
— |
| rekaai/reka-edge |
reka/bf16 |
monitoring |
— |
| rekaai/reka-flash-3 |
reka/fp8 |
monitoring |
— |
| rekaai/reka-flash-3:free |
chutes/bf16 |
retired |
— |
| relace/relace-search |
relace/bf16 |
— |
retired (stalled) |
| sao10k/l3.1-euryale-70b |
nextbit/fp8 |
retired |
— |
| sao10k/l3.3-euryale-70b |
nextbit/bf16 |
monitoring |
— |
| sarvamai/sarvam-m:free |
chutes |
retired |
— |
| sentientagi/dobby-mini-unhinged-plus-llama-3.1-8b |
fireworks |
retired |
— |
| shisa-ai/shisa-v2-llama3.3-70b |
chutes |
retired |
— |
| shisa-ai/shisa-v2-llama3.3-70b:free |
chutes |
retired |
— |
| tencent/hunyuan-a13b-instruct |
chutes/bf16 |
retired |
— |
| tencent/hunyuan-a13b-instruct:free |
chutes/bf16 |
retired |
— |
| tencent/hy3-preview |
siliconflow |
— |
monitoring |
| tencent/hy3-preview |
gmicloud/bf16 |
— |
monitoring |
| thedrummer/cydonia-24b-v4.1 |
parasail/bf16 |
monitoring |
— |
| thedrummer/rocinante-12b |
nextbit/bf16 |
retired |
— |
| thedrummer/rocinante-12b |
parasail/bf16 |
monitoring |
— |
| thedrummer/skyfall-36b-v2 |
chutes |
retired |
— |
| thedrummer/skyfall-36b-v2 |
parasail/fp8 |
monitoring |
— |
| thedrummer/unslopnemo-12b |
nextbit/fp8 |
monitoring |
— |
| thudm/glm-4-32b:free |
chutes |
retired |
— |
| thudm/glm-z1-32b |
chutes |
retired |
— |
| thudm/glm-z1-32b:free |
chutes |
retired |
— |
| tngtech/deepseek-r1t-chimera |
chutes |
retired |
— |
| tngtech/deepseek-r1t-chimera:free |
chutes |
retired |
— |
| undi95/remm-slerp-l2-13b |
mancer/fp8 |
retired |
— |
| undi95/remm-slerp-l2-13b |
nextbit/bf16 |
monitoring |
— |
| x-ai/grok-2-1212 |
xai |
retired |
— |
| x-ai/grok-2-vision-1212 |
xai |
retired |
— |
| x-ai/grok-3 |
xai |
retired |
— |
| x-ai/grok-3 |
xai/fast |
retired |
— |
| x-ai/grok-3-beta |
xai |
retired |
— |
| x-ai/grok-3-beta |
xai/fast |
retired |
— |
| x-ai/grok-3-mini |
xai |
retired |
— |
| x-ai/grok-3-mini |
xai/fast |
retired |
— |
| x-ai/grok-3-mini-beta |
xai/fast |
retired |
— |
| x-ai/grok-3-mini-beta |
xai |
retired |
— |
| x-ai/grok-4 |
xai |
retired |
— |
| x-ai/grok-beta |
xai |
retired |
— |
| x-ai/grok-code-fast-1 |
xai |
retired |
— |
| x-ai/grok-vision-beta |
xai |
retired |
— |
| xiaomi/mimo-v2.5 |
xiaomi/fp8 |
— |
monitoring |
| xiaomi/mimo-v2.5 |
digitalocean |
— |
monitoring |
| xiaomi/mimo-v2.5 |
deepinfra/bf16 |
— |
monitoring |
| xiaomi/mimo-v2.5 |
parasail/fp8 |
— |
monitoring |
| xiaomi/mimo-v2.5 |
venice/fp8 |
— |
monitoring |
| z-ai/glm-4.5 |
chutes/fp8 |
retired |
— |
| z-ai/glm-4.5 |
mancer/fp8 |
retired |
— |
| z-ai/glm-4.5-air:free |
chutes/bf16 |
retired |
— |
| z-ai/glm-4.6 |
cerebras |
retired |
— |
| z-ai/glm-4.6 |
mancer/fp8 |
retired |
— |
| z-ai/glm-4.6 |
fireworks |
retired |
— |
| z-ai/glm-4.7 |
cerebras/fp16 |
retired |
— |
| z-ai/glm-4.7 |
mancer/fp4 |
retired |
— |
| z-ai/glm-4.7 |
mancer/fp8 |
retired |
— |
| z-ai/glm-4.7 |
cerebras |
retired |
— |
| z-ai/glm-4.7 |
inceptron/fp8 |
retired |
— |
| z-ai/glm-5 |
fireworks |
retired |
— |
| z-ai/glm-5.1 |
phala |
retired |
— |
| z-ai/glm-5.1 |
gmicloud/fp8 |
monitoring |
— |
| z-ai/glm-5.2 |
gmicloud/fp8 |
retired |
— |
| z-ai/glm-5.2 |
alibaba |
retired |
— |