{"models":[{"id":"deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo","type":"llm","name":"Llama 3.3 70B Instruct Turbo","model_id":"meta-llama/Llama-3.3-70B-Instruct-Turbo","capabilities":["text","tools"],"speed":"fast","cost":0.032,"quality":"good","context_window":131072,"max_output_tokens":131072,"description":"","params":{"temperature":{"min":0,"max":2,"default":1},"caller_params":["chat_template_kwargs","repetition_penalty","seed","top_k"]},"pricing":{"billing_unit":"per_mtok","input":[0.1],"output":[0.32]},"region":"US","model":"llama-3.3-70b-instruct-turbo","family":"llama-3.3-70b-instruct-turbo","pooled":true,"provider":{"slug":"deepinfra","display_name":"DeepInfra","owner_country":"US"},"service_route":{"id":"deepinfra/us","adapter":"deepinfra"},"maker":{"slug":"meta","display_name":"Meta","country":"US"},"country":"United States","compliance":{"residency":"US","country":"United States","inference_location":"US","zdr":{"logging":false,"moderation":false,"caching":null,"training":false,"subprocessors":null},"training":"no","logging":"none","moderation":"none","caching":"unknown","content_storage":"unknown","dpa_available":true,"third_party_access":null,"transfer_mechanism":"unknown","route_id":"deepinfra/us"},"release":{"date":"2024-12-06","source":"vendor","url":"https://github.com/meta-llama/llama-models/blob/main/models/llama3_3/MODEL_CARD.md"},"quantization":"fp8","references":[{"kind":"model_card","url":"https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct","created_at":"2026-10-07T06:52:19.408494Z","updated_at":"2026-10-07T06:52:19.408494Z"},{"kind":"paper","url":"https://arxiv.org/abs/2407.21783","created_at":"2026-10-07T06:52:19.408494Z","updated_at":"2026-10-07T06:52:19.408494Z"}],"input_modalities":["text"],"output_modalities":["text"]},{"id":"deepinfra:flex/meta-llama/Llama-3.3-70B-Instruct-Turbo","type":"llm","name":"Llama 3.3 70B Instruct Turbo","model_id":"meta-llama/Llama-3.3-70B-Instruct-Turbo","capabilities":["text","tools"],"speed":"fast","cost":0.026,"quality":"good","context_window":131072,"max_output_tokens":131072,"description":"","params":{"temperature":{"min":0,"max":2,"default":1},"caller_params":["chat_template_kwargs","repetition_penalty","seed","top_k"]},"pricing":{"billing_unit":"per_mtok","input":[0.08],"output":[0.256]},"region":"US","model":"llama-3.3-70b-instruct-turbo","family":"llama-3.3-70b-instruct-turbo","provider":{"slug":"deepinfra","display_name":"DeepInfra","owner_country":"US"},"service_route":{"id":"deepinfra/us","adapter":"deepinfra"},"service_tier":"flex","maker":{"slug":"meta","display_name":"Meta","country":"US"},"country":"United States","compliance":{"residency":"US","country":"United States","inference_location":"US","zdr":{"logging":false,"moderation":false,"caching":null,"training":false,"subprocessors":null},"training":"no","logging":"none","moderation":"none","caching":"unknown","content_storage":"unknown","dpa_available":true,"third_party_access":null,"transfer_mechanism":"unknown","route_id":"deepinfra/us"},"release":{"date":"2024-12-06","source":"vendor","url":"https://github.com/meta-llama/llama-models/blob/main/models/llama3_3/MODEL_CARD.md"},"quantization":"fp8","references":[{"kind":"model_card","url":"https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct","created_at":"2026-10-07T06:52:19.408494Z","updated_at":"2026-10-07T06:52:19.408494Z"},{"kind":"paper","url":"https://arxiv.org/abs/2407.21783","created_at":"2026-10-07T06:52:19.408494Z","updated_at":"2026-10-07T06:52:19.408494Z"}],"input_modalities":["text"],"output_modalities":["text"]},{"id":"evroc/llama-3.3-70b-instruct","type":"llm","name":"Llama 3.3 70B Instruct FP8","model_id":"nvidia/Llama-3.3-70B-Instruct-FP8","capabilities":["text","tools","structured_output"],"speed":"medium","cost":0.127,"quality":"great","context_window":128000,"max_output_tokens":8192,"description":"Meta Llama 3.3 70B on Evroc (EU)","params":{"temperature":{"min":0,"max":2,"default":1},"caller_params":["chat_template_kwargs","frequency_penalty","min_p","repetition_penalty","seed","top_k"]},"pricing":{"billing_unit":"per_mtok","input":[1.1253],"output":[1.1253]},"region":"EU","model":"llama-3.3-70b-instruct-fp8","family":"llama-3.3-70b-instruct-fp8","pooled":true,"provider":{"slug":"evroc","display_name":"Evroc","owner_country":"SE"},"service_route":{"id":"evroc/think-eu","adapter":"evroc"},"maker":{"slug":"meta","display_name":"Meta","country":"US"},"country":"Sweden","compliance":{"residency":"EU","country":"Sweden","inference_location":"SE","zdr":{"logging":false,"moderation":false,"caching":null,"training":false,"subprocessors":false},"training":"no","logging":"none","moderation":"none","caching":"unknown","content_storage":"unknown","dpa_available":true,"third_party_access":null,"transfer_mechanism":"eu_resident","route_id":"evroc/think-eu"},"release":{"date":"2024-12-06","source":"vendor","url":"https://github.com/meta-llama/llama-models/blob/main/models/llama3_3/MODEL_CARD.md"},"quantization":"fp8","references":[{"kind":"model_card","url":"https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct","created_at":"2026-10-07T06:52:19.408494Z","updated_at":"2026-10-07T06:52:19.408494Z"},{"kind":"paper","url":"https://arxiv.org/abs/2407.21783","created_at":"2026-10-07T06:52:19.408494Z","updated_at":"2026-10-07T06:52:19.408494Z"}],"input_modalities":["text"],"output_modalities":["text"]},{"id":"greenpt/llama-3.3-70b-instruct","type":"llm","name":"Llama 3.3 70B","model_id":"llama-3.3-70b-instruct","capabilities":["text","structured_output","tools"],"speed":"medium","cost":0.136,"quality":"great","context_window":131072,"max_output_tokens":16384,"description":"","params":{"temperature":{"min":0,"max":2,"default":1},"caller_params":["min_p","top_k"]},"pricing":{"billing_unit":"per_mtok","input":[1.23783],"output":[1.23783]},"region":"EU","model":"llama-3.3-70b-instruct","family":"llama-3.3-70b-instruct","pooled":true,"provider":{"slug":"greenpt","display_name":"GreenPT","owner_country":"NL"},"service_route":{"id":"greenpt/eu","adapter":"greenpt"},"maker":{"slug":"meta","display_name":"Meta","country":"US"},"compliance":{"residency":"EU","inference_location":"EU","zdr":{"logging":false,"moderation":false,"caching":true,"training":false,"subprocessors":true},"training":"no","logging":"none","moderation":"unknown","caching":"implicit","content_storage":"ephemeral","dpa_available":true,"third_party_access":true,"transfer_mechanism":"eu_resident","route_id":"greenpt/eu"},"release":{"date":"2024-12-06","source":"vendor","url":"https://github.com/meta-llama/llama-models/blob/main/models/llama3_3/MODEL_CARD.md"},"references":[{"kind":"model_card","url":"https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct","created_at":"2026-10-07T06:52:19.408494Z","updated_at":"2026-10-07T06:52:19.408494Z"},{"kind":"paper","url":"https://arxiv.org/abs/2407.21783","created_at":"2026-10-07T06:52:19.408494Z","updated_at":"2026-10-07T06:52:19.408494Z"}],"input_modalities":["text"],"output_modalities":["text"]},{"id":"infercom/llama-3.3-70b-instruct","type":"llm","name":"Llama 3.3 70B Instruct","model_id":"Meta-Llama-3.3-70B-Instruct","capabilities":["text","tools","structured_output"],"speed":"fast","cost":0.118,"quality":"good","context_window":131072,"max_output_tokens":131072,"description":"Meta Llama 3.3 70B Instruct on Infercom","params":{"temperature":{"min":0,"max":2,"default":1},"caller_params":["logit_bias","repetition_penalty","top_k"]},"pricing":{"billing_unit":"per_mtok","input":[0.67518],"output":[1.35036]},"region":"US","model":"meta-llama-3.3-70b-instruct","family":"meta-llama-3.3-70b-instruct","pooled":true,"provider":{"slug":"infercom","display_name":"Infercom","owner_country":"LU"},"service_route":{"id":"infercom/us","adapter":"infercom"},"maker":{"slug":"meta","display_name":"Meta","country":"US"},"country":"United States","compliance":{"residency":"US","country":"United States","inference_location":"US","zdr":{"logging":false,"moderation":false,"caching":null,"training":false,"subprocessors":true},"training":"no","logging":"none","moderation":"none","caching":"unknown","content_storage":"unknown","dpa_available":true,"third_party_access":true,"transfer_mechanism":"sccs","route_id":"infercom/us"},"release":{"date":"2024-12-06","source":"vendor","url":"https://github.com/meta-llama/llama-models/blob/main/models/llama3_3/MODEL_CARD.md"},"references":[{"kind":"model_card","url":"https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct","created_at":"2026-10-07T06:52:19.408494Z","updated_at":"2026-10-07T06:52:19.408494Z"},{"kind":"paper","url":"https://arxiv.org/abs/2407.21783","created_at":"2026-10-07T06:52:19.408494Z","updated_at":"2026-10-07T06:52:19.408494Z"}],"input_modalities":["text"],"output_modalities":["text"]},{"id":"nextbit:eu/euryale:33-70b","type":"llm","name":"L3.3 70B Euryale v2.3","model_id":"euryale:33-70b","capabilities":["text","structured_output"],"speed":"fast","cost":0.089,"quality":"good","context_window":131072,"max_output_tokens":16384,"description":"L3.3 70B Euryale v2.3 by Sao10K, an independent developer. Hugging Face: https://huggingface.co/Sao10K/L3.3-70B-Euryale-v2.3. Base model: Meta's Llama 3.3 70B Instruct, https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct.","params":{"temperature":{"min":0,"max":2,"default":1},"caller_params":["chat_template_kwargs","min_p","repetition_penalty","seed","top_k"]},"pricing":{"billing_unit":"per_mtok","input":[0.65],"output":[0.75]},"region":"EU","aliases":["nextbit/euryale:33-70b"],"model":"l3.3-70b-euryale-v2.3","family":"l3.3-70b-euryale-v2.3","pooled":true,"provider":{"slug":"nextbit","display_name":"Nextbit","owner_country":"ES"},"service_route":{"id":"nextbit:eu","adapter":"nextbit:eu"},"maker":{"slug":"community","display_name":"Community"},"country":"Spain","compliance":{"residency":"EU","country":"Spain","inference_location":"ES","zdr":{"logging":false,"moderation":null,"caching":true,"training":false,"subprocessors":true},"training":"no","logging":"none","moderation":"unknown","caching":"implicit","content_storage":"ephemeral","dpa_available":true,"third_party_access":true,"transfer_mechanism":"eu_resident","route_id":"nextbit:eu"},"quantization":"bf16","references":[{"kind":"model_card","url":"https://huggingface.co/Sao10K/L3.3-70B-Euryale-v2.3","created_at":"2026-10-07T06:52:19.408494Z","updated_at":"2026-10-07T06:52:19.408494Z"}],"input_modalities":["text"],"output_modalities":["text"]},{"id":"novita/meta-llama/llama-3.3-70b-instruct","type":"llm","name":"Llama 3.3 70B","model_id":"meta-llama/llama-3.3-70b-instruct","capabilities":["text","tools","structured_output"],"speed":"fast","cost":0.04,"quality":"good","context_window":131072,"max_output_tokens":120000,"description":"","params":{"temperature":{"min":0,"max":2,"default":1},"caller_params":["chat_template_kwargs","repetition_penalty","top_k"]},"pricing":{"billing_unit":"per_mtok","input":[0.135],"output":[0.4]},"region":"US","model":"llama-3.3-70b-instruct","family":"llama-3.3-70b-instruct","pooled":true,"provider":{"slug":"novita","display_name":"Novita","owner_country":"US"},"service_route":{"id":"novita/api-us","adapter":"novita"},"maker":{"slug":"meta","display_name":"Meta","country":"US"},"country":"United States","compliance":{"residency":"US","country":"United States","inference_location":"US","zdr":{"logging":false,"moderation":false,"caching":null,"training":false,"subprocessors":null},"training":"no","logging":"none","moderation":"default_on","caching":"unknown","content_storage":"unknown","dpa_available":true,"third_party_access":true,"transfer_mechanism":"sccs","route_id":"novita/api-us"},"release":{"date":"2024-12-06","source":"vendor","url":"https://github.com/meta-llama/llama-models/blob/main/models/llama3_3/MODEL_CARD.md"},"quantization":"bf16","references":[{"kind":"model_card","url":"https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct","created_at":"2026-10-07T06:52:19.408494Z","updated_at":"2026-10-07T06:52:19.408494Z"},{"kind":"paper","url":"https://arxiv.org/abs/2407.21783","created_at":"2026-10-07T06:52:19.408494Z","updated_at":"2026-10-07T06:52:19.408494Z"}],"input_modalities":["text"],"output_modalities":["text"]},{"id":"scaleway/llama-3.3-70b-instruct","type":"llm","name":"Llama 3.3 70B","model_id":"llama-3.3-70b-instruct","capabilities":["text","tools","structured_output"],"speed":"fast","cost":0.118,"quality":"good","context_window":131072,"max_output_tokens":16384,"description":"","params":{"temperature":{"min":0,"max":2,"default":1},"caller_params":["frequency_penalty","min_p","presence_penalty","repetition_penalty","seed","top_k"]},"pricing":{"billing_unit":"per_mtok","input":[1.01277],"output":[1.01277]},"region":"EU","model":"llama-3.3-70b-instruct","family":"llama-3.3-70b-instruct","pooled":true,"provider":{"slug":"scaleway","display_name":"Scaleway","owner_country":"FR"},"service_route":{"id":"scaleway","adapter":"scaleway"},"maker":{"slug":"meta","display_name":"Meta","country":"US"},"country":"France","compliance":{"residency":"EU","country":"France","inference_location":"FR","zdr":{"logging":true,"moderation":false,"caching":true,"training":false,"subprocessors":false},"training":"no","logging":"abuse_monitoring","retention_days":14,"moderation":"none","caching":"implicit","content_storage":"retained","dpa_available":true,"third_party_access":true,"transfer_mechanism":"eu_resident","route_id":"scaleway"},"release":{"date":"2024-12-06","source":"vendor","url":"https://github.com/meta-llama/llama-models/blob/main/models/llama3_3/MODEL_CARD.md"},"references":[{"kind":"model_card","url":"https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct","created_at":"2026-10-07T06:52:19.408494Z","updated_at":"2026-10-07T06:52:19.408494Z"},{"kind":"paper","url":"https://arxiv.org/abs/2407.21783","created_at":"2026-10-07T06:52:19.408494Z","updated_at":"2026-10-07T06:52:19.408494Z"}],"input_modalities":["text"],"output_modalities":["text"]},{"id":"scx:us/llama-3.3-70b-instruct","type":"llm","name":"Llama 3.3 70B","model_id":"Meta-Llama-3.3-70B-Instruct","capabilities":["text","tools","structured_output"],"speed":"medium","cost":0.169,"quality":"great","context_window":131072,"max_output_tokens":8192,"description":"Llama 3.3 70B Instruct at bf16 on SCX's California SambaNova deployment, 128K context.","params":{"temperature":{"min":0,"max":2,"default":1},"caller_params":["chat_template_kwargs","seed","top_k"]},"pricing":{"billing_unit":"per_mtok","input":[0.8211384],"output":[2.6311222800000005]},"region":"US","model":"llama-3.3-70b-instruct","family":"llama-3.3-70b-instruct","provider":{"slug":"scx","display_name":"SCX","owner_country":"AU"},"service_route":{"id":"scx:us","adapter":"scx:us"},"maker":{"slug":"meta","display_name":"Meta","country":"US"},"country":"United States","compliance":{"residency":"US","country":"United States","inference_location":"US","zdr":{"logging":false,"moderation":false,"caching":null,"training":false,"subprocessors":null},"training":"no","logging":"none","moderation":"optional","caching":"unknown","content_storage":"unknown","dpa_available":true,"third_party_access":null,"transfer_mechanism":"unknown","route_id":"scx:us"},"release":{"date":"2024-12-06","source":"vendor","url":"https://github.com/meta-llama/llama-models/blob/main/models/llama3_3/MODEL_CARD.md"},"references":[{"kind":"model_card","url":"https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct","created_at":"2026-10-07T06:52:19.408494Z","updated_at":"2026-10-07T06:52:19.408494Z"},{"kind":"paper","url":"https://arxiv.org/abs/2407.21783","created_at":"2026-10-07T06:52:19.408494Z","updated_at":"2026-10-07T06:52:19.408494Z"}],"input_modalities":["text"],"output_modalities":["text"]}],"total":9,"offset":0,"limit":50}