Rank 10 · AI compute
OpenRouter · Llama 3.1 8B
https://openrouter.ai/api/v1/models/meta-llama/llama-3.1-8b-instruct/endpoints
Public per-token prices for one open AI model across providers.
Consistency · 30d
14.3
● live · checked 4h ago
Test-quote timeline · oldest → newest
bar height = response time · red = no answer
When (UTC)RequestOutcomeTimeAnswer
2026-10-14 12:006991dbcf82ok · 20020ms{"data":{"id":"meta-llama/llama-3.1-8b-instruct","name":"Meta: Llama 3.1 8B Instruct","created":1721692800,"description":"Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...","architecture":{"tokenizer":"Llama3","instruct_type":"llama3","modality":"text->text","input_modalities":["text"],"output_modalities":["text"]},"endpoints":[{"name":"DeepInfra | meta-llama/llama-3.1-8b-instruct","model_id":"meta-llama/llama-3.1-8b-instruct","model_name":"Meta: Llama 3.1 8B Instruct","context_length":131072,"pricing":{"prompt":"0.00000002","completion":"0.00000004","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp8","quantization":"fp8","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias
2026-10-14 06:006991dbcf82ok · 20019ms{"data":{"id":"meta-llama/llama-3.1-8b-instruct","name":"Meta: Llama 3.1 8B Instruct","created":1721692800,"description":"Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...","architecture":{"tokenizer":"Llama3","instruct_type":"llama3","modality":"text->text","input_modalities":["text"],"output_modalities":["text"]},"endpoints":[{"name":"DeepInfra | meta-llama/llama-3.1-8b-instruct","model_id":"meta-llama/llama-3.1-8b-instruct","model_name":"Meta: Llama 3.1 8B Instruct","context_length":131072,"pricing":{"prompt":"0.00000002","completion":"0.00000004","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp8","quantization":"fp8","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias
2026-10-14 00:006991dbcf82ok · 20027ms{"data":{"id":"meta-llama/llama-3.1-8b-instruct","name":"Meta: Llama 3.1 8B Instruct","created":1721692800,"description":"Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...","architecture":{"tokenizer":"Llama3","instruct_type":"llama3","modality":"text->text","input_modalities":["text"],"output_modalities":["text"]},"endpoints":[{"name":"DeepInfra | meta-llama/llama-3.1-8b-instruct","model_id":"meta-llama/llama-3.1-8b-instruct","model_name":"Meta: Llama 3.1 8B Instruct","context_length":131072,"pricing":{"prompt":"0.00000002","completion":"0.00000004","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp8","quantization":"fp8","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias
2026-10-13 18:006991dbcf82ok · 20036ms{"data":{"id":"meta-llama/llama-3.1-8b-instruct","name":"Meta: Llama 3.1 8B Instruct","created":1721692800,"description":"Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...","architecture":{"tokenizer":"Llama3","instruct_type":"llama3","modality":"text->text","input_modalities":["text"],"output_modalities":["text"]},"endpoints":[{"name":"DeepInfra | meta-llama/llama-3.1-8b-instruct","model_id":"meta-llama/llama-3.1-8b-instruct","model_name":"Meta: Llama 3.1 8B Instruct","context_length":131072,"pricing":{"prompt":"0.00000002","completion":"0.00000004","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp8","quantization":"fp8","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias
2026-10-13 12:006991dbcf82ok · 20015ms{"data":{"id":"meta-llama/llama-3.1-8b-instruct","name":"Meta: Llama 3.1 8B Instruct","created":1721692800,"description":"Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...","architecture":{"tokenizer":"Llama3","instruct_type":"llama3","modality":"text->text","input_modalities":["text"],"output_modalities":["text"]},"endpoints":[{"name":"DeepInfra | meta-llama/llama-3.1-8b-instruct","model_id":"meta-llama/llama-3.1-8b-instruct","model_name":"Meta: Llama 3.1 8B Instruct","context_length":131072,"pricing":{"prompt":"0.00000002","completion":"0.00000004","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp8","quantization":"fp8","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias
2026-10-13 06:006991dbcf82ok · 20022ms{"data":{"id":"meta-llama/llama-3.1-8b-instruct","name":"Meta: Llama 3.1 8B Instruct","created":1721692800,"description":"Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...","architecture":{"tokenizer":"Llama3","instruct_type":"llama3","modality":"text->text","input_modalities":["text"],"output_modalities":["text"]},"endpoints":[{"name":"DeepInfra | meta-llama/llama-3.1-8b-instruct","model_id":"meta-llama/llama-3.1-8b-instruct","model_name":"Meta: Llama 3.1 8B Instruct","context_length":131072,"pricing":{"prompt":"0.00000002","completion":"0.00000004","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp8","quantization":"fp8","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias
2026-10-12 22:136991dbcf82ok · 20034ms{"data":{"id":"meta-llama/llama-3.1-8b-instruct","name":"Meta: Llama 3.1 8B Instruct","created":1721692800,"description":"Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...","architecture":{"tokenizer":"Llama3","instruct_type":"llama3","modality":"text->text","input_modalities":["text"],"output_modalities":["text"]},"endpoints":[{"name":"DeepInfra | meta-llama/llama-3.1-8b-instruct","model_id":"meta-llama/llama-3.1-8b-instruct","model_name":"Meta: Llama 3.1 8B Instruct","context_length":131072,"pricing":{"prompt":"0.00000002","completion":"0.00000004","discount":0},"provider_name":"DeepInfra","tag":"deepinfra/fp8","quantization":"fp8","max_completion_tokens":16384,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias