llm-adapters

Supported Models

This table provides an overview of the supported models, including their vendor, provider, cost details, and capabilities.

Model Vendor Provider Prompt $ Completion $ Request $ Context Completion User Repeating Roles Streaming Vision Tools Supports N System Multiple Systems Empty Content Tool Choice Tool Choice Required JSON Output JSON Content Last Assistant First Assistant Temperature Only System Only Assistant
jamba-1.5-mini ai21 ai21 $2e-07 $4e-07 $0.0 256000 N/A
jamba-1.5-large ai21 ai21 $2e-06 $8e-06 $0.0 256000 N/A
claude-3-haiku-20240307 anthropic anthropic $2.5e-07 $1.25e-06 $0.0 200000 4096
claude-3-sonnet-20240229 anthropic anthropic $3e-06 $1.5e-05 $0.0 200000 4096
claude-3-opus-20240229 anthropic anthropic $1.5e-05 $7.5e-05 $0.0 200000 4096
claude-3-opus-latest anthropic anthropic $1.5e-05 $7.5e-05 $0.0 200000 4096
claude-3-5-haiku-20241022 anthropic anthropic $1e-06 $5e-06 $0.0 200000 8192
claude-3-5-sonnet-20240620 anthropic anthropic $3e-06 $1.5e-05 $0.0 200000 4096
claude-3-5-sonnet-20241022 anthropic anthropic $3e-06 $1.5e-05 $0.0 200000 4096
claude-3-5-haiku-latest anthropic anthropic $1e-06 $5e-06 $0.0 200000 8192
claude-3-5-sonnet-latest anthropic anthropic $3e-06 $1.5e-05 $0.0 200000 4096
gpt-4o openai azure $5e-06 $1.5e-05 $0.0 128000 4096
gpt-4o-mini openai azure $1.5e-07 $6e-07 $0.0 128000 16385
llama3.1-8b meta-llama cerebras $1e-07 $1e-07 $0.0 128000 8192
llama3.1-70b meta-llama cerebras $6e-07 $6e-07 $0.0 128000 8192
command-r-plus-04-2024 cohere cohere $3e-06 $1.5e-05 $0.0 128000 4000
command-r-plus-08-2024 cohere cohere $2.5e-06 $1e-05 $0.0 128000 4000
command-r-plus cohere cohere $2.5e-06 $1e-05 $0.0 128000 4000
command-r-03-2024 cohere cohere $5e-07 $1.5e-06 $0.0 128000 4000
command-r-08-2024 cohere cohere $1.5e-07 $6e-07 $0.0 128000 4000
command-r cohere cohere $1.5e-07 $6e-07 $0.0 128000 4000
command cohere cohere $1e-06 $2e-06 $0.0 4000 4000
command-nightly cohere cohere $1e-06 $2e-06 $0.0 128000 128000
command-light cohere cohere $3e-07 $6e-07 $0.0 4000 4000
command-light-nightly cohere cohere $3e-07 $6e-07 $0.0 4000 4000
c4ai-aya-expanse-8b cohere cohere $5e-07 $1.5e-06 $0.0 8000 4000
c4ai-aya-expanse-32b cohere cohere $5e-07 $1.5e-06 $0.0 128000 4000
databricks-meta-llama-3-1-70b-instruct meta-llama databricks $1.0000200000000001 $2.9999900000000004 $0.0 8000 N/A
databricks-meta-llama-3-1-405b-instruct meta-llama databricks $5.000030000000001 $15.000020000000001 $0.0 128000 N/A
databricks-mixtral-8x7b-instruct databricks databricks $0.5000100000000001 $1.0000200000000001 $0.0 32000 N/A
databricks-dbrx-instruct databricks databricks $0.7499800000000001 $2.25001 $0.0 32000 4000
Llama-3.2-11B-Vision-Instruct meta-llama deepinfra $5.5e-08 $5.5e-08 $0.0 128000 N/A
Llama-3.2-90B-Vision-Instruct meta-llama deepinfra $3.5e-07 $4e-07 $0.0 128000 N/A
Meta-Llama-3.1-405B-Instruct meta-llama deepinfra $1.79e-06 $1.79e-06 $0.0 32000 N/A
Meta-Llama-3.1-8B-Instruct meta-llama deepinfra $6e-08 $6e-08 $0.0 128000 N/A
Meta-Llama-3.1-70B-Instruct meta-llama deepinfra $3.5e-07 $4e-07 $0.0 128000 N/A
gemma-2-27b-it google deepinfra $2.7e-06 $2.7e-06 $0.0 4096 N/A
gemma-2-9b-it google deepinfra $6e-07 $6e-07 $0.0 4096 N/A
Mistral-7B-Instruct-v0.3 mistralai deepinfra $5.5e-08 $5.5e-08 $0.0 32768 N/A
Qwen2.5-72B-Instruct Qwen deepinfra $3.5e-07 $4e-07 $0.0 32768 N/A
llama-v3p1-405b-instruct meta-llama fireworks $3e-06 $3e-06 $0.0 131072 N/A
llama-v3p1-70b-instruct meta-llama fireworks $9e-07 $9e-07 $0.0 131072 N/A
llama-v3p1-8b-instruct meta-llama fireworks $2e-07 $2e-07 $0.0 131072 N/A
llama-v3p2-3b-instruct meta-llama fireworks $2e-07 $2e-07 $0.0 131072 N/A
mixtral-8x22b-instruct mistralai fireworks $9e-07 $9e-07 $0.0 65536 N/A
llama-v3p2-11b-vision-instruct meta-llama fireworks $2e-07 $2e-07 $0.0 131072 N/A
llama-v3p2-90b-vision-instruct meta-llama fireworks $9e-07 $9e-07 $0.0 131072 N/A
mixtral-8x7b-instruct-hf mistralai fireworks $5e-07 $5e-07 $0.0 32768 N/A
yi-large 01 fireworks $3e-06 $3e-06 $0.0 32768 N/A
llama-v3-70b-instruct-hf meta-llama fireworks $9e-07 $9e-07 $0.0 8192 N/A
llama-v3-70b-instruct meta-llama fireworks $9e-07 $9e-07 $0.0 8192 N/A
llama-v3-8b-instruct-hf meta-llama fireworks $2e-07 $2e-07 $0.0 8192 N/A
llama-v3-8b-instruct meta-llama fireworks $2e-07 $2e-07 $0.0 8192 N/A
phi-3-vision-128k-instruct microsoft fireworks $9e-07 $9e-07 $0.0 32064 N/A
mixtral-8x7b-instruct mistralai fireworks $5e-07 $5e-07 $0.0 32768 N/A
mythomax-l2-13b gryphe fireworks $2e-07 $2e-07 $0.0 4096 N/A
qwen2p5-72b-instruct qwen fireworks $9e-07 $9e-07 $0.0 32768 N/A
llama-v3p2-1b-instruct 01 fireworks $2e-07 $2e-07 $0.0 131072 N/A
gemini-1.0-pro gemini gemini $5e-07 $1.5e-06 $0.0 30720 2048
gemini-1.5-pro gemini gemini $3.5e-06 $1.05e-05 $0.0 128000 8192
gemini-1.5-flash gemini gemini $3.5e-07 $7e-07 $0.0 128000 8192
llama-3.1-70b-versatile meta-llama groq $5.9e-07 $7.9e-07 $0.0 131072 N/A
llama-3.1-8b-instant meta-llama groq $5e-08 $8e-08 $0.0 131072 N/A
llama3-70b-8192 meta-llama groq $5.9e-07 $7.9e-07 $0.0 8192 N/A
llama3-8b-8192 meta-llama groq $5e-08 $8e-08 $0.0 8192 N/A
mixtral-8x7b-32768 mistralai groq $2.4e-07 $2.4e-07 $0.0 32768 N/A
gemma-7b-it google groq $7e-08 $7e-08 $0.0 8192 N/A
gemma2-9b-it google groq $2e-07 $2e-07 $0.0 8192 N/A
llama3-groq-8b-8192-tool-use-preview groq groq $1.9e-07 $1.9e-07 $0.0 8192 N/A
llama-guard-3-8b meta-llama groq $2e-07 $2e-07 $0.0 8192 N/A
mistral-7b mistralai lepton $7e-08 $7e-08 $0.0 8192 N/A
mixtral-8x7b mistralai lepton $5e-07 $5e-07 $0.0 32768 N/A
qwen2-72b qwen lepton $8e-07 $8e-07 $0.0 128000 N/A
wizardlm-2-7b wizardlm lepton $7e-08 $7e-08 $0.0 32000 N/A
wizardlm-2-8x22b wizardlm lepton $1e-06 $1e-06 $0.0 64000 N/A
dolphin-mixtral-8x7b mistralai lepton $5e-07 $5e-07 $0.0 32000 N/A
moonshot-v1-8k moonshot moonshot $1.66e-06 $1.66e-06 $0.0 8000 N/A
moonshot-v1-32k moonshot moonshot $3.32e-06 $3.32e-06 $0.0 32000 N/A
moonshot-v1-128k moonshot moonshot $8.29e-06 $8.29e-06 $0.0 128000 N/A
hermes-2-pro-llama-3-8b hermes-llama octoai $1.5e-07 $1.5e-07 $0.0 8192 N/A
meta-llama-3-70b-instruct meta-llama octoai $9e-07 $9e-07 $0.0 8192 N/A
nous-hermes-2-mixtral-8x7b-dpo nous-hermes octoai $4.5e-07 $4.5e-07 $0.0 8192 N/A
mixtral-8x7b-instruct mixtral octoai $4.5e-07 $4.5e-07 $0.0 32768 N/A
gpt-3.5-turbo openai openai $3e-06 $6e-06 $0.0 16385 16385
gpt-4 openai openai $3e-05 $6e-05 $0.0 8192 8192
gpt-4-turbo openai openai $1e-05 $3e-05 $0.0 128000 4096
gpt-4o openai openai $2.5e-06 $1e-05 $0.0 128000 16384
gpt-4o-2024-05-13 openai openai $5e-06 $1.5e-05 $0.0 128000 4096
gpt-4o-2024-08-06 openai openai $2.5e-06 $1e-05 $0.0 128000 16384
gpt-4o-mini openai openai $1.5e-07 $6e-07 $0.0 128000 16385
gpt-4o-mini-2024-07-18 openai openai $1.5e-07 $6e-07 $0.0 128000 16385
o1-preview openai openai $1.5e-05 $6e-05 $0.0 128000 32768
o1-preview-2024-09-12 openai openai $1.5e-05 $6e-05 $0.0 128000 32768
o1-mini openai openai $3e-06 $1.2e-05 $0.0 128000 65536
o1-mini-2024-09-12 openai openai $3e-06 $1.2e-05 $0.0 128000 65536
llama-3.1-sonar-small-128k-online perplexity perplexity $2e-07 $2e-07 $0.005 127072 N/A
llama-3.1-sonar-large-128k-online perplexity perplexity $1e-06 $1e-06 $0.005 127072 N/A
llama-3.1-sonar-huge-128k-online perplexity perplexity $5e-06 $5e-06 $0.005 127072 N/A
llama-3.1-sonar-small-128k-chat perplexity perplexity $2e-07 $2e-07 $0.0 131072 N/A
llama-3.1-sonar-large-128k-chat perplexity perplexity $1e-06 $1e-06 $0.0 131072 N/A
llama-3.1-8b-instruct meta-llama perplexity $2e-07 $2e-07 $0.0 131072 N/A
llama-3.1-70b-instruct meta-llama perplexity $1e-06 $1e-06 $0.0 131072 N/A
Llama-3-8b-chat-hf meta-llama together $2e-07 $2e-07 $0.0 8192 N/A
Llama-3-70b-chat-hf meta-llama together $9e-07 $9e-07 $0.0 8192 N/A
Meta-Llama-3.1-8B-Instruct-Turbo meta-llama together $1.8e-07 $1.8e-07 $0.0 131072 N/A
Meta-Llama-3.1-70B-Instruct-Turbo meta-llama together $8.8e-07 $8.8e-07 $0.0 131072 N/A
Meta-Llama-3.1-405B-Instruct-Turbo meta-llama together $3.5e-06 $3.5e-06 $0.0 130815 N/A
Llama-3.2-3B-Instruct-Turbo meta-llama together $6e-08 $6e-08 $0.0 131072 N/A
Llama-3.2-11B-Vision-Instruct-Turbo meta-llama together $1.8e-07 $1.8e-07 $0.0 131072 N/A
Llama-3.2-90B-Vision-Instruct-Turbo meta-llama together $1.2e-06 $1.2e-06 $0.0 131072 N/A
Qwen2-72B-Instruct qwen together $9e-07 $9e-07 $0.0 32768 N/A
Qwen2.5-7B-Instruct-Turbo qwen together $3e-07 $5e-06 $0.0 32768 N/A
Qwen2.5-72B-Instruct-Turbo qwen together $1.2e-06 $1.2e-06 $0.0 32768 N/A
Mistral-7B-Instruct-v0.3 mistralai together $2e-07 $2e-07 $0.0 32768 N/A
Mixtral-8x7B-Instruct-v0.1 mistralai together $6e-07 $6e-07 $0.0 32768 N/A
Mixtral-8x22B-Instruct-v0.1 mistralai together $1.2e-06 $1.2e-06 $0.0 65536 N/A
gemma-2-9b-it google together $3e-07 $3e-07 $0.0 8192 N/A
gemma-2-27b-it google together $8e-07 $8e-07 $0.0 8192 N/A