OpenRouter endpoint#
In this notebook we will use the OpenRouter infrastructure. You will see that also this method uses the OpenAI API and we change the base_url.
import os
import openai
openai.__version__
'2.43.0'
def prompt_openrouter(message:str, model="google/gemini-3.6-flash"):
"""A prompt helper function that sends a message to openrouter
and returns only the text response.
"""
import os
# convert message in the right format if necessary
if isinstance(message, str):
message = [{"role": "user", "content": message}]
# setup connection to the LLM
client = openai.OpenAI(
base_url = "https://openrouter.ai/api/v1",
api_key = os.environ.get('OPENROUTER_API_KEY')
)
response = client.chat.completions.create(
model=model,
messages=message
)
# extract answer
return response.choices[0].message.content
prompt_openrouter("Hi!")
'Hello! How can I help you today?'
Exercise#
List the models available in the openrouter endpoint and try them out by specifying them when calling prompt_openrouter().
client = openai.OpenAI()
client.base_url = "https://openrouter.ai/api/v1"
client.api_key = os.environ.get('OPENROUTER_API_KEY')
print("\n".join([model.id for model in client.models.list().data]))
inclusionai/ling-3.0-flash:free
poolside/laguna-s-2.1
poolside/laguna-s-2.1:free
google/gemini-3.6-flash
google/gemini-3.5-flash-lite
meituan/longcat-2.0
thinkingmachines/inkling
openrouter/auto-beta
moonshotai/kimi-k3
meta/muse-spark-1.1
kwaipilot/kat-coder-air-v2.5
kwaipilot/kat-coder-pro-v2.5
openai/gpt-5.6-luna-pro
openai/gpt-5.6-luna
openai/gpt-5.6-terra-pro
openai/gpt-5.6-terra
openai/gpt-5.6-sol-pro
openai/gpt-5.6-sol
x-ai/grok-4.5
~x-ai/grok-latest
aion-labs/aion-3.0-mini
aion-labs/aion-3.0
tencent/hy3
poolside/laguna-xs-2.1
poolside/laguna-xs-2.1:free
anthropic/claude-sonnet-5
google/gemini-3.1-flash-lite-image
nex-agi/nex-n2-mini
sakana/fugu-ultra
google/gemini-3.1-flash-image
google/gemini-3-pro-image
cohere/north-mini-code:free
z-ai/glm-5.2
openrouter/fusion
moonshotai/kimi-k2.7-code
~anthropic/claude-fable-latest
anthropic/claude-fable-5
nex-agi/nex-n2-pro
nvidia/nemotron-3.5-content-safety:free
nvidia/nemotron-3-ultra-550b-a55b
nvidia/nemotron-3-ultra-550b-a55b:free
qwen/qwen3.7-plus
minimax/minimax-m3
stepfun/step-3.7-flash
anthropic/claude-opus-4.8-fast
anthropic/claude-opus-4.8
qwen/qwen3.7-max
x-ai/grok-build-0.1
google/gemini-3.5-flash
anthropic/claude-opus-4.7-fast
perceptron/perceptron-mk1
inclusionai/ring-2.6-1t
google/gemini-3.1-flash-lite
openai/gpt-chat-latest
x-ai/grok-4.3
ibm-granite/granite-4.1-8b
mistralai/mistral-medium-3-5
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free
poolside/laguna-m.1
poolside/laguna-m.1:free
~anthropic/claude-haiku-latest
~openai/gpt-mini-latest
~google/gemini-pro-latest
~moonshotai/kimi-latest
~google/gemini-flash-latest
~anthropic/claude-sonnet-latest
~openai/gpt-latest
qwen/qwen3.5-plus-20260420
qwen/qwen3.6-flash
qwen/qwen3.6-35b-a3b
qwen/qwen3.6-max-preview
qwen/qwen3.6-27b
openai/gpt-5.5-pro
openai/gpt-5.5
deepseek/deepseek-v4-pro
deepseek/deepseek-v4-flash
inclusionai/ling-2.6-1t
tencent/hy3-preview
xiaomi/mimo-v2.5-pro
xiaomi/mimo-v2.5
openai/gpt-5.4-image-2
inclusionai/ling-2.6-flash
~anthropic/claude-opus-latest
openrouter/pareto-code
moonshotai/kimi-k2.6
anthropic/claude-opus-4.7
z-ai/glm-5.1
google/gemma-4-26b-a4b-it
google/gemma-4-26b-a4b-it:free
google/gemma-4-31b-it
google/gemma-4-31b-it:free
qwen/qwen3.6-plus
z-ai/glm-5v-turbo
arcee-ai/trinity-large-thinking
x-ai/grok-4.20-multi-agent
x-ai/grok-4.20
google/lyria-3-pro-preview
google/lyria-3-clip-preview
kwaipilot/kat-coder-pro-v2
rekaai/reka-edge
minimax/minimax-m2.7
openai/gpt-5.4-nano
openai/gpt-5.4-mini
mistralai/mistral-small-2603
z-ai/glm-5-turbo
nvidia/nemotron-3-super-120b-a12b
nvidia/nemotron-3-super-120b-a12b:free
bytedance-seed/seed-2.0-lite
qwen/qwen3.5-9b
openai/gpt-5.4-pro
openai/gpt-5.4
inception/mercury-2
openai/gpt-5.3-chat
google/gemini-3.1-flash-lite-preview
bytedance-seed/seed-2.0-mini
google/gemini-3.1-flash-image-preview
qwen/qwen3.5-35b-a3b
qwen/qwen3.5-27b
qwen/qwen3.5-122b-a10b
qwen/qwen3.5-flash-02-23
google/gemini-3.1-pro-preview-customtools
openai/gpt-5.3-codex
aion-labs/aion-2.0
google/gemini-3.1-pro-preview
anthropic/claude-sonnet-4.6
qwen/qwen3.5-plus-02-15
qwen/qwen3.5-397b-a17b
minimax/minimax-m2.5
z-ai/glm-5
qwen/qwen3-max-thinking
anthropic/claude-opus-4.6
qwen/qwen3-coder-next
openrouter/free
stepfun/step-3.5-flash
moonshotai/kimi-k2.5
upstage/solar-pro-3
minimax/minimax-m2-her
writer/palmyra-x5
openai/gpt-audio
openai/gpt-audio-mini
z-ai/glm-4.7-flash
openai/gpt-5.2-codex
bytedance-seed/seed-1.6-flash
bytedance-seed/seed-1.6
minimax/minimax-m2.1
z-ai/glm-4.7
google/gemini-3-flash-preview
nvidia/nemotron-3-nano-30b-a3b
nvidia/nemotron-3-nano-30b-a3b:free
openai/gpt-5.2-chat
openai/gpt-5.2-pro
openai/gpt-5.2
mistralai/devstral-2512
relace/relace-search
z-ai/glm-4.6v
openrouter/bodybuilder
openai/gpt-5.1-codex-max
amazon/nova-2-lite-v1
mistralai/ministral-14b-2512
mistralai/ministral-8b-2512
mistralai/ministral-3b-2512
mistralai/mistral-large-2512
deepseek/deepseek-v3.2
anthropic/claude-opus-4.5
allenai/olmo-3-32b-think
google/gemini-3-pro-image-preview
deepcogito/cogito-v2.1-671b
openai/gpt-5.1
openai/gpt-5.1-chat
openai/gpt-5.1-codex
openai/gpt-5.1-codex-mini
moonshotai/kimi-k2-thinking
amazon/nova-premier-v1
perplexity/sonar-pro-search
mistralai/voxtral-small-24b-2507
openai/gpt-oss-safeguard-20b
nvidia/nemotron-nano-12b-v2-vl:free
minimax/minimax-m2
qwen/qwen3-vl-32b-instruct
ibm-granite/granite-4.0-h-micro
openai/gpt-5-image-mini
anthropic/claude-haiku-4.5
qwen/qwen3-vl-8b-thinking
qwen/qwen3-vl-8b-instruct
openai/gpt-5-image
openai/o3-deep-research
openai/o4-mini-deep-research
google/gemini-2.5-flash-image
qwen/qwen3-vl-30b-a3b-thinking
qwen/qwen3-vl-30b-a3b-instruct
openai/gpt-5-pro
z-ai/glm-4.6
anthropic/claude-sonnet-4.5
deepseek/deepseek-v3.2-exp
thedrummer/cydonia-24b-v4.1
relace/relace-apply-3
qwen/qwen3-vl-235b-a22b-thinking
qwen/qwen3-vl-235b-a22b-instruct
qwen/qwen3-max
qwen/qwen3-coder-plus
openai/gpt-5-codex
deepseek/deepseek-v3.1-terminus
qwen/qwen3-coder-flash
qwen/qwen3-next-80b-a3b-thinking
qwen/qwen3-next-80b-a3b-instruct
qwen/qwen-plus-2025-07-28
qwen/qwen-plus-2025-07-28:thinking
nvidia/nemotron-nano-9b-v2:free
moonshotai/kimi-k2-0905
qwen/qwen3-30b-a3b-thinking-2507
nousresearch/hermes-4-70b
nousresearch/hermes-4-405b
deepseek/deepseek-chat-v3.1
mistralai/mistral-medium-3.1
z-ai/glm-4.5v
ai21/jamba-large-1.7
openai/gpt-5-chat
openai/gpt-5
openai/gpt-5-mini
openai/gpt-5-nano
openai/gpt-oss-120b
openai/gpt-oss-20b
openai/gpt-oss-20b:free
anthropic/claude-opus-4.1
mistralai/codestral-2508
qwen/qwen3-coder-30b-a3b-instruct
qwen/qwen3-30b-a3b-instruct-2507
z-ai/glm-4.5
z-ai/glm-4.5-air
qwen/qwen3-235b-a22b-thinking-2507
qwen/qwen3-coder
bytedance/ui-tars-1.5-7b
google/gemini-2.5-flash-lite
qwen/qwen3-235b-a22b-2507
moonshotai/kimi-k2
cognitivecomputations/dolphin-mistral-24b-venice-edition
tencent/hunyuan-a13b-instruct
morph/morph-v3-large
morph/morph-v3-fast
baidu/ernie-4.5-vl-424b-a47b
mistralai/mistral-small-3.2-24b-instruct
minimax/minimax-m1
google/gemini-2.5-flash
google/gemini-2.5-pro
openai/o3-pro
google/gemini-2.5-pro-preview
deepseek/deepseek-r1-0528
anthropic/claude-opus-4
anthropic/claude-sonnet-4
google/gemma-3n-e4b-it
mistralai/mistral-medium-3
google/gemini-2.5-pro-preview-05-06
arcee-ai/virtuoso-large
meta-llama/llama-guard-4-12b
qwen/qwen3-30b-a3b
qwen/qwen3-8b
qwen/qwen3-14b
qwen/qwen3-32b
qwen/qwen3-235b-a22b
openai/o4-mini-high
openai/o3
openai/o4-mini
openai/gpt-4.1
openai/gpt-4.1-mini
openai/gpt-4.1-nano
meta-llama/llama-4-maverick
meta-llama/llama-4-scout
deepseek/deepseek-chat-v3-0324
openai/o1-pro
mistralai/mistral-small-3.1-24b-instruct
google/gemma-3-4b-it
google/gemma-3-12b-it
cohere/command-a
openai/gpt-4o-mini-search-preview
openai/gpt-4o-search-preview
rekaai/reka-flash-3
google/gemma-3-27b-it
thedrummer/skyfall-36b-v2
perplexity/sonar-reasoning-pro
perplexity/sonar-pro
perplexity/sonar-deep-research
mistralai/mistral-saba
openai/o3-mini-high
aion-labs/aion-rp-llama-3.1-8b
qwen/qwen2.5-vl-72b-instruct
qwen/qwen-plus
openai/o3-mini
mistralai/mistral-small-24b-instruct-2501
perplexity/sonar
deepseek/deepseek-r1-distill-llama-70b
deepseek/deepseek-r1
minimax/minimax-01
microsoft/phi-4
deepseek/deepseek-chat
sao10k/l3.3-euryale-70b
openai/o1
cohere/command-r7b-12-2024
meta-llama/llama-3.3-70b-instruct
amazon/nova-lite-v1
amazon/nova-micro-v1
amazon/nova-pro-v1
openai/gpt-4o-2024-11-20
mistralai/mistral-large-2407
qwen/qwen-2.5-coder-32b-instruct
thedrummer/unslopnemo-12b
anthracite-org/magnum-v4-72b
qwen/qwen-2.5-7b-instruct
inflection/inflection-3-pi
inflection/inflection-3-productivity
thedrummer/rocinante-12b
meta-llama/llama-3.2-1b-instruct
meta-llama/llama-3.2-3b-instruct
qwen/qwen-2.5-72b-instruct
cohere/command-r-08-2024
cohere/command-r-plus-08-2024
sao10k/l3.1-euryale-70b
nousresearch/hermes-3-llama-3.1-70b
nousresearch/hermes-3-llama-3.1-405b
sao10k/l3-lunaris-8b
openai/gpt-4o-2024-08-06
meta-llama/llama-3.1-70b-instruct
meta-llama/llama-3.1-8b-instruct
mistralai/mistral-nemo
openai/gpt-4o-mini
openai/gpt-4o-mini-2024-07-18
google/gemma-2-27b-it
openai/gpt-4o
openai/gpt-4o-2024-05-13
mistralai/mixtral-8x22b-instruct
microsoft/wizardlm-2-8x22b
openai/gpt-4-turbo
anthropic/claude-3-haiku
mistralai/mistral-large
openai/gpt-3.5-turbo-0613
openai/gpt-4-turbo-preview
openrouter/auto
openai/gpt-3.5-turbo-instruct
openai/gpt-3.5-turbo-16k
mancer/weaver
undi95/remm-slerp-l2-13b
gryphe/mythomax-l2-13b
openai/gpt-3.5-turbo
openai/gpt-4