Kimi K3.1 Pro
kimi-k3.1-pro
Context: 1.0M
Models
The live catalogue remains the authority for supported model IDs, modalities, locations and public availability. If the catalogue is temporarily unavailable, contact our team to discuss your requirements.
Unified access to every leading model family across multiple providers.
| Family | Modalities | Max context | Suppliers | Geo-filter |
|---|---|---|---|---|
| Chat & Completion Alibaba · Anthropic · CloudSigma +9 |
Chat & Completion | 2M | 12 | |
| Vision & Multimodal Alibaba · CloudSigma · Mistral AI |
Vision & Multimodal | 1.0M | 3 | |
| OCR & Documents CloudSigma · Mistral AI |
OCR & Documents | 33K | 2 | |
| Document Conversion CloudSigma |
Document Conversion | - | 1 | |
| Image Generation OpenAI |
Image Generation | - | 1 | |
| Embedding CloudSigma |
Embedding | - | 1 | |
| Reranking CloudSigma |
Reranking | - | 1 | |
| Text-to-Speech CloudSigma |
Text-to-Speech | - | 1 | |
| Transcription OpenAI |
Transcription | - | 1 | |
| Realtime Transcription OpenAI |
Realtime Audio | 33K | 1 | |
| Speaker Recognition CloudSigma |
Speaker Recognition | - | 1 | |
| Audio Understanding CloudSigma |
Audio Understanding | - | 1 | |
| Tools DeepSeek |
Tools | - | 1 |
Explore the live open source chat and completion models in the public catalogue.
kimi-k3.1-pro
Context: 1.0M
deepseek-v4.1-flash-1017
Context: 1.0M
glm-5.3
Context: 1.0M
qwen3-235b
Context: 256K
glm-5.3-flash
Context: 1.0M
minimax-m3
Context: 1M
deepseek-v4-pro
Context: 1.0M
hy3-preview
Context: 262K
minimax-m3.1-flash
Context: 1M
deepseek-v4-flash
Context: 1.0M
kimi-k3
Context: 1.0M
glm-4.7-flash
Context: -
kimi-k2.6
Context: 262K
glm-5.1
Context: 200K
mistral-small-4
Context: 131K
qwen3-30b-a3b
Context: 262K
qwen3-vl-30b-a3b-instruct
Context: -
qwen3.5-397b-a17b
Context: 262K
codestral
Context: 256K
gemini-2.5-pro
Context: 1M
qwen3.8-flash
Context: 1M
deepseek-r1-0528
Context: 164K
llama-3.1-8b-turbo
Context: 131K
qwen-3-32b
Context: 40K
gemma-3-27b
Context: 128K
gemma-4-31b
Context: 256K
qwen3.5-plus
Context: 1M
glm-4.5-air
Context: 128K
llama-3.3-70b
Context: 128K
deepseek-v4-flash-0731
Context: 1.0M
deepseek-v4-pro-0813
Context: 1.0M
glm-5.2
Context: 1.0M
llama-4-scout
Context: 320K
gpt-oss-120b
Context: 131K
hermes-4-405b
Context: 131K
kimi-k2.7-code
Context: 262K
muse-spark-open
Context: 1.0M
magistral-medium
Context: 40K
nemotron-3-nano
Context: 262K
nemotron-3-super-120b
Context: 262K
nemotron-3.5-lightning
Context: 1.0M
qwen3.8-27b
Context: 262K
reflection-beam-1.0
Context: 1.0M
mistral-medium
Context: 131K
qwen-72b
Context: 33K
deepseek-chat
Context: 64K
gemini-3.1-flash-lite
Context: 1M
The first Premium / Frontier and Open Source models in the live Chat & Completion catalogue. Scheduled rates are evaluated now in each schedule's timezone; models without a schedule show their standard catalogue rate.
Premium / Frontier
gpt-6-astra
Standard catalogue rate
$10.00 input / $50.00 output / MTok
No public time-based schedule is currently available for this model.
View pricing detailsOpen Source
kimi-k3.1-pro
Standard catalogue rate
$2.00 input / $10.00 output / MTok
No public time-based schedule is currently available for this model.
View pricing detailsApply supported access and routing controls to model requests.
Access supported OpenAI and Anthropic models through one CloudSigma service. Applications should handle terminal errors and follow the endpoint's retry guidance.
Use an EU-only key policy for supported models. Review inference, logging and storage boundaries for your workload.
Choose the model publishers available to each API key and apply supported access policies for your workload.
Use supported chat, vision, image, embedding, speech, transcription and reranking capabilities through their documented endpoints. Compatibility and billing units vary.
Use documented OpenAI-compatible chat, Anthropic-compatible Messages and native specialist interfaces. Check the supported endpoint and model matrix when migrating.
Review model and key usage and cost breakdowns. Set spending controls and discuss hard-budget enforcement scope during enterprise evaluation.
Configure an EU-only key policy and choose an eligible model. Routing uses the active provider geography catalogue and rejects requests where no permitted route is available.
Review permitted inference locations alongside logging and storage policies. Model availability is not a blanket compliance or end-to-end residency guarantee.
Explore access controls# EU-only chat request
curl https://taas.cloudsigma.com/v1/chat/completions \
-H "Authorization: Bearer $TAAS_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "auto",
"region": "EU",
"messages": [
{"role": "user", "content": "Summarise this contract."}
]
}'
# Inspect documented response metadata and request logs.
Use the same CloudSigma credentials and model identifiers across supported endpoints. Handle errors according to the endpoint documentation, including whether output has already started.
Your configured model access and supported regional restrictions continue to apply to each request.
Read the developer guide# Python — documented OpenAI-compatible chat
from openai import OpenAI
client = OpenAI(
api_key="your-taas-key",
base_url="https://taas.cloudsigma.com/v1"
)
# Handle errors according to the endpoint documentation
response = client.chat.completions.create(
model="auto",
messages=[{"role": "user",
"content": "Draft a privacy notice."}]
)
print(response.choices[0].message.content)
Explore the public catalogue, review endpoint compatibility and establish access, spending and location requirements.