120BChat
paidGPT-OSS 120B
gpt-oss-120bLarge open-weight model with high throughput, built for production chat, agents, and batch completions.
In
$0.03Cache
-Out
$0.17Context 131,072 · ~500 T/s
Models API
One key. Many models. Two API formats.
Base host
models.dataspires.comUnified Models API
One API. Every model you need.
A single gateway for high-speed, long-context, and free models, compatible with both OpenAI and Anthropic API formats. Authenticate with your DataSpires API key, pick a model ID, and start generating. Usage is metered in tokens and settled from your wallet credits.
Models
9
Paid
6
Free
3
Public base URL
Point OpenAI or Anthropic clients at this host. Same afk_live_... key for both.
OpenAI Compatible
https://models.dataspires.com/v1Use with /chat/completions and /models
Anthropic Compatible
https://models.dataspires.comUse with /v1/messages
Available models
6 paid · 3 free · prices in $/M tokens from your wallet credits
27BChat
paidQwen 3.6 27B
qwen-3.6-27bMid-size Qwen with strong reasoning and multilingual chat at high tokens per second.
In
$0.28Cache
-Out
$1.99Context 131,072 · ~500 T/s
GLMLong context
paidGLM 4.7
glm-4.7Long-context GLM with cache-aware input pricing, strong for documents and multi-turn work.
In
$0.40Cache
$0.05Out
$1.75Context 202,752 · ~58 T/s
GLM1M context
paidGLM 5.2
glm-5.2Up to 1M context, suited for long documents, research corpora, and agent workloads.
In
$0.80Cache
$0.05Out
$2.30Context 1M · ~85 T/s
DeepSeekCode
paidDeepSeek 4 Pro
deepseek-4-proStrong coding and reasoning with 1M context and very low cache rates.
In
$0.43Cache
$0.003Out
$0.87Context 1M · ~114 T/s
ChatGeneral
paidNemotron 3 Super
nemotron-3-superCapable general chat model at competitive token rates for everyday product features.
In
$0.09Cache
-Out
$0.40Context 262K · ~61 T/s
FreeChat
freeLaguna
lagunaFree tier model with a wide context window, ideal for prototyping and light workloads.
In
FreeCache
FreeOut
FreeContext 262K · ~34 T/s
Free7B
freeQwen 7B
qwen-7bCompact free model for quick experiments, demos, and low-cost testing.
In
FreeCache
FreeOut
FreeContext 8,192
FreeHosted
freeGemma 4 E4B
gemma4-e4bDataSpires-hosted Gemma with free OpenAI-compatible access for development and evaluation.
In
FreeCache
FreeOut
FreeContext 8,192