Coding models

DeepSeek, Kimi, GLM and more — one OpenAI-compatible API.

Nine coding models served from one gateway. Point any OpenAI-compatible client at a single base URL, pick a model per request, and change providers by editing one line.

Catalog

9 models. 1M-token context on the flagship tier.

Served through Fireworks AI and Nebius AI Studio infrastructure.

NVIDIATier 1

Nemotron 3 Nano 30B A3B

nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B

Mixture-of-experts model, strong on reasoning traces.

Input / 1M$0.06
Output / 1M$0.24
Context128k tokens
From$2.00/mo
Nemotron 3 Nano 30B A3B API
GoogleTier 1

Gemma 3 27B

google/gemma-3-27b-it

Efficient open-weight model, strong on general instructions.

Input / 1M$0.10
Output / 1M$0.30
Context128k tokens
From$2.00/mo
Gemma 3 27B API
Z.aiTier 1

GLM 5.3 Flash

glm-5.3-flash

Fast tier-1 model with strong instruction following.

Input / 1M$0.15
Output / 1M$0.50
Context1M tokens
From$2.00/mo
GLM 5.3 Flash API
DeepSeekTier 1

DeepSeek V4.1 Flash

deepseek-v4p1-flash

Fastest and cheapest tier-1 workhorse. Good first opinion.

Input / 1M$0.22
Output / 1M$0.66
Context1M tokens
From$0.0000/mo
DeepSeek V4.1 Flash API
OpenAITier 2

GPT-OSS 120B

gpt-oss-120b

Open-weight 120B reasoning model, careful with math and code.

Input / 1M$0.15
Output / 1M$0.60
Context128k tokens
From$5.00/mo
GPT-OSS 120B API
MiniMaxTier 3

MiniMax M3

minmax-m3

Balanced frontier model, strong summarisation and synthesis.

Input / 1M$0.30
Output / 1M$1.20
Context1M tokens
From$15.00/mo
MiniMax M3 API
Z.aiTier 3

GLM 5.3

glm-5.3

Frontier GLM tier. Strong long-form writing and structure.

Input / 1M$1.40
Output / 1M$4.40
Context1M tokens
From$15.00/mo
GLM 5.3 API
DeepSeekTier 3

DeepSeek V4 Pro

deepseek-v4-pro

Frontier DeepSeek tier. Deepest analysis, slowest and priciest.

Input / 1M$1.75
Output / 1M$3.50
Context1M tokens
From$15.00/mo
DeepSeek V4 Pro API
Moonshot AITier 3

Kimi K3

kimi-k3

Long-context specialist, good at very large pasted context.

Input / 1M$3.00
Output / 1M$15.00
Context1M tokens
From$15.00/mo
Kimi K3 API

Plan access by model

Each plan includes models up to a usage tier. Requesting a model outside your plan returns HTTP 403 with the list of models you can use.

ModelFreeFreeStarter$2/moGo$5/moPro$15/mo
Nemotron 3 Nano 30B A3Bnvidia/NVIDIA-Nemotron-3-Nano-30B-A3B—IncludedIncludedIncluded
Gemma 3 27Bgoogle/gemma-3-27b-it—IncludedIncluded—
GLM 5.3 Flashglm-5.3-flash—IncludedIncludedIncluded
DeepSeek V4.1 Flashdeepseek-v4p1-flashIncludedIncludedIncludedIncluded
GPT-OSS 120Bgpt-oss-120b——IncludedIncluded
MiniMax M3minmax-m3———Included
GLM 5.3glm-5.3———Included
DeepSeek V4 Prodeepseek-v4-pro———Included
Kimi K3kimi-k3———Included