250+ AI coding models in your terminal

Darce works with every OpenRouter model that can drive a coding agent: tool calling, 64k+ context, current generation. Here are the popular ones.

Pick a model with /model (or Ctrl+P), start with one using darce --model <id>, and switch to a smarter or cheaper one mid-task with Shift+↑ / Shift+↓. One Darce plan covers them all; no provider keys needed. Prices below are OpenRouter's per-million-token rates, refreshed daily, and show relative cost: your Darce allowance is used in proportion to them. See how models work in Darce.

npx darce-cli                          # try it free, no account
darce --model qwen/qwen3-coder         # start with a specific model
/model sonnet                          # switch inside a session

Anthropic models

Model	Context	Input / output per 1M
Claude Opus 5.5 `anthropic/claude-opus-5.5`	1M tokens	$4.00 / $20.00
Claude Sonnet 5.5 `anthropic/claude-sonnet-5.5`	1M tokens	$2.00 / $10.00
Claude Haiku 5.5 `anthropic/claude-haiku-5.5`	1M tokens	$0.10 / $0.50
Claude Fable 5.1 `anthropic/claude-fable-5.1`	1M tokens	$10.00 / $50.00
Claude Opus 5 `anthropic/claude-opus-5`	1M tokens	$5.00 / $25.00
Claude Sonnet 4.5 `anthropic/claude-sonnet-4.5`	1M tokens	$3.00 / $15.00

OpenAI models

Model	Context	Input / output per 1M
GPT-6.1 Sol `openai/gpt-6.1-sol`	1.05M tokens	$2.00 / $10.00
GPT-6 Sol `openai/gpt-6-sol`	1.05M tokens	$2.00 / $10.00
GPT-6 Luna `openai/gpt-6-luna`	1.05M tokens	$0.10 / $0.50
GPT-6 Astra `openai/gpt-6-astra`	1.05M tokens	$10.00 / $50.00
GPT-5.6 Sol `openai/gpt-5.6-sol`	1.05M tokens	$2.00 / $10.00
GPT-5.5 `openai/gpt-5.5`	1.05M tokens	$5.00 / $30.00
GPT-5.3-Codex `openai/gpt-5.3-codex`	400k tokens	$1.75 / $14.00
gpt-oss-120b `openai/gpt-oss-120b`	131k tokens	$0.037 / $0.17

Google models

Model	Context	Input / output per 1M
Gemini 3.1 Pro Preview `google/gemini-3.1-pro-preview`	1.05M tokens	$2.00 / $12.00
Gemini 3.8 Flash `google/gemini-3.8-flash`	1.05M tokens	$0.75 / $3.75
Gemini 3.5 Flash Lite `google/gemini-3.5-flash-lite`	1.05M tokens	$0.30 / $2.50
Gemma 4 31B `google/gemma-4-31b-it`	262k tokens	$0.090 / $0.34

Qwen (Alibaba) models

Model	Context	Input / output per 1M
Qwen3 Coder 480B A35B `qwen/qwen3-coder`	262k tokens	$0.30 / $1.00
Qwen3 Coder Next `qwen/qwen3-coder-next`	262k tokens	$0.12 / $0.80
Qwen3 Coder Plus `qwen/qwen3-coder-plus`	1M tokens	$0.65 / $3.25
Qwen3 Coder Flash `qwen/qwen3-coder-flash`	1M tokens	$0.20 / $0.97
Qwen3 Coder 30B A3B Instruct `qwen/qwen3-coder-30b-a3b-instruct`	262k tokens	$0.070 / $0.28
Qwen3.8 Max (0902) `qwen/qwen3.8-max-0902`	1M tokens	$2.00 / $6.00
Qwen3.8 Flash `qwen/qwen3.8-flash`	1M tokens	$0.15 / $0.47

DeepSeek models

Model	Context	Input / output per 1M
DeepSeek V4 Pro 0423 `deepseek/deepseek-v4-pro`	1.05M tokens	$0.95 / $1.90
DeepSeek V4.1 Flash `deepseek/deepseek-v4.1-flash`	1.05M tokens	$0.30 / $1.20
DeepSeek V3.2 `deepseek/deepseek-v3.2`	164k tokens	$0.26 / $0.80

Moonshot AI models

Model	Context	Input / output per 1M
Kimi K3 `moonshotai/kimi-k3`	1.05M tokens	$0.64 / $13.50
Kimi K2.7 Code `moonshotai/kimi-k2.7-code`	262k tokens	$0.67 / $3.35
Kimi K2.6 `moonshotai/kimi-k2.6`	262k tokens	$0.47 / $2.45
Kimi K2 Thinking `moonshotai/kimi-k2-thinking`	262k tokens	$0.60 / $2.50

Z.ai models

Model	Context	Input / output per 1M
GLM 5.3 `z-ai/glm-5.3`	1.05M tokens	$0.039 / $4.80
GLM 5.3 Flash `z-ai/glm-5.3-flash`	1.05M tokens	$0.15 / $0.50
GLM 5.1 `z-ai/glm-5.1`	205k tokens	$0.97 / $3.04

xAI models

Model	Context	Input / output per 1M
Grok 4.7 `x-ai/grok-4.7`	500k tokens	$2.00 / $6.00
Grok Build 0.1 `x-ai/grok-build-0.1`	256k tokens	$1.00 / $2.00

MiniMax models

Model	Context	Input / output per 1M
MiniMax M3 `minimax/minimax-m3`	1.05M tokens	$0.30 / $1.20
MiniMax M2.7 `minimax/minimax-m2.7`	205k tokens	$0.21 / $0.84

Mistral AI models

Model	Context	Input / output per 1M
Devstral 2 2512 `mistralai/devstral-2512`	262k tokens	$0.40 / $2.00
Codestral 2508 `mistralai/codestral-2508`	256k tokens	$0.30 / $0.90
Mistral Large 4 `mistralai/mistral-large-4-0`	1.05M tokens	$0.68 / $2.09

Not listed here?

This page covers 42 popular coding models from 10vendors. Darce's picker lists 250+, ranked by OpenRouter's live popularity, and any other model works by its full id: darce --model vendor/model-name. Can't decide? Race three with /derby on your own task and keep the best diff.

Coming from Claude Code? See the open source Claude Code alternative. New to Darce? Start with getting started.

Model data from OpenRouter.

Try Darce in your terminal

Free to try, no account. Every change it makes can be undone with /undo.

$ npx darce-cli