Switching plans from opencode go to CommandCode GOAT
I saw the recently up-and-coming CommandCode GOAT — heard it’s even better value than opencode’s go plan, with more models supported and a bigger quota.
Checked the official table: deepseek-v4-flash-vision is at list price, and there’s a $60 quota.
After opencode go’s adjustment this month, DeepSeek models no longer get anywhere near a $60 quota — basically unusable.
I happen to be renewing opencode go tomorrow. Let me evaluate it — might just buy a month and try it out.
Main concerns:
- Privacy: is there zero data retention
- Is it compatible with paseo integration
- Is it compatible with CodexBar for aggregated usage viewing
Privacy
privacy: https://commandcode.ai/docs/resources/security
You have to buy goat, i.e. a plan of $10 or more, before they offer API access.
ZDR policy: https://commandcode.ai/docs/resources/zdr
The goat plan doesn’t guarantee zero data retention for all models — not as transparent as the Opencode Go plan on this point.
If you want ZDR (zero data retention), every request must carry an x-cmd-zdr: 1 header, and that can also be handled in the config.
Paseo integration ❌
Looked it up — Paseo doesn’t currently support CommandCode.
So I’ll keep using opencode to hook into GOAT’s API, and keep using opencode inside paseo.
Which is fine — saves me from configuring openviking, search mcp, and the rest.
So the crux is getting opencode hooked up to GOAT’s API calls.
As for API calls, CommandCode GOAT and above all support API access. ✅
CodexBar compatibility ✅
CodexBar is really something — you can view usage directly for all kinds of plans.
It supports CommandCode out of the box.
Configuring opencode to use the GOAT plan
Not complicated — two steps: store the key with /connect + declare the provider in opencode.json.
Step 1: Enter the API Key with /connect
Inside opencode, run:
/connect
Choose Other provider, enter the provider name goat, paste the API Key and hit Enter.
The key is stored in ~/.local/share/opencode/auth.json (permissions 600, readable only by the current user); opencode automatically sends it as Authorization: Bearer <key>, so you don’t need to put it in opencode.json — that keeps the secret out of git.
Step 2: Configure opencode.json
In the global config ~/.config/opencode/opencode.json (same for the project-level .opencode/opencode.json), add a goat provider:
{
"provider": {
"goat": {
"npm": "@ai-sdk/openai-compatible",
"name": "goat",
"options": {
"baseURL": "https://api.commandcode.ai/provider/v1"
},
"models": {
"deepseek/deepseek-v4-flash-vision-exp": {
"name": "deepseek-v4-flash-vision-exp",
"limit": {
"context": 1000000,
"output": 262144
}
},
"deepseek/deepseek-v4-flash":{
"name":"deepseek-v4-flash",
"limit":
{
"context": 1000000,
"output": 262144
}
},
"z-ai/glm-5.3-flash":{
"name":"glm-5.3-flash",
"limit":
{
"context": 1000000,
"output": 262144
}
}
}
}
}
}
Key points:
npmuses@ai-sdk/openai-compatible— CommandCode provides an OpenAI-compatible endpointbaseURLis the provider gateway address (not the model name)- The
modelskey is the full model ID on the API side,deepseek/deepseek-v4-flash-vision-exp; filllimitaccording to the context/output caps the plan gives you - After the change, restart opencode for it to take effect (config is only loaded at startup, no hot reload)
Optional: custom zdr request header
The goat plan officially requires every request to carry x-cmd-zdr: 1. opencode passes the provider’s options through to the @ai-sdk/openai-compatible constructor as-is, and that natively supports headers, so just write:
"options": {
"baseURL": "https://api.commandcode.ai/provider/v1",
"headers": {
"x-cmd-zdr": "1"
}
}
This header goes out with every request and doesn’t conflict with the key stored by /connect. Tested and confirmed working.
Verification
After restarting opencode, switch to goat/deepseek/deepseek-v4-flash-vision-exp via /models, send a message, and if it replies normally the whole setup is in place.
Turns out deepseek-v4-flash-vision-exp isn’t a ZDR upstream????
Well then, I’ll just turn off ZDR.
I don’t normally use the vision-exp model anyway.
Tested ds-v4-flash and glm-5.3-flash, both support ZDR.
So I’ll just import these three models to use.
GLM-5.3-flash in the commandcode goat plan gives a bigger quota than opencode Go.
Fleshing out the config
Right now I’m using Command Code’s GOAT plan inside opencode, and opencode doesn’t officially support this provider out of the box.
Which means the models in my OpenCode are hand-configured, and I only set up 3 of them earlier.
Now I want to configure all of them.
As for ZDR, I also need to run a full round of testing to see which models support ZDR.
And I need to delete the already-canceled opencode go plus a whole pile of leftover provider entries — from auth.json.
Cleaning up auth.json:
/Users/rhett/.local/share/opencode/auth.json — clean it up manually in sublime; there’s way too much junk from before.
Configure all available models
curl https://api.commandcode.ai/provider/v1/models > ~/Downloads/goat-models.json
Read all available models.
Need to extract them into usable config and add them to the goat provider in /Users/rhett/.config/opencode/opencode.json.
For ZDR detection, write a script that does something like
curl https://api.commandcode.ai/provider/v1/chat/completions \
-H "Authorization: Bearer <CMD_API_KEY>" \
-H "Content-Type: application/json" \
-H "x-cmd-zdr: 1" \
-d '{
"model": "deepseek/deepseek-v4-flash",
"messages": [{"role": "user", "content": "Write a haiku about race conditions."}]
}'
based on the official statement:
if a model has no ZDR-capable upstream the request fails with a
422(cmd_zdr_no_providers) rather than falling back to a non-ZDR provider.
Run through every model and see which endpoints return a 422 error — that tells you which models aren’t safe.
ZDR detection script
#!/bin/bash
# ZDR 支持检测脚本：遍历 goat-models.json 中所有模型，检测是否支持 ZDR
# 判定规则：带 x-cmd-zdr:1 请求返回 422 cmd_zdr_no_providers => 不支持 ZDR（不安全）
# 返回 200 => 支持 ZDR
# 用法: bash check-zdr.sh
set -u
API_KEY="user_5NNqepzcPpbuusKVXmAzV3mgSe5zmNpttPV9TTryCyzuT7PnmQhxn9HKZHHAwbT6zCzJvKEqNXPvquLeNa8g1u2x"
BASE_URL="https://api.commandcode.ai/provider/v1/chat/completions"
MODELS_FILE="$HOME/Downloads/goat-models.json"
OUT_FILE="$HOME/Downloads/zdr-result.txt"
# 读取所有模型 id
MODELS=()
while IFS= read -r line; do
MODELS+=("$line")
done < <(python3 -c "
import json
with open('$MODELS_FILE') as f:
data = json.load(f)
for m in data['data']:
print(m['id'])
")
echo "共 ${#MODELS[@]} 个模型，开始 ZDR 检测..." >&2
echo "共 ${#MODELS[@]} 个模型" > "$OUT_FILE"
SUPPORT=()
NOT_SUPPORT=()
for model in "${MODELS[@]}"; do
resp=$(curl -s -o /tmp/zdr-body.json -w "%{http_code}" \
"$BASE_URL" \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-H "x-cmd-zdr: 1" \
-d "{
\"model\": \"$model\",
\"messages\": [{\"role\": \"user\", \"content\": \"Say OK\"}],
\"max_tokens\": 8
}")
code=$resp
if [ "$code" = "200" ]; then
SUPPORT+=("$model")
echo "ZDR ✓ $model" | tee -a "$OUT_FILE"
elif [ "$code" = "422" ]; then
NOT_SUPPORT+=("$model")
echo "ZDR ✗ $model (422)" | tee -a "$OUT_FILE"
else
NOT_SUPPORT+=("$model")
echo "ZDR ? $model (HTTP $code) $(cat /tmp/zdr-body.json | head -c 120)" | tee -a "$OUT_FILE"
fi
sleep 0.2
done
echo "" >> "$OUT_FILE"
echo "===== 汇总 =====" >> "$OUT_FILE"
echo "支持 ZDR: ${#SUPPORT[@]} 个" >> "$OUT_FILE"
for m in "${SUPPORT[@]}"; do echo " ✓ $m" >> "$OUT_FILE"; done
echo "不支持/未知: ${#NOT_SUPPORT[@]} 个" >> "$OUT_FILE"
for m in "${NOT_SUPPORT[@]}"; do echo " ✗ $m" >> "$OUT_FILE"; done
echo "" >&2
echo "完成！结果写入: $OUT_FILE" >&2
ZDR detection results
共 61 个模型
ZDR ? claude-sonnet-5 (HTTP 400) {"error":{"message":"Model \"claude-sonnet-5\" must be called via /provider/v1/messages (Anthropic Messages shape).","ty
ZDR ? claude-sonnet-4-6 (HTTP 400) {"error":{"message":"Model \"claude-sonnet-4-6\" must be called via /provider/v1/messages (Anthropic Messages shape).","
ZDR ? claude-fable-5 (HTTP 400) {"error":{"message":"Model \"claude-fable-5\" must be called via /provider/v1/messages (Anthropic Messages shape).","typ
ZDR ? claude-opus-5 (HTTP 400) {"error":{"message":"Model \"claude-opus-5\" must be called via /provider/v1/messages (Anthropic Messages shape).","type
ZDR ? claude-opus-4-8 (HTTP 400) {"error":{"message":"Model \"claude-opus-4-8\" must be called via /provider/v1/messages (Anthropic Messages shape).","ty
ZDR ? claude-opus-4-7 (HTTP 400) {"error":{"message":"Model \"claude-opus-4-7\" must be called via /provider/v1/messages (Anthropic Messages shape).","ty
ZDR ? claude-haiku-4-5-20251001 (HTTP 400) {"error":{"message":"Model \"claude-haiku-4-5-20251001\" must be called via /provider/v1/messages (Anthropic Messages sh
ZDR ? gpt-5.6-sol (HTTP 400) {"error":{"message":"{\"error\":{\"message\":\"Invalid 'max_output_tokens': integer below minimum value. Expected a valu
ZDR ? gpt-5.6-terra (HTTP 403) {"error":{"message":"MODEL_NOT_IN_PLAN: GPT-5.6 Terra available in Pro and above plans or extra on demand usage","type":
ZDR ? gpt-5.6-luna (HTTP 403) {"error":{"message":"Authentication failed. Please check your credentials.","type":"permission_error"}}
ZDR ? gpt-5.5 (HTTP 403) {"error":{"message":"MODEL_NOT_IN_PLAN: GPT-5.5 available in Pro and above plans or extra on demand usage","type":"permi
ZDR ? gpt-5.4 (HTTP 403) {"error":{"message":"MODEL_NOT_IN_PLAN: GPT-5.4 available in Pro and above plans or extra on demand usage","type":"permi
ZDR ? gpt-5.3-codex (HTTP 403) {"error":{"message":"MODEL_NOT_IN_PLAN: GPT-5.3 Codex available in Pro and above plans or extra on demand usage","type":
ZDR ? gpt-5.4-mini (HTTP 403) {"error":{"message":"MODEL_NOT_IN_PLAN: GPT-5.4 Mini available in Pro and above plans or extra on demand usage","type":"
ZDR ✓ deepseek/deepseek-v4-pro
ZDR ✓ deepseek/deepseek-v4-flash
ZDR ✗ deepseek/deepseek-v4-flash-vision-exp (422)
ZDR ✓ deepseek/deepseek-v4-flash-fast
ZDR ✓ moonshotai/Kimi-K3
ZDR ✓ moonshotai/Kimi-K2.7-Code
ZDR ✓ moonshotai/Kimi-K2.7-Code-Highspeed
ZDR ✓ moonshotai/Kimi-K2.6
ZDR ✓ moonshotai/Kimi-K2.5
ZDR ✓ z-ai/glm-5.3-flash
ZDR ✓ zai-org/GLM-5.3
ZDR ✓ zai-org/GLM-5.2
ZDR ✓ zai-org/GLM-5.2-Fast
ZDR ✓ zai-org/GLM-5.1
ZDR ✓ zai-org/GLM-5
ZDR ✓ MiniMaxAI/MiniMax-M3
ZDR ✓ MiniMaxAI/MiniMax-M2.7
ZDR ✓ MiniMaxAI/MiniMax-M2.5
ZDR ✓ xiaomi/mimo-v2.5-pro
ZDR ✓ xiaomi/mimo-v2.5
ZDR ✓ Qwen/Qwen3.8-Max
ZDR ✓ Qwen/Qwen3.8-27B
ZDR ✗ Qwen/Qwen3.8-Flash (422)
ZDR ✓ Qwen/Qwen3.7-Max
ZDR ✓ Qwen/Qwen3.7-Plus
ZDR ✓ Qwen/Qwen3.7-Flash
ZDR ✓ Qwen/Qwen3.6-Max-Preview
ZDR ✓ Qwen/Qwen3.6-Plus
ZDR ✗ stepfun/Step-3.7-Flash (422)
ZDR ✓ stepfun/Step-3.5-Flash
ZDR ✓ tencent/hy3-paid
ZDR ✓ tencent/hy4-preview
ZDR ? google/gemini-3.7-flash (HTTP 403) {"error":{"message":"Authentication failed. Please check your credentials.","type":"permission_error"}}
ZDR ? google/gemini-3.6-flash (HTTP 403) {"error":{"message":"MODEL_NOT_IN_PLAN: Gemini 3.6 Flash available in Pro and above plans or extra on demand usage","typ
ZDR ? google/gemini-3.5-flash (HTTP 403) {"error":{"message":"MODEL_NOT_IN_PLAN: Gemini 3.5 Flash available in Pro and above plans or extra on demand usage","typ
ZDR ? google/gemini-3.5-flash-lite (HTTP 403) {"error":{"message":"MODEL_NOT_IN_PLAN: Gemini 3.5 Flash Lite available in Pro and above plans or extra on demand usage"
ZDR ? google/gemini-3.1-flash-lite (HTTP 403) {"error":{"message":"MODEL_NOT_IN_PLAN: Gemini 3.1 Flash Lite available in Pro and above plans or extra on demand usage"
ZDR ? sakana/fugu-ultra (HTTP 403) {"error":{"message":"MODEL_NOT_IN_PLAN: Fugu Ultra available in Provider and above plans or extra on demand usage","type
ZDR ✓ nvidia/nemotron-3-ultra-550b-a55b
ZDR ✓ thinkingmachines/inkling
ZDR ✓ thinkingmachines/inkling-small
ZDR ✗ poolside/laguna-s-2.1-free (422)
ZDR ? meta/muse-spark-1.1 (HTTP 403) {"error":{"message":"MODEL_NOT_IN_PLAN: Muse Spark 1.1 available in Pro and above plans or extra on demand usage","type"
ZDR ✗ meta/muse-spark-1.2 (422)
ZDR ✗ meta/muse-spark-1.2-contributor (422)
ZDR ✗ xai/grok-4.5 (422)
ZDR ✗ xai/grok-4.6 (422)
===== 汇总 =====
支持 ZDR: 32 个
✓ deepseek/deepseek-v4-pro
✓ deepseek/deepseek-v4-flash
✓ deepseek/deepseek-v4-flash-fast
✓ moonshotai/Kimi-K3
✓ moonshotai/Kimi-K2.7-Code
✓ moonshotai/Kimi-K2.7-Code-Highspeed
✓ moonshotai/Kimi-K2.6
✓ moonshotai/Kimi-K2.5
✓ z-ai/glm-5.3-flash
✓ zai-org/GLM-5.3
✓ zai-org/GLM-5.2
✓ zai-org/GLM-5.2-Fast
✓ zai-org/GLM-5.1
✓ zai-org/GLM-5
✓ MiniMaxAI/MiniMax-M3
✓ MiniMaxAI/MiniMax-M2.7
✓ MiniMaxAI/MiniMax-M2.5
✓ xiaomi/mimo-v2.5-pro
✓ xiaomi/mimo-v2.5
✓ Qwen/Qwen3.8-Max
✓ Qwen/Qwen3.8-27B
✓ Qwen/Qwen3.7-Max
✓ Qwen/Qwen3.7-Plus
✓ Qwen/Qwen3.7-Flash
✓ Qwen/Qwen3.6-Max-Preview
✓ Qwen/Qwen3.6-Plus
✓ stepfun/Step-3.5-Flash
✓ tencent/hy3-paid
✓ tencent/hy4-preview
✓ nvidia/nemotron-3-ultra-550b-a55b
✓ thinkingmachines/inkling
✓ thinkingmachines/inkling-small
不支持/未知: 29 个
✗ claude-sonnet-5
✗ claude-sonnet-4-6
✗ claude-fable-5
✗ claude-opus-5
✗ claude-opus-4-8
✗ claude-opus-4-7
✗ claude-haiku-4-5-20251001
✗ gpt-5.6-sol
✗ gpt-5.6-terra
✗ gpt-5.6-luna
✗ gpt-5.5
✗ gpt-5.4
✗ gpt-5.3-codex
✗ gpt-5.4-mini
✗ deepseek/deepseek-v4-flash-vision-exp
✗ Qwen/Qwen3.8-Flash
✗ stepfun/Step-3.7-Flash
✗ google/gemini-3.7-flash
✗ google/gemini-3.6-flash
✗ google/gemini-3.5-flash
✗ google/gemini-3.5-flash-lite
✗ google/gemini-3.1-flash-lite
✗ sakana/fugu-ultra
✗ poolside/laguna-s-2.1-free
✗ meta/muse-spark-1.1
✗ meta/muse-spark-1.2
✗ meta/muse-spark-1.2-contributor
✗ xai/grok-4.5
✗ xai/grok-4.6
Final config:
The final config, mainly the ‘provider’ section — I entered the ZDR-compatible ones and all of them separately, as two parts.
{
"$schema": "https://opencode.ai/config.json",
"permission": {
},
"mcp": {
},
"provider": {
"goat": {
"npm": "@ai-sdk/openai-compatible",
"name": "goat",
"options": {
"baseURL": "https://api.commandcode.ai/provider/v1",
"headers": {}
},
"models": {
"deepseek/deepseek-v4-pro": {
"name": "DeepSeek V4 Pro (latest)",
"limit": {
"context": 1000000,
"output": 262144
}
},
"deepseek/deepseek-v4-flash": {
"name": "DeepSeek V4 Flash (latest)",
"limit": {
"context": 1000000,
"output": 262144
}
},
"deepseek/deepseek-v4-flash-fast": {
"name": "DeepSeek V4 Flash Fast",
"limit": {
"context": 1000000,
"output": 262144
}
},
"moonshotai/Kimi-K3": {
"name": "Kimi K3",
"limit": {
"context": 1000000,
"output": 262144
}
},
"moonshotai/Kimi-K2.7-Code": {
"name": "Kimi K2.7 Code",
"limit": {
"context": 256000,
"output": 262144
}
},
"moonshotai/Kimi-K2.7-Code-Highspeed": {
"name": "Kimi K2.7 Code HighSpeed",
"limit": {
"context": 262000,
"output": 262144
}
},
"moonshotai/Kimi-K2.6": {
"name": "Kimi K2.6",
"limit": {
"context": 256000,
"output": 262144
}
},
"moonshotai/Kimi-K2.5": {
"name": "Kimi K2.5",
"limit": {
"context": 256000,
"output": 262144
}
},
"z-ai/glm-5.3-flash": {
"name": "GLM-5.3 Flash",
"limit": {
"context": 1048576,
"output": 262144
}
},
"zai-org/GLM-5.3": {
"name": "GLM-5.3",
"limit": {
"context": 1000000,
"output": 262144
}
},
"zai-org/GLM-5.2": {
"name": "GLM-5.2",
"limit": {
"context": 1000000,
"output": 262144
}
},
"zai-org/GLM-5.2-Fast": {
"name": "GLM-5.2 Fast",
"limit": {
"context": 1000000,
"output": 262144
}
},
"zai-org/GLM-5.1": {
"name": "GLM-5.1",
"limit": {
"context": 200000,
"output": 262144
}
},
"zai-org/GLM-5": {
"name": "GLM-5",
"limit": {
"context": 200000,
"output": 262144
}
},
"MiniMaxAI/MiniMax-M3": {
"name": "MiniMax M3",
"limit": {
"context": 1000000,
"output": 262144
}
},
"MiniMaxAI/MiniMax-M2.7": {
"name": "MiniMax M2.7",
"limit": {
"context": 200000,
"output": 262144
}
},
"MiniMaxAI/MiniMax-M2.5": {
"name": "MiniMax M2.5",
"limit": {
"context": 200000,
"output": 262144
}
},
"xiaomi/mimo-v2.5-pro": {
"name": "MiMo V2.5 Pro",
"limit": {
"context": 1000000,
"output": 262144
}
},
"xiaomi/mimo-v2.5": {
"name": "MiMo V2.5",
"limit": {
"context": 1000000,
"output": 262144
}
},
"Qwen/Qwen3.8-Max": {
"name": "Qwen 3.8 Max",
"limit": {
"context": 1000000,
"output": 262144
}
},
"Qwen/Qwen3.8-27B": {
"name": "Qwen 3.8 27B",
"limit": {
"context": 262144,
"output": 262144
}
},
"Qwen/Qwen3.7-Max": {
"name": "Qwen 3.7 Max",
"limit": {
"context": 1000000,
"output": 262144
}
},
"Qwen/Qwen3.7-Plus": {
"name": "Qwen 3.7 Plus",
"limit": {
"context": 1000000,
"output": 262144
}
},
"Qwen/Qwen3.7-Flash": {
"name": "Qwen 3.7 Flash",
"limit": {
"context": 1000000,
"output": 262144
}
},
"Qwen/Qwen3.6-Max-Preview": {
"name": "Qwen 3.6 Max Preview",
"limit": {
"context": 200000,
"output": 262144
}
},
"Qwen/Qwen3.6-Plus": {
"name": "Qwen 3.6 Plus",
"limit": {
"context": 200000,
"output": 262144
}
},
"stepfun/Step-3.5-Flash": {
"name": "Step 3.5 Flash",
"limit": {
"context": 1000000,
"output": 262144
}
},
"tencent/hy3-paid": {
"name": "Tencent Hy3",
"limit": {
"context": 262144,
"output": 262144
}
},
"tencent/hy4-preview": {
"name": "Tencent Hy4 Preview",
"limit": {
"context": 1048576,
"output": 262144
}
},
"nvidia/nemotron-3-ultra-550b-a55b": {
"name": "Nemotron 3 Ultra",
"limit": {
"context": 1000000,
"output": 262144
}
},
"thinkingmachines/inkling": {
"name": "Inkling",
"limit": {
"context": 256000,
"output": 262144
}
},
"thinkingmachines/inkling-small": {
"name": "Inkling Small",
"limit": {
"context": 1000000,
"output": 262144
}
},
"gpt-5.6-sol": {
"name": "GPT-5.6 Sol",
"limit": {
"context": 1050000,
"output": 262144
}
},
"deepseek/deepseek-v4-flash-vision-exp": {
"name": "DeepSeek V4 Flash Vision (exp)",
"limit": {
"context": 1000000,
"output": 262144
}
},
"Qwen/Qwen3.8-Flash": {
"name": "Qwen 3.8 Flash",
"limit": {
"context": 1000000,
"output": 262144
}
},
"stepfun/Step-3.7-Flash": {
"name": "Step 3.7 Flash",
"limit": {
"context": 256000,
"output": 262144
}
},
"poolside/laguna-s-2.1-free": {
"name": "Laguna S 2.1",
"limit": {
"context": 256000,
"output": 262144
}
},
"meta/muse-spark-1.2": {
"name": "Muse Spark 1.2",
"limit": {
"context": 1048576,
"output": 262144
}
},
"meta/muse-spark-1.2-contributor": {
"name": "Muse Spark 1.2 Contributor",
"limit": {
"context": 1048576,
"output": 262144
}
},
"xai/grok-4.5": {
"name": "Grok 4.5",
"limit": {
"context": 500000,
"output": 262144
}
},
"xai/grok-4.6": {
"name": "Grok 4.6",
"limit": {
"context": 500000,
"output": 262144
}
}
}
},
"goat-zdr": {
"npm": "@ai-sdk/openai-compatible",
"name": "goat-zdr",
"options": {
"baseURL": "https://api.commandcode.ai/provider/v1",
"headers": {
"x-cmd-zdr": "1"
}
},
"models": {
"deepseek/deepseek-v4-pro": {
"name": "DeepSeek V4 Pro (latest)",
"limit": {
"context": 1000000,
"output": 262144
}
},
"deepseek/deepseek-v4-flash": {
"name": "DeepSeek V4 Flash (latest)",
"limit": {
"context": 1000000,
"output": 262144
}
},
"deepseek/deepseek-v4-flash-fast": {
"name": "DeepSeek V4 Flash Fast",
"limit": {
"context": 1000000,
"output": 262144
}
},
"moonshotai/Kimi-K3": {
"name": "Kimi K3",
"limit": {
"context": 1000000,
"output": 262144
}
},
"moonshotai/Kimi-K2.7-Code": {
"name": "Kimi K2.7 Code",
"limit": {
"context": 256000,
"output": 262144
}
},
"moonshotai/Kimi-K2.7-Code-Highspeed": {
"name": "Kimi K2.7 Code HighSpeed",
"limit": {
"context": 262000,
"output": 262144
}
},
"moonshotai/Kimi-K2.6": {
"name": "Kimi K2.6",
"limit": {
"context": 256000,
"output": 262144
}
},
"moonshotai/Kimi-K2.5": {
"name": "Kimi K2.5",
"limit": {
"context": 256000,
"output": 262144
}
},
"z-ai/glm-5.3-flash": {
"name": "GLM-5.3 Flash",
"limit": {
"context": 1048576,
"output": 262144
}
},
"zai-org/GLM-5.3": {
"name": "GLM-5.3",
"limit": {
"context": 1000000,
"output": 262144
}
},
"zai-org/GLM-5.2": {
"name": "GLM-5.2",
"limit": {
"context": 1000000,
"output": 262144
}
},
"zai-org/GLM-5.2-Fast": {
"name": "GLM-5.2 Fast",
"limit": {
"context": 1000000,
"output": 262144
}
},
"zai-org/GLM-5.1": {
"name": "GLM-5.1",
"limit": {
"context": 200000,
"output": 262144
}
},
"zai-org/GLM-5": {
"name": "GLM-5",
"limit": {
"context": 200000,
"output": 262144
}
},
"MiniMaxAI/MiniMax-M3": {
"name": "MiniMax M3",
"limit": {
"context": 1000000,
"output": 262144
}
},
"MiniMaxAI/MiniMax-M2.7": {
"name": "MiniMax M2.7",
"limit": {
"context": 200000,
"output": 262144
}
},
"MiniMaxAI/MiniMax-M2.5": {
"name": "MiniMax M2.5",
"limit": {
"context": 200000,
"output": 262144
}
},
"xiaomi/mimo-v2.5-pro": {
"name": "MiMo V2.5 Pro",
"limit": {
"context": 1000000,
"output": 262144
}
},
"xiaomi/mimo-v2.5": {
"name": "MiMo V2.5",
"limit": {
"context": 1000000,
"output": 262144
}
},
"Qwen/Qwen3.8-Max": {
"name": "Qwen 3.8 Max",
"limit": {
"context": 1000000,
"output": 262144
}
},
"Qwen/Qwen3.8-27B": {
"name": "Qwen 3.8 27B",
"limit": {
"context": 262144,
"output": 262144
}
},
"Qwen/Qwen3.7-Max": {
"name": "Qwen 3.7 Max",
"limit": {
"context": 1000000,
"output": 262144
}
},
"Qwen/Qwen3.7-Plus": {
"name": "Qwen 3.7 Plus",
"limit": {
"context": 1000000,
"output": 262144
}
},
"Qwen/Qwen3.7-Flash": {
"name": "Qwen 3.7 Flash",
"limit": {
"context": 1000000,
"output": 262144
}
},
"Qwen/Qwen3.6-Max-Preview": {
"name": "Qwen 3.6 Max Preview",
"limit": {
"context": 200000,
"output": 262144
}
},
"Qwen/Qwen3.6-Plus": {
"name": "Qwen 3.6 Plus",
"limit": {
"context": 200000,
"output": 262144
}
},
"stepfun/Step-3.5-Flash": {
"name": "Step 3.5 Flash",
"limit": {
"context": 1000000,
"output": 262144
}
},
"tencent/hy3-paid": {
"name": "Tencent Hy3",
"limit": {
"context": 262144,
"output": 262144
}
},
"tencent/hy4-preview": {
"name": "Tencent Hy4 Preview",
"limit": {
"context": 1048576,
"output": 262144
}
},
"nvidia/nemotron-3-ultra-550b-a55b": {
"name": "Nemotron 3 Ultra",
"limit": {
"context": 1000000,
"output": 262144
}
},
"thinkingmachines/inkling": {
"name": "Inkling",
"limit": {
"context": 256000,
"output": 262144
}
},
"thinkingmachines/inkling-small": {
"name": "Inkling Small",
"limit": {
"context": 1000000,
"output": 262144
}
},
"gpt-5.6-sol": {
"name": "GPT-5.6 Sol",
"limit": {
"context": 1050000,
"output": 262144
}
}
}
}
},
"plugin": [
]
}