Video Providers

Video Context MCP supports six AI providers for video analysis. You can configure all of them and the server will fall back automatically when one is unavailable or rate-limited.

Provider Comparison

Feature	Gemini 3.7 Flash	MiniMax-M3	Kimi K3	Qwen3.7 Plus/Flash	MiMo-V2.5	GLM-5.3-Flash
Price	Free tier	$0.30 / $1.20 (≤512K)	$0.60 / $3.00	$0.50 / $3.00	$0.40 / $2.00	$0.075 / $0.25 (promo)
Context window	1M tokens	1M tokens	256K tokens	1M tokens	256K tokens	1M tokens
Native video upload	Up to 2 GB	No — image-only	Up to 100 MB	No	No	No
Frame/image cap	n/a	100 images per request	n/a	2,048 (Plus) / 256 (Flash)	20 images per request	150 images per request
Large local files	Native upload	Always frame-based	Native upload up to 100 MB	S3 relay or frame fallback	S3 relay or frame fallback	S3 relay or frame fallback
Best for	Default free provider	Long-video understanding	Broadest native format support	1M-context paid fallback	Thinking-mode workflows	Cheap last-resort fallback

Tip

Prices are per 1M tokens (input / output) where shown. See Model Pricing for current list prices, cost examples, and media generation pricing.

Gemini 3.7 Flash — Default

The default provider. Free with no credit card required. Accepts files up to 2 GB natively. An excellent all-round provider with the largest context window.

Environment variable: GEMINI_API_KEY
Model selection: GEMINI_MODEL — gemini-3.7-flash (default) or gemini-3.6-flash (rollback)
Get API key →

MiniMax-M3

MiniMax-M3 is a paid, image-only provider built for long-video understanding. The server extracts keyframes and sends them as images, with support for up to 100 images per request and 10 MB per image. It is the second provider in the fallback chain and the strongest frame-based option for long videos.

Environment variable: MINIMAX_API_KEY
Optional timeout override: M3_REQUEST_TIMEOUT_MS
Get API key →

Kimi K3

Paid provider with the broadest native video format support. Accepts files up to 100 MB natively without S3 relay, which is why it now sits ahead of Qwen in the fallback chain.

Environment variable: MOONSHOT_API_KEY
Get API key →

Qwen3.7 Plus / Flash

Paid provider with a 1M-token context window. Supports up to 2,048 images per request (Plus) or 256 (Flash). Local files use base64 with a practical cap of about 10 MB unless you configure the S3 Relay.

Environment variable: DASHSCOPE_API_KEY
Model selection: QWEN_MODEL — qwen3.7-plus (default) or qwen3.7-flash
Optional endpoint override: QWEN_BASE_URL
Get API key →

MiMo-V2.5

Paid provider with Xiaomi’s thinking-mode support. Local files use base64 with a practical cap of about 10 MB unless you configure the S3 Relay.

Environment variable: MIMO_API_KEY
Get API key →

GLM-5.3-Flash

Paid provider and the current default GLM model (since v2.2.0): $0.075 input / $0.25 output per 1M tokens at the launch promo (ends 2026-09-09; then $0.15 / $0.50) — 16× cheaper than the previous GLM-5V-Turbo default. Z.AI’s first native multimodal GLM-5 model with a 1M-token context window. Uses base64 video encoding for local files (cap: ~12 MB); falls back to S3 relay or frame-based analysis for larger files. Supports up to 150 images per request and direct video URLs up to 200 MB. GLM sits at the end of the fallback chain because its legacy free tier is the most aggressively rate-limited.

Note

GLM-5.3-Flash cannot disable chain-of-thought (it defaults to max reasoning effort), so the server automatically sends reasoning_effort: 'low' on regular analysis calls to keep latency and output cost down.

Caution

GLM-5.3-Flash’s video parser is stricter than GLM-5V-Turbo’s: malformed MP4 containers (e.g. clips cut with ffmpeg -c copy) are rejected with error 1210. Re-encoding the file (-c:v libx264 -c:a aac) fixes it, and the runtime fallback chain serves the answer from the next provider automatically.

Environment variable: Z_AI_API_KEY
Model selection: GLM_MODEL — glm-5.3-flash (default), glm-5v-turbo (previous model), glm-4.6v (rollback), or glm-4.6v-flash (legacy free tier)
Get API key →

Fallback Chains

When a provider fails or its key is missing, the server automatically tries the next provider in priority order:

Default Provider	Fallback Order
Gemini (default)	Gemini → MiniMax-M3 → Kimi → Qwen → MiMo → GLM
MiniMax-M3	MiniMax-M3 → Gemini → Kimi → Qwen → MiMo → GLM
Kimi	Kimi → Gemini → MiniMax-M3 → Qwen → MiMo → GLM
Qwen	Qwen → Gemini → MiniMax-M3 → Kimi → MiMo → GLM
MiMo	MiMo → Gemini → MiniMax-M3 → Kimi → Qwen → GLM
GLM	GLM → Gemini → MiniMax-M3 → Kimi → Qwen → MiMo

Change the Default Provider

Set the VIDEO_MCP_DEFAULT_PROVIDER environment variable in your MCP config:

"VIDEO_MCP_DEFAULT_PROVIDER": "m3"

Valid values: gemini (default), m3, kimi, qwen, mimo, glm

Tip

To ensure the LLM respects your configured default provider, add the following to your Copilot instructions (.github/copilot-instructions.md) or AGENTS.md:

If VIDEO_MCP_DEFAULT_PROVIDER is set in the MCP config, respect that value as the default provider for video tools. Do not specify a provider parameter unless the user explicitly requests one. :::

Large Local Files

GLM, Qwen, and MiMo all have a ~10–12 MB base64 encoding limit for local files. Kimi accepts native upload up to 100 MB. MiniMax-M3 is image-only, so it always analyzes extracted frames and never counts as an upload-capable fallback. When a GLM, Qwen, or MiMo file exceeds the base64 limit:

1. The server first tries to fall back to an upload-capable provider (Gemini or Kimi) if available in the chain.
2. If that fails too, the server falls back to frame-based analysis (evenly-spaced keyframes) as a last resort.
3. For the best quality with large local files, configure the S3 Relay — GLM, Qwen, and MiMo will receive a presigned URL to the full video, bypassing the limit entirely.