80 callable models — 67 text across 10 vendors, plus 6 image and 7 video, with pricing, context and capabilities
The platform currently offers 80 callable models: 67 text chat models across 10 vendors, plus 6 image and 7 video generators. Text pricing is in USD per 1M tokens; images bill per image and video per second — see Image / video / music APIs.
Live data comes from the public catalog endpoint GET https://model.zsopc.com/api/v1/models/public. This page is synced per release; the online model plaza is authoritative.
Cached pricing needs no opt-in: when upstream usage reports cached_tokens, the gateway settles that portion of the input at the cached rate automatically — clients don't (and can't) enable it explicitly. Models without a cached figure bill all input at the Input price.
Limited-time promotion: the whole Anthropic Claude line is charged at 40% off (list price × 0.6) and the whole OpenAI GPT text line at 70% off (× 0.3), with cached rates discounted equally. The tables show list prices; actual billing always uses the discounted rate, for both API-key calls and in-platform conversations. Discounted models carry an "X% OFF" badge on the model plaza.
Billed per image through POST /v1/images/generations. See Image / video APIs.
Model ID
Name
Price
Endpoint
doubao-seedream-4-0-250828
Seedream 4.0
$0.029/image
/v1/images/generations (size ≥ 960²)
doubao-seedream-4-5-251128
Seedream 4.5
$0.037/image
/v1/images/generations (size ≥ 1920²)
doubao-seedream-5-0-260128
Seedream 5.0
$0.032/image
/v1/images/generations (size ≥ 1920²)
doubao-seedream-5-0-pro-260628
Seedream 5.0 Pro
$0.044 per image for output ≤ 2.36 MP, $0.088 above, plus $0.003 per input reference image
/v1/images/generations (size ≥ 960²)
grok-imagine-image
Grok Imagine (Image)
$0.07/image
/v1/images/generations
grok-imagine-image-quality
Grok Imagine (Quality)
$0.07/image
/v1/images/generations
nano-banana
Nano Banana (Gemini 2.5 Flash Image)
$0.039/image
/v1/images/generations
nano-banana-pro
Nano Banana Pro (Gemini 3 Pro Image)
$0.134/image
/v1/images/generations
nano-banana-2
Nano Banana 2 (Gemini 3.1 Flash Image)
$0.04/image
/v1/images/generations
Since 2026-07-08 the three nano entries are the only way in: the older ids gemini-2.5-flash-image, gemini-3-pro-image-preview, gemini-3.1-flash-image(-preview) and the tvod-nano-* family all keep working as aliases resolving onto the canonical entries above. The former chat / Gemini-native surface for gemini-3.1-flash-image has been retired — call /v1/images/generations instead.
Different models support different client SDKs, and the compatibility matrix is authoritative on what is actually reachable. The catalog's supported_protocols field (returned by GET /api/v1/models/public, the same source as the model plaza cards) reflects only the native / primary path; many models are additionally reachable on other protocols through gateway translation or an upstream channel (the response then carries an X-Protocol-Translation header), and those appear only in the matrix. Native paths as of June 2026:
OpenAI Chat (/v1/chat/completions) — 77 of 78 text models (only doubao-seed-translation-250915 is excluded), by far the widest coverage
Anthropic Messages (/v1/messages) — natively: all 9 Claude models plus 4 Gemini SKUs (gemini-2.5-flash-lite, gemini-2.5-flash-thinking, gemini-3-flash, gemini-3.1-pro-low). GPT-5.x and most third-party models are also reachable via upstream conversion or translation — see the matrix
OpenAI Responses (/v1/responses) — gpt-5.4 / gpt-5.5 (the primary path for Codex CLI) plus claude-opus-4-6, claude-opus-4-7, claude-opus-4-8, claude-sonnet-4-6 and claude-haiku-4-5-20251001
Gemini Native (/v1beta/...) — natively: gemini-2.5-flash, gemini-2.5-pro, gemini-3-flash-preview, gemini-3-pro-preview. Some other models are reachable via upstream conversion — see the matrix
For a model × protocol combination with no reachable channel, the gateway returns 503 no_channel_available (the model exists but has no channel on that protocol — not a 404); switch to a supported protocol.
The response looks like { "models": [...] }. Note that this endpoint returns every registered entry — including placeholder SKUs that aren't live yet and non-chat SKUs — so filter on the three fields below when consuming it from a script rather than looping over the whole list:
Field
Meaning
callable
false means a placeholder SKU (listed but not live); calling it returns model_not_found
endpoint_type
null means an ordinary chat model. images_generations, videos_generations, contents_generations_tasks, embeddings and similar mean the model uses its own dedicated endpoint and cannot be sent to /v1/chat/completions — see Image / video / music APIs
supported_protocols
the client protocols available for this model (see "Cross-vendor protocol support" above)
To take only the models you can send straight to /v1/chat/completions:
