Reference

Models catalog

Every public alias you can pass as the model field. Prices are quoted in USD per 1 million tokens, the same unit OpenAI, Anthropic and Google publish on their pricing pages. Relay billing meters at per-token resolution; amounts are shown in USD and your wallet is debited in USD-cents.

44 models live. You can also browse this list in the developer console.

deepseek-v

AliasModalityInput / 1M ($)Output / 1M ($)
deepseek-v4-flashπŸ’¬ Text$0.140$0.280
deepseek-v4-proπŸ’¬ Text$0.440$0.870

doubao

AliasModalityInput / 1M ($)Output / 1M ($)
doubao-1.5-lite-32kπŸ’¬ Text$0.040$0.080
doubao-1.5-pro-32kπŸ’¬ Text$0.110$0.280
doubao-1.5-pro-32k-characterπŸ’¬ Text$0.110$0.280
doubao-1.5-vision-proπŸ’¬ Text$0.420$1.25

doubao-embedding

AliasModalityInput / 1M ($)Output / 1M ($)
doubao-embedding-visionπŸ”’ Embeddings$0.100β€”

doubao-seed

AliasModalityInput / 1M ($)Output / 1M ($)
doubao-seed-1.6πŸ’¬ Text$0.110$1.11
doubao-seed-1.6-flashπŸ’¬ Text$0.020$0.210
doubao-seed-1.6-visionπŸ’¬ Text$0.110$1.13
doubao-seed-1.8πŸ’¬ Text$0.110$0.280
doubao-seed-2.0-codeπŸ’¬ Text$0.440$2.22
doubao-seed-2.0-liteπŸ’¬ Text$0.080$0.500
doubao-seed-2.0-miniπŸ’¬ Text$0.030$0.280
doubao-seed-2.0-proπŸ’¬ Text$0.440$2.22
doubao-seed-2.1-proπŸ’¬ Text$0.830$4.17
doubao-seed-2.1-turboπŸ’¬ Text$0.420$2.08
doubao-seed-characterπŸ’¬ Text$0.110$0.280
doubao-seed-codeπŸ’¬ Text$0.170$1.12
doubao-seed-evolvingπŸ’¬ Text$0.830$4.17
doubao-seed-translationπŸ’¬ Text$0.170$0.500

doubao-seedance

AliasModalityInput / 1M ($)Output / 1M ($)
doubao-seedance-1.0-pro🎬 Videoβ€”$2.08
doubao-seedance-1.0-pro-fast🎬 Videoβ€”$0.580
doubao-seedance-1.5-pro🎬 Videoβ€”$2.22
doubao-seedance-2-0-pro🎬 Videoβ€”$6.40
doubao-seedance-2.0-fast🎬 Videoβ€”$5.14

doubao-seedream

AliasModalityInput / 1M ($)Output / 1M ($)
doubao-seedream-4.0πŸ–Ό Imageβ€”β€”
doubao-seedream-4.5πŸ–Ό Imageβ€”β€”
doubao-seedream-5.0-liteπŸ–Ό Imageβ€”β€”

gpt

AliasModalityInput / 1M ($)Output / 1M ($)
gpt-4.1-miniπŸ’¬ Text$0.150$0.600
gpt-5.2πŸ’¬ Text$1.75$14.00
gpt-5.3-codexπŸ’¬ Text$1.75$14.00
gpt-5.3-codex-sparkπŸ’¬ Textβ€”β€”
gpt-5.4πŸ’¬ Text$2.50$15.00
gpt-5.4-miniπŸ’¬ Text$0.700$4.20
gpt-5.4-openai-compactπŸ’¬ Text$2.50$15.00
gpt-5.4-xhigh-fastπŸ’¬ Text$2.50$15.00
gpt-5.5πŸ’¬ Text$5.00$30.00
gpt-5.5-openai-compactπŸ’¬ Text$5.00$30.00
gpt-5.5-xhigh-fastπŸ’¬ Text$5.00$30.00

volc-deepseek

AliasModalityInput / 1M ($)Output / 1M ($)
volc-deepseek-v3.2πŸ’¬ Text$0.280$0.420
volc-deepseek-v4-flashπŸ’¬ Text$0.140$0.280
volc-deepseek-v4-proπŸ’¬ Text$1.67$3.33

volc-glm

AliasModalityInput / 1M ($)Output / 1M ($)
volc-glm-4.7πŸ’¬ Text$0.420$1.94

Routing & failover

You always pass the platform alias (e.g. gpt-5.2), never the upstream-specific id (e.g. openai/gpt-5.2). Behind the scenes:

  1. Each alias maps to one or more upstream routes ordered by priority.
  2. Each route consumes credentials from a per-provider pool. If a credential gets repeatedly rejected, it's cooled down for 60s and the next request picks a sibling.
  3. A single retryable upstream error (5xx, 401/403 token issues, 429 rate limit) triggers the relay to retry the next candidate automatically β€” your client only sees the final result.
  4. If every candidate is exhausted, you get an explicit 503 with a clear message instead of a stuck request.

See Common errors for what each status code means and how to react.