Explore model capabilities and official USD rates where verified. Review a fresh USDC quote before authorizing a live request.
Catalog specifications are a reference snapshot. Prices link to official sources; unverified rates are marked. Live USDC quotes are not connected in this preview.
glm-5.3Z.AI GLM-5.3 — latest-generation model with a 1M context window and up to 128k output tokens.
International API list rates. Cache storage and tool charges are separate.
glm-5.3-flashZ.AI GLM-5.3 Flash — efficient multimodal GLM with a 1M context window and up to 128k output tokens.
International API list rates. Cache storage and tool charges are separate.
glm-5.2Z.AI GLM-5.2 — model for long-horizon tasks with a 1M context window and up to 128k output tokens.
International API list rates. Cache storage and tool charges are separate.
glm-5.1Z.AI GLM-5.1 — flagship for long-horizon autonomous tasks (Opus 4.6-aligned); 200k context, 128k output.
International API list rates. Cache storage and tool charges are separate.
glm-5.0-turboZ.AI GLM-5-Turbo — deeply optimized for OpenClaw-style agent tasks; 200k context, 128k output.
Price not verified
This exact ID has no verified official USD price row; no price is inferred from GLM-5 or GLM-5-Turbo.
glm-5v-turboZ.AI GLM-5V-Turbo — multimodal coding model with text, image, and video input; 200k context, 128k output.
Price not verified
The model has official capability documentation, but its current USD tariff was not present in the official price table checked.
muse-spark-1.1Meta Muse Spark 1.1 — long-context agentic reasoning; 1,048,576-token context and 1M output verified. The archived route accepts text input only.
Standard mode; no long-context premium. Search grounding is billed separately.
muse-spark-1.2Meta Muse Spark 1.2 — long-context agentic reasoning; 1,048,576-token context and 1M output verified. The archived route accepts text input only.
Standard mode; no long-context premium. Search grounding is billed separately.
qwen3.8-maxAlibaba Qwen3.8 Max — multimodal flagship with text, image, and video input; 1M context.
Singapore international deployment, up to 1M input tokens. Standard list rates; cache, batch, and regional discounts excluded.
qwen3.7-maxAlibaba Qwen3.7 Max — strongest Qwen reasoning with built-in tools; 1M context.
Singapore international deployment, up to 1M input tokens. Standard list rates; cache, batch, and regional discounts excluded.
qwen3.7-plusAlibaba Qwen3.7 Plus — balanced multimodal performance and cost for large codebases; 1M context.
Singapore international list rates before promotions. Up to 256K input tokens: base rates; above 256K: higher tier. Cache discount excluded.
kimi-k3Moonshot AI Kimi K3 — multimodal model with text, image, and video input; 1M context for coding and deep reasoning.
Standard token rates. Cache writes are billed separately by TTL; the token calculator excludes writes, tools, and taxes.
kimi-k2.7Moonshot AI Kimi K2.7 — dedicated coding model, reliable long-context instruction following; 256k context.
Price not verified
Official pricing names kimi-k2.7-code. This exact catalog ID is not confirmed as an alias; no tariff is inferred.
kimi-k2.6Moonshot AI Kimi K2.6 — text and image input with thinking and non-thinking modes; 256k context.
Standard token rates. K2 access restrictions begin October 31; retirement is planned by December 2026. Taxes excluded.
kimi-k2.5Moonshot AI Kimi K2.5 — open-source SoTA in agents, code and visual understanding; 256k context.
Price not verified
This exact older version is absent from the current official pricing table. No current USD rate verified.
deepseek-v4-proDeepSeek V4 Pro — flagship reasoning model, thinking + non-thinking modes; 1M context, 384k output.
Peak rates. Off-peak is 50% lower. See official UTC schedule and Chinese public-holiday exceptions.
deepseek-v4-pro-0813DeepSeek V4 Pro (snapshot 0813) — pinned Pro release; 1M context, 384k output.
Official table identifies this version under API ID deepseek-v4-pro. Peak rates shown; off-peak is 50% lower.
deepseek-v4-flashDeepSeek V4 Flash — fast, cost-efficient V4 with thinking modes; 1M context, 384k output.
Accepted legacy alias now serves V4.1-Flash-1017. Peak rates shown; off-peak is 50% lower.
deepseek-v4.1-flashDeepSeek V4.1 Flash — fast, cost-efficient multimodal reasoning with text and image input; 1M context, 128k output.
Price not verified
Current API uses deepseek-flash for V4.1-Flash-1017. This exact version/ID mapping has no separately verified current tariff.
deepseek-v4-flash-0731DeepSeek V4 Flash (snapshot 0731) — pinned release of V4 Flash; 1M context, 384k output.
Price not verified
This retired version has no current first-party USD tariff verified. The legacy unversioned alias serves a newer model.
minimax-m3MiniMax M3 — native multimodal model with text, image, and video input; 1M context via MiniMax Sparse Attention.
Standard list rates before the displayed permanent 50% discount. Above 512K input tokens, rates double. Priority costs 1.5× standard.
minimax-m2.7MiniMax M2.7 — efficient coding and agent model; 200k context.
Price not verified
Older price references exist, but this exact model is absent from the current official pricing overview. Current USD tariff unverified.
hy3Tencent Hunyuan 3 — text model for general chat, coding, and reasoning; 1M context, 64k output.
Tencent TokenHub Singapore list rates. Model identifier hy3 is confirmed by the official model list.
hy4Tencent Hunyuan 4 — long-context text reasoning model; 1M context, 64k output.
Price not verified
Official model list and pricing use hy4-preview. This exact hy4 ID is not confirmed as an alias; no price is inferred.
grok-4.5xAI Grok 4.5 — multimodal model with text, image, and file input plus web/X search; 500k context.
Global standard rates; all token rates double at 200k input tokens. Regional endpoints and tools can add charges.
grok-4.6xAI Grok 4.6 — agentic coding and visual work with text, image, and file input; 500k context.
Global standard rates; all token rates double at 200k input tokens. Regional endpoints and tools can add charges.
gpt-5.5OpenAI GPT-5.5 — a new class of intelligence for coding and professional work; 1.05M context.
Standard API, global processing, input up to 272K tokens. Meter uses short-context input/output/cache-read rates; longer prompts use the separately listed rates. Tool charges and cache writes are additional.
gpt-6-astraOpenAI GPT-6 Astra — advanced reasoning model for complex professional work; 1.05M context, 128k output.
Standard API, global processing, input up to 272K tokens. Meter uses short-context input/output/cache-read rates; longer prompts use the separately listed rates. Tool charges and cache writes are additional.
gpt-5.6-solOpenAI GPT-5.6 Sol — frontier model for complex reasoning and coding; 1.05M context, 128k output.
Standard API, global processing, input up to 272K tokens. Meter uses short-context input/output/cache-read rates; longer prompts use the separately listed rates. Tool charges and cache writes are additional. Promotional rate is available at least through November 21, 2026.
gpt-5.6-terraOpenAI GPT-5.6 Terra — balances intelligence and cost (mini tier); 1.05M context.
Standard API, global processing, input up to 272K tokens. Meter uses short-context input/output/cache-read rates; longer prompts use the separately listed rates. Tool charges and cache writes are additional.
gpt-5.6-lunaOpenAI GPT-5.6 Luna — cost-sensitive, high-volume workloads (nano tier); 1.05M context.
Standard API, global processing, input up to 272K tokens. Meter uses short-context input/output/cache-read rates; longer prompts use the separately listed rates. Tool charges and cache writes are additional.
claude-fable-5.1Anthropic Claude Fable 5.1 — latest Fable tier for coding and agentic work; 1M context, 128k output.
Standard first-party Claude API, global routing. Meter excludes separate cache-write and server-tool charges; batch, fast-mode and regional rates differ.
claude-fable-5Anthropic Claude Fable 5 — newest Claude tier for coding and agentic work; 1M context, 128k output.
Standard first-party Claude API, global routing. Meter excludes separate cache-write and server-tool charges; batch, fast-mode and regional rates differ.
claude-opus-5Anthropic Claude Opus 5 — flagship Claude for frontier coding, reasoning and agents; 1M context, 128k output.
Standard first-party Claude API, global routing. Meter excludes separate cache-write and server-tool charges; batch, fast-mode and regional rates differ.
claude-opus-4.8Anthropic Claude Opus 4.8 — frontier coding and long-horizon agentic work; 1M context.
Standard first-party Claude API, global routing. Meter excludes separate cache-write and server-tool charges; batch, fast-mode and regional rates differ.
claude-opus-4.7Anthropic Claude Opus 4.7 — high-end coding and deep reasoning; 1M context.
Standard first-party Claude API, global routing. Meter excludes separate cache-write and server-tool charges; batch, fast-mode and regional rates differ.
claude-opus-4.6Anthropic Claude Opus 4.6 — balanced Opus-tier coding and analysis; 1M context.
Standard first-party Claude API, global routing. Meter excludes separate cache-write and server-tool charges; batch, fast-mode and regional rates differ.
claude-sonnet-5Anthropic Claude Sonnet 5 — fast, capable coding and everyday reasoning; 1M context.
Standard first-party Claude API, global routing. Meter excludes separate cache-write and server-tool charges; batch, fast-mode and regional rates differ.
claude-sonnet-4.6Anthropic Claude Sonnet 4.6 — fast all-round coding and chat; 1M context.
Standard first-party Claude API, global routing. Meter excludes separate cache-write and server-tool charges; batch, fast-mode and regional rates differ.
claude-haiku-4.5Anthropic Claude Haiku 4.5 — fastest Claude for lightweight, high-volume tasks; 200k context.
Standard first-party Claude API, global routing. Meter excludes separate cache-write and server-tool charges; batch, fast-mode and regional rates differ.
gpt-5.5-imageArchived image model specification.
Price not verified
No official API rate or documented official alias was found for this exact catalog ID. Published GPT Image prices have not been substituted.
gpt-5.6-luna-imageArchived image model specification.
Price not verified
No official API rate or documented official alias was found for this exact catalog ID. Published GPT Image prices have not been substituted.
gpt-5.6-sol-imageArchived image model specification.
Price not verified
No official API rate or documented official alias was found for this exact catalog ID. Published GPT Image prices have not been substituted.
gpt-5.6-terra-imageArchived image model specification.
Price not verified
No official API rate or documented official alias was found for this exact catalog ID. Published GPT Image prices have not been substituted.
grok-imagine-imageArchived image model specification.
Text prompts have no separate charge.
grok-imagine-image-2.0Archived image model specification.
Select the resolution and quality when estimating.
bge-small-enArchived embedding model specification.
Hosting-dependent
Open model weights. Hosting costs depend on the operator; no universal developer API list price.
bge-base-enArchived embedding model specification.
Hosting-dependent
Open model weights. Hosting costs depend on the operator; no universal developer API list price.
bge-large-enArchived embedding model specification.
Hosting-dependent
Open model weights. Hosting costs depend on the operator; no universal developer API list price.
bge-m3Archived embedding model specification.
Hosting-dependent
Open model weights. Hosting costs depend on the operator; no universal developer API list price.
embeddinggemma-300mArchived embedding model specification.
Hosting-dependent
Google documents this 300M open embedding model for deployment on your own hardware. No fixed first-party per-token API price is published here; hosting costs depend on deployment.
qwen3-embedding-0.6bArchived embedding model specification.
Hosting-dependent
Open weights for self-hosting. No official hosted API USD tariff verified for this exact model; infrastructure cost varies.
bge-reranker-baseArchived rerank model specification.
Hosting-dependent
Open model weights. Hosting costs depend on the operator; no universal developer API list price.
voyage-4-liteArchived embedding model specification.
Standard text embedding API input-token rate after any account-specific free allowance; batch pricing differs.
voyage-4Archived embedding model specification.
Standard text embedding API input-token rate after any account-specific free allowance; batch pricing differs.
voyage-4-largeArchived embedding model specification.
Standard text embedding API input-token rate after any account-specific free allowance; batch pricing differs.
voyage-code-4Archived embedding model specification.
Standard text embedding API input-token rate after any account-specific free allowance; batch pricing differs.
voyage-finance-2Archived embedding model specification.
Standard text embedding API input-token rate after any account-specific free allowance; batch pricing differs.
voyage-law-2Archived embedding model specification.
Standard text embedding API input-token rate after any account-specific free allowance; batch pricing differs.
voyage-rerank-3Archived rerank model specification.
Official standard API rate for rerank-3; catalog uses a vendor-prefixed label. Billed tokens equal query tokens times document count, plus all document tokens. Account allowances and batch discounts are excluded.
voyage-rerank-3-liteArchived rerank model specification.
Official standard API rate for rerank-3-lite; catalog uses a vendor-prefixed label. Billed tokens equal query tokens times document count, plus all document tokens. Account allowances and batch discounts are excluded.
voyage-rerank-2.5Archived rerank model specification.
Official standard API rate for rerank-2.5; catalog uses a vendor-prefixed label. Billed tokens equal query tokens times document count, plus all document tokens. Account allowances and batch discounts are excluded.
voyage-rerank-2.5-liteArchived rerank model specification.
Official standard API rate for rerank-2.5-lite; catalog uses a vendor-prefixed label. Billed tokens equal query tokens times document count, plus all document tokens. Account allowances and batch discounts are excluded.
glm-5.3-flashxAdditional chat specification preserved from the exported capability reference.
International API list rates. Cache storage and tool charges are separate.
grok-4.7Additional chat specification preserved from the exported capability reference.
Global standard rates; all token rates double at 200k input tokens. Regional endpoints and tools can add charges.
grok-imagine-videoAdditional video specification preserved from the exported capability reference.
Charges depend on input media and generated duration.
grok-imagine-video-1.5Additional video specification preserved from the exported capability reference.
Charges depend on input media and generated duration.
grok-voice-ttsAdditional text to speech specification preserved from the exported capability reference.
Catalog label for the xAI TTS service; the native endpoint selects voice_id rather than this model ID.
grok-voice-transcribe-1.0Additional speech to text specification preserved from the exported capability reference.
Price not verified
The current guide lists 2.0; pricing for version 1.0 was not confirmed.
grok-voice-transcribe-2.0Additional speech to text specification preserved from the exported capability reference.
Current transcription model confirmed in the official speech-to-text guide.
gpt-liveAdditional realtime specification preserved from the exported capability reference.
Price not verified
Official pricing identifies gpt-live-1; the catalog ID gpt-live has no confirmed official alias mapping. Duration-based pricing must not be substituted without that mapping.
jev-1.13Additional structured evaluation specification preserved from the exported capability reference.
Official version jev-1.13.0. Input only; output has no charge.
Try a different name, developer, or capability.