Model catalog
Models
| Model | API identifier | Input / 1M | Cache read / 1M | Cache write / 1M | Output / 1M | Features |
|---|---|---|---|---|---|---|
 Claude Fable 5.1Anthropic | claude-fable-5-1 | $10.00 | $0.25 | $12.50 5m$20.00 1h | $50.00 | DirectAutoSmart Caching |
| Claude Haiku 5.5AnthropicAbove 100K input tokens: 5× input/cache, 5× output | claude-haiku-5-5 | $0.10 | $0.01 | $0.125 5m$0.20 1h | $0.50 | DirectAutoSmart Caching |
| Claude Opus 5.5Anthropic | claude-opus-5-5 | $4.00 | $0.20 | $5.00 5m$8.00 1h | $20.00 | DirectAutoSmart Caching |
| Claude Sonnet 5.5Anthropic | claude-sonnet-5-5 | $2.00 | $0.20 | $2.50 5m$4.00 1h | $10.00 | DirectAutoSmart Caching |
 DeepSeek V4 ProDeepInfra | deepseek-ai/DeepSeek-V4-Pro | $1.30 | — | — | $2.60 | DirectAuto |
| DeepSeek V4.1 FlashDeepInfra | deepseek-ai/DeepSeek-V4.1-Flash | $0.14 | $0.0042 | $0.14 standard | $0.42 | DirectAutoSmart Caching |
| GLM 5.3DeepInfra | zai-org/GLM-5.3 | $1.20 | $0.12 | $1.20 standard | $4.00 | DirectAutoSmart Caching |
| GLM 5.3 FlashDeepInfra | zai-org/GLM-5.3-Flash | $0.075 | $0.015 | $0.075 standard | $0.25 | DirectAutoSmart Caching |
| MiMo V2.6 FlashDeepInfra | XiaomiMiMo/MiMo-V2.6-Flash | $0.14 | $0.003 | $0.14 standard | $0.28 | DirectAutoSmart Caching |
| MiMo V2.6 ProDeepInfra | XiaomiMiMo/MiMo-V2.6-Pro | $0.435 | $0.004 | $0.435 standard | $0.87 | DirectAutoSmart Caching |
 DeepSeek V4.1 Flash (Fireworks)Fireworks AI | accounts/fireworks/models/deepseek-v4p1-flash | $0.30 | $0.006 | $0.30 standard | $1.20 | DirectAutoSmart Caching |
| Qwen 3.8 MaxFireworks AI | accounts/fireworks/models/qwen3p8-max | $2.00 | $0.25 | $2.00 standard | $6.00 | DirectAutoSmart Caching |
 50% off · ends Dec 31, 2026Gemini 3.7 FlashGoogle | gemini-3.7-flash | $0.75 | — | — | $3.75 | DirectAuto |
| 50% off · ends Dec 31, 2026Gemini 3.8 FlashGoogle | gemini-3.8-flash | $0.75 | $0.075 | $0.75 standard | $3.75 | DirectAutoSmart Caching |
 Muse Spark 1.3Meta | muse-spark-1.3 | $1.25 | $0.15 | $1.25 standard | $4.25 | DirectAutoSmart Caching |
 GPT-6 AstraOpenAI | gpt-6-astra | $10.00 | $1.00 | $12.50 5m | $50.00 | DirectAutoSmart Caching |
| GPT-6 LunaOpenAIAbove 272K input tokens: 2× input/cache, 1.5× output | gpt-6-luna | $0.10 | $0.01 | $0.125 5m | $0.50 | DirectAutoSmart Caching |
| GPT-6 SolOpenAIAbove 272K input tokens: 2× input/cache, 1.5× output | gpt-6-sol | $2.00 | $0.20 | $2.50 5m | $10.00 | DirectAutoSmart Caching |
| GPT-6.1 SolOpenAIAbove 272K input tokens: 2× input/cache, 1.5× output | gpt-6.1-sol | $2.00 | $0.10 | $2.50 5m | $10.00 | DirectAutoSmart Caching |
 Grok 4.6xAI | grok-4.6 | $2.00 | $0.50 | $2.00 standard | $6.00 | DirectAutoSmart Caching |
| Grok 4.7xAIAbove 200K input tokens: 2× input/cache, 2× output | grok-4.7 | $2.00 | $0.50 | $2.00 standard | $6.00 | DirectAutoSmart Caching |
Cache prices show separate provider tariffs when available; “standard” means cache writes use the input rate, and a dash means Smart Caching is unavailable. Availability gates reflect the current backend deployment contract. Project provider, model, and price policies can narrow the list further; an authenticated GET /v1/models request is authoritative for a specific API key.