Market preview
DeepSeek: DeepSeek Pro Latest+27%DeepSeek V4 Flash Latest+16%DeepSeek: DeepSeek V4 Flash 0731+16%@cf/ai4bharat/indictrans2-en-indic-1B$0.342 / 1MV100$0.02/hr
United States
DeepInfra is an AI infrastructure startup based in Palo Alto, California, founded in 2022. It runs its own inference-optimized infrastructure in secure US-based data centers.
From the provider's own site · deepinfra.com ↗
API provider · 126 models tracked · Profile updated Oct 3, 2026 00:13 UTC
Models
Model identity is kept separate from provider-specific pricing and availability.
| Model | Creator | Access | Context | Data |
|---|---|---|---|---|
 Google: Gemini 3.7 FlashGoogle | Not listed | 1M | Sourcehttps://openrouter.ai/api/v1/models See where this value came from and when it was checked.
| |
| Google: Gemini 3.1 Flash LiteGoogle | Not listed | 1M | Sourcehttps://openrouter.ai/api/v1/models See where this value came from and when it was checked.
| |
 Qwen: Qwen3.6 35B A3BQwen | Qwen | Not listed | 262.1K | Sourcehttps://openrouter.ai/api/v1/models See where this value came from and when it was checked.
|
| Qwen: Qwen3.6 27BQwen | Qwen | Not listed | 262.1K | Sourcehttps://openrouter.ai/api/v1/models See where this value came from and when it was checked.
|
 DeepSeek: DeepSeek V4 Pro 0423DeepSeek | DeepSeek | Not listed | 1M | Sourcehttps://openrouter.ai/api/v1/models See where this value came from and when it was checked.
|
| DeepSeek: DeepSeek V4 Flash 0423DeepSeek | DeepSeek | Not listed | 1M | Sourcehttps://openrouter.ai/api/v1/models See where this value came from and when it was checked.
|
| Qwen: Qwen3.8 2.4T A95BQwen | Qwen | Not listed | 1M | Sourcehttps://openrouter.ai/api/v1/models See where this value came from and when it was checked.
|
 MoonshotAI: Kimi K2.6Moonshotai | Moonshotai | Not listed | 262.1K | Sourcehttps://openrouter.ai/api/v1/models See where this value came from and when it was checked.
|
 Anthropic: Claude Opus 4.7Anthropic | Anthropic | Not listed | 1M | Sourcehttps://openrouter.ai/api/v1/models See where this value came from and when it was checked.
|
 Z.ai: GLM 5.1Z.ai (GLM) | Z.ai (GLM) | Not listed | 202.8K | Sourcehttps://openrouter.ai/api/v1/models See where this value came from and when it was checked.
|
| Google: Gemma 4 26B A4B Google | Not listed | 262.1K | Sourcehttps://openrouter.ai/api/v1/models See where this value came from and when it was checked.
| |
| Google: Gemma 4 31BGoogle | Not listed | 262.1K | Sourcehttps://openrouter.ai/api/v1/models See where this value came from and when it was checked.
| |
 ibm-granite/granite-4.2-3bIbm Granite | Ibm Granite | Not listed | Not published | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| ibm-granite/granite-4.2-8bIbm Granite | Ibm Granite | Not listed | Not published | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| ibm-granite/granite-4.2-30bIbm Granite | Ibm Granite | Not listed | Not published | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| Z.ai: GLM 5.3 FlashZ.ai (GLM) | Z.ai (GLM) | Not listed | 1M | Sourcehttps://developers.cloudflare.com/workers-ai/platform/pricing/ See where this value came from and when it was checked.
|
| Qwen: Qwen3.8 FlashQwen | Qwen | Not listed | 1M | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
 Tencent: Hy4 previewTencent | Tencent | Not listed | 1M | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| DeepSeek: DeepSeek V4 Pro 0813DeepSeek | DeepSeek | Not listed | 1M | Sourcehttps://openrouter.ai/api/v1/models See where this value came from and when it was checked.
|
 Ling 3.0 Flash FinInclusionai | Inclusionai | Not listed | 262.1K | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| inclusionAI/Ling-3.0-flash-VLInclusionai | Inclusionai | Not listed | Not published | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| DeepSeek: DeepSeek V4.1 FlashDeepSeek | DeepSeek | Not listed | 1M | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| XiaomiMiMo/MiMo-V2.6-Flash-RLXiaomimimo | Xiaomimimo | Not listed | Not published | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| XiaomiMiMo/MiMo-V2.6-FlashXiaomimimo | Xiaomimimo | Not listed | Not published | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| XiaomiMiMo/MiMo-V2.6-ProXiaomimimo | Xiaomimimo | Not listed | Not published | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| Anthropic: Claude Opus 5.5Anthropic | Anthropic | Not listed | 1M | Sourcehttps://docs.anthropic.com/en/docs/about-claude/pricing See where this value came from and when it was checked.
|
| Anthropic: Claude Sonnet 5.5Anthropic | Anthropic | Not listed | 1M | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| deepseek-ai/DeepSeek-V4.1-Flash-TurboDeepseek Ai | Deepseek Ai | Not listed | Not published | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
 MiniMax: MiniMax M2.7Minimax | Minimax | Not listed | 204.8K | Sourcehttps://openrouter.ai/api/v1/models See where this value came from and when it was checked.
|
| Qwen: Qwen3.5-9BQwen | Qwen | Not listed | 262.1K | Sourcehttps://openrouter.ai/api/v1/models See where this value came from and when it was checked.
|
| Qwen: Qwen3.5-35B-A3BQwen | Qwen | Not listed | 262.1K | Sourcehttps://openrouter.ai/api/v1/models See where this value came from and when it was checked.
|
| Qwen: Qwen3.5-27BQwen | Qwen | Not listed | 262.1K | Sourcehttps://openrouter.ai/api/v1/models See where this value came from and when it was checked.
|
| Qwen: Qwen3.5-122B-A10BQwen | Qwen | Not listed | 262.1K | Sourcehttps://openrouter.ai/api/v1/models See where this value came from and when it was checked.
|
| Anthropic: Claude Sonnet 4.6Anthropic | Anthropic | Not listed | 1M | Sourcehttps://openrouter.ai/api/v1/models See where this value came from and when it was checked.
|
| Qwen: Qwen3.5 397B A17BQwen | Qwen | Not listed | 262.1K | Sourcehttps://openrouter.ai/api/v1/models See where this value came from and when it was checked.
|
| Z.ai: GLM 5Z.ai (GLM) | Z.ai (GLM) | Not listed | 198K | Sourcehttps://openrouter.ai/api/v1/models See where this value came from and when it was checked.
|
| Qwen: Qwen3 Max ThinkingQwen | Qwen | Not listed | 262.1K | Sourcehttps://openrouter.ai/api/v1/models See where this value came from and when it was checked.
|
| MoonshotAI: Kimi K2.5Moonshotai | Moonshotai | Not listed | 262.1K | Sourcehttps://openrouter.ai/api/v1/models See where this value came from and when it was checked.
|
| DeepSeek: DeepSeek V4 Flash Vision ExpDeepSeek | DeepSeek | Not listed | 1M | Sourcehttps://openrouter.ai/api/v1/models See where this value came from and when it was checked.
|
| Z.ai: GLM 4.7 FlashZ.ai (GLM) | Z.ai (GLM) | Not listed | 202.8K | Sourcehttps://openrouter.ai/api/v1/models See where this value came from and when it was checked.
|
| Z.ai: GLM 4.7Z.ai (GLM) | Z.ai (GLM) | Not listed | 202.8K | Sourcehttps://openrouter.ai/api/v1/models See where this value came from and when it was checked.
|
| NVIDIA | Not listed | 262.1K | Sourcehttps://openrouter.ai/api/v1/models See where this value came from and when it was checked.
|
| DeepSeek: DeepSeek V3.2DeepSeek | DeepSeek | Not listed | 163.8K | Sourcehttps://openrouter.ai/api/v1/models See where this value came from and when it was checked.
|
| Qwen: Qwen3.8 MaxQwen | Qwen | Not listed | 1M | Sourcehttps://openrouter.ai/api/v1/models See where this value came from and when it was checked.
|
| Anthropic: Claude Haiku 4.5Anthropic | Anthropic | Not listed | 200K | Sourcehttps://openrouter.ai/api/v1/models See where this value came from and when it was checked.
|
| Qwen: Qwen3 VL 30B A3B InstructQwen | Qwen | Not listed | 131.1K | Sourcehttps://openrouter.ai/api/v1/models See where this value came from and when it was checked.
|
| Z.ai: GLM 4.6Z.ai (GLM) | Z.ai (GLM) | Not listed | 202.8K | Sourcehttps://openrouter.ai/api/v1/models See where this value came from and when it was checked.
|
| DeepSeek: DeepSeek V4 Flash 0731DeepSeek | DeepSeek | Not listed | 1M | Sourcehttps://openrouter.ai/api/v1/models See where this value came from and when it was checked.
|
| Qwen: Qwen3 VL 235B A22B InstructQwen | Qwen | Not listed | 131.1K | Sourcehttps://openrouter.ai/api/v1/models See where this value came from and when it was checked.
|
| Qwen: Qwen3 MaxQwen | Qwen | Not listed | 262.1K | Sourcehttps://openrouter.ai/api/v1/models See where this value came from and when it was checked.
|
Pricing
Rates this provider publishes for the models it serves. A rate nobody published is left absent, never shown as zero.
| Model | Input | Output | Cached | Batch input | Observed | Evidence |
|---|---|---|---|---|---|---|
| Google: Gemini 3.7 FlashGoogle | $0.75/ 1M | $3.75/ 1M | Not published | Not published | Aug 23, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| Google: Gemini 3.1 Flash LiteGoogle | $0.25/ 1M | $1.5/ 1M | Not published | Not published | Aug 23, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| Qwen: Qwen3.6 35B A3BQwen | $0.1/ 1M | $0.95/ 1M | $0.1 | Not published | Oct 2, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| Qwen: Qwen3.6 27BQwen | $0.32/ 1M | $3.2/ 1M | Not published | Not published | Aug 23, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| DeepSeek: DeepSeek V4 Pro 0423DeepSeek | $1.3/ 1M | $2.6/ 1M | $0.1 | Not published | Aug 23, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| DeepSeek: DeepSeek V4 Flash 0423DeepSeek | $0.09/ 1M | $0.18/ 1M | $0.018 | Not published | Aug 23, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| Qwen: Qwen3.8 2.4T A95BQwen | $2/ 1M | $6/ 1M | $0.2 | Not published | Aug 23, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| MoonshotAI: Kimi K2.6Moonshotai | $0.75/ 1M | $3.5/ 1M | $0.15 | Not published | Aug 23, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| Anthropic: Claude Opus 4.7Anthropic | $5/ 1M | $25/ 1M | Not published | Not published | Aug 26, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| Z.ai: GLM 5.1Z.ai (GLM) | $1.05/ 1M | $3.5/ 1M | $0.205 | Not published | Aug 26, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| Google: Gemma 4 26B A4B Google | $0.07/ 1M | $0.34/ 1M | Not published | Not published | Aug 23, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| Google: Gemma 4 31BGoogle | $0.15/ 1M | $0.4/ 1M | Not published | Not published | Oct 2, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| ibm-granite/granite-4.2-3bIbm Granite | $0.03/ 1M | $0.12/ 1M | $0.0075 | Not published | Aug 26, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| ibm-granite/granite-4.2-8bIbm Granite | $0.06/ 1M | $0.25/ 1M | $0.015 | Not published | Aug 26, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| ibm-granite/granite-4.2-30bIbm Granite | $0.16/ 1M | $0.65/ 1M | $0.04 | Not published | Aug 26, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| Z.ai: GLM 5.3 FlashZ.ai (GLM) | $0.15/ 1M | $0.5/ 1M | $0.03 | Not published | Aug 26, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| Qwen: Qwen3.8 FlashQwen | $0.113/ 1M | $0.382/ 1M | $0.014 | Not published | Sep 14, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| Tencent: Hy4 previewTencent | $0.834/ 1M | $2.501/ 1M | $0.042 | Not published | Sep 25, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| DeepSeek: DeepSeek V4 Pro 0813DeepSeek | $1.3/ 1M | $2.6/ 1M | $0.1 | Not published | Aug 23, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| Ling 3.0 Flash FinInclusionai | $0.06/ 1M | $0.18/ 1M | $0.012 | Not published | Sep 3, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| inclusionAI/Ling-3.0-flash-VLInclusionai | $0.06/ 1M | $0.18/ 1M | $0.012 | Not published | Sep 8, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| DeepSeek: DeepSeek V4.1 FlashDeepSeek | $0.2/ 1M | $0.6/ 1M | $0.006 | Not published | Sep 11, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| XiaomiMiMo/MiMo-V2.6-Flash-RLXiaomimimo | $0.14/ 1M | $0.28/ 1M | $0.0028 | Not published | Sep 22, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| XiaomiMiMo/MiMo-V2.6-FlashXiaomimimo | $0.14/ 1M | $0.28/ 1M | $0.0028 | Not published | Sep 30, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| XiaomiMiMo/MiMo-V2.6-ProXiaomimimo | $0.43/ 1M | $0.87/ 1M | $0.0036 | Not published | Sep 27, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| Anthropic: Claude Opus 5.5Anthropic | $4/ 1M | $20/ 1M | $0.2 | Not published | Sep 23, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| Anthropic: Claude Sonnet 5.5Anthropic | $2/ 1M | $10/ 1M | Not published | Not published | Sep 30, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| deepseek-ai/DeepSeek-V4.1-Flash-TurboDeepseek Ai | $0.3/ 1M | $1.2/ 1M | $0.006 | Not published | Oct 3, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| MiniMax: MiniMax M2.7Minimax | $0.25/ 1M | $1/ 1M | $0.05 | Not published | Aug 26, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| Qwen: Qwen3.5-9BQwen | $0.1/ 1M | $0.15/ 1M | Not published | Not published | Aug 23, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| Qwen: Qwen3.5-35B-A3BQwen | $0.14/ 1M | $1/ 1M | $0.05 | Not published | Aug 23, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| Qwen: Qwen3.5-27BQwen | $0.26/ 1M | $2.6/ 1M | Not published | Not published | Aug 23, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| Qwen: Qwen3.5-122B-A10BQwen | $0.29/ 1M | $2.4/ 1M | Not published | Not published | Aug 23, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| Anthropic: Claude Sonnet 4.6Anthropic | $3/ 1M | $15/ 1M | Not published | Not published | Aug 26, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| Qwen: Qwen3.5 397B A17BQwen | $0.45/ 1M | $3/ 1M | $0.22 | Not published | Aug 23, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| Z.ai: GLM 5Z.ai (GLM) | $0.6/ 1M | $2.08/ 1M | $0.12 | Not published | Aug 26, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| Qwen: Qwen3 Max ThinkingQwen | $1.2/ 1M | $6/ 1M | $0.24 | Not published | Aug 23, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| MoonshotAI: Kimi K2.5Moonshotai | $0.45/ 1M | $2.25/ 1M | $0.07 | Not published | Aug 23, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| DeepSeek: DeepSeek V4 Flash Vision ExpDeepSeek | $0.44/ 1M | $1.32/ 1M | $0.014 | Not published | Sep 10, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| Z.ai: GLM 4.7 FlashZ.ai (GLM) | $0.06/ 1M | $0.4/ 1M | $0.01 | Not published | Aug 26, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| Z.ai: GLM 4.7Z.ai (GLM) | $0.4/ 1M | $1.75/ 1M | $0.08 | Not published | Aug 26, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| $0.05/ 1M | $0.2/ 1M | $0.025 | Not published | Aug 23, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| DeepSeek: DeepSeek V3.2DeepSeek | $0.26/ 1M | $0.38/ 1M | $0.13 | Not published | Aug 26, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| Qwen: Qwen3.8 MaxQwen | $1.65/ 1M | $4.951/ 1M | $0.206 | Not published | Aug 23, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| Anthropic: Claude Haiku 4.5Anthropic | $1/ 1M | $5/ 1M | Not published | Not published | Aug 26, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| Qwen: Qwen3 VL 30B A3B InstructQwen | $0.15/ 1M | $0.6/ 1M | Not published | Not published | Aug 23, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| Z.ai: GLM 4.6Z.ai (GLM) | $0.5/ 1M | $2/ 1M | $0.1 | Not published | Aug 26, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| DeepSeek: DeepSeek V4 Flash 0731DeepSeek | $0.06/ 1M | $0.18/ 1M | $0.015 | Not published | Sep 6, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| Qwen: Qwen3 VL 235B A22B InstructQwen | $0.2/ 1M | $0.88/ 1M | $0.11 | Not published | Aug 23, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|
| Qwen: Qwen3 MaxQwen | $1.2/ 1M | $6/ 1M | $0.24 | Not published | Aug 23, 2026 | Sourcehttps://api.deepinfra.com/v1/openai/models See where this value came from and when it was checked.
|