Deepinfra
Serverless and private inference endpoints for open models.
- Models tracked
- 49
- Route-ready
- 49
- Input from
- $0.010
- Output from
- $0.10
Catalog Coverage
Model Endpoints
| Model | Route model | Context | Input / 1M | Output / 1M | Region | Evidence |
|---|---|---|---|---|---|---|
| GLM 5.3Route-ready | zai-org/GLM-5.3 | 1,000K | $0.90 | $4.00 | Global | Provider-reported |
| DeepSeek V4.1 FlashRoute-ready | deepseek-ai/DeepSeek-V4.1-Flash | 1,049K | $0.20 | $0.60 | Global | Provider-reported |
| Hy4 previewRoute-ready | tencent/Hy4-preview | 1,000K | $0.834 | $2.501 | Global | Provider-reported |
| Claude Opus 5.5Route-ready | anthropic/claude-opus-5-5 | 1,000K | $4.00 | $20.00 | Global | Provider-reported |
| DeepSeek V4 FlashRoute-ready | deepseek-ai/DeepSeek-V4-Flash | 1,049K | $0.090 | $0.18 | Global | Provider-reported |
| DeepSeek V4 ProRoute-ready | deepseek-ai/DeepSeek-V4-Pro | 1,049K | $1.30 | $2.60 | Global | Provider-reported |
| Qwen3.8 FlashRoute-ready | Qwen/Qwen3.8-Flash | 1,000K | $0.113 | $0.382 | Global | Provider-reported |
| MiniMax M3Route-ready | MiniMaxAI/MiniMax-M3 | 1,049K | $0.28 | $1.10 | Global | Provider-reported |
| Inkling SmallRoute-ready | thinkingmachines/Inkling-Small | 1,049K | $0.45 | $1.20 | Global | Provider-reported |
| Granite 4.2 3BRoute-ready | ibm-granite/granite-4.2-3b | 131K | $0.030 | $0.12 | — | Provider-reported |
| DeepSeek V3.2Route-ready | deepseek-ai/DeepSeek-V3.2 | 164K | $0.26 | $0.38 | Global | Provider-reported |
| Granite 4.2 30BRoute-ready | ibm-granite/granite-4.2-30b | 131K | $0.16 | $0.65 | — | Provider-reported |
| Qwen3.5 35B A3BRoute-ready | Qwen/Qwen3.5-35B-A3B | 262K | $0.14 | $1.00 | Global | Provider-reported |
| GLM 5.1Route-ready | zai-org/GLM-5.1 | 203K | $1.05 | $3.50 | — | Provider-reported |
| Qwen3.8 27BRoute-ready | Qwen/Qwen3.8-27B | 262K | $0.20 | $2.50 | Global | Provider-reported |
| InklingRoute-ready | thinkingmachines/Inkling | 1,049K | $0.95 | $4.05 | Global | Provider-reported |
| Kimi K2.5Route-ready | moonshotai/Kimi-K2.5 | 262K | $0.45 | $2.25 | — | Provider-reported |
| gpt-oss-120bRoute-ready | openai/gpt-oss-120b | 131K | $0.037 | $0.17 | Global | Provider-reported |
| Gemma 4 E4BRoute-ready | google/gemma-4-E4B-it | 131K | $0.020 | $0.10 | Global | Provider-reported |
| GLM 5Route-ready | zai-org/GLM-5 | 203K | $0.60 | $2.08 | — | Provider-reported |
| Granite 4.2 8BRoute-ready | ibm-granite/granite-4.2-8b | 131K | $0.060 | $0.25 | Global | Provider-reported |
| Claude Fable 5Route-ready | anthropic/claude-fable-5 | 1,000K | $10.00 | $50.00 | Global | Provider-reported |
| Hy3Route-ready | tencent/Hy3 | 262K | $0.13 | $0.53 | — | Provider-reported |
| Qwen3.8 2.4T A95BRoute-ready | Qwen/Qwen3.8-2.4T-A95B | 262K | $2.00 | $6.00 | — | Provider-reported |
| Claude Opus 5Route-ready | anthropic/claude-opus-5 | 1,000K | $5.00 | $25.00 | Global | Provider-reported |
| Muse Glimmer 30BRoute-ready | meta-models/Muse-Glimmer-30B | 131K | $0.30 | $1.20 | Global | Provider-reported |
| DeepSeek V4 Flash Vision ExpRoute-ready | deepseek-ai/DeepSeek-V4-Flash-Vision-Exp | 1,049K | $0.44 | $1.32 | Global | Provider-reported |
| Kimi K3Route-ready | moonshotai/Kimi-K3 | 1,049K | $2.85 | $14.25 | Global | Provider-reported |
| Claude Haiku 4.5Route-ready | anthropic/claude-haiku-4-5 | 200K | $1.00 | $5.00 | Global | Provider-reported |
| Qwen3.7 MaxRoute-ready | Qwen/Qwen3.7-Max | 1,000K | $2.50 | $7.50 | Global | Provider-reported |
| Llama 4 Scout 17B 16E InstructRoute-ready | meta-llama/Llama-4-Scout-17B-16E-Instruct | 10,000K | $0.10 | $0.30 | Global | Provider-reported |
| Qwen3.8 MaxRoute-ready | Qwen/Qwen3.8-Max | 1,000K | $1.65 | $4.951 | Global | Provider-reported |
| GLM 5.3 FlashRoute-ready | zai-org/GLM-5.3-Flash | 1,000K | $0.15 | $0.50 | Global | Provider-reported |
| Claude Sonnet 4.6Route-ready | anthropic/claude-sonnet-4-6 | 1,000K | $3.00 | $15.00 | Global | Provider-reported |
| Claude Opus 4.7Route-ready | anthropic/claude-opus-4-7 | 1,000K | $5.00 | $25.00 | Global | Provider-reported |
| Gemma 4 26B A4BRoute-ready | google/gemma-4-26B-A4B-it | 262K | $0.070 | $0.34 | Global | Provider-reported |
| Gemma 4 31BRoute-ready | google/gemma-4-31B-it | 262K | $0.20 | $0.40 | Global | Provider-reported |
| Claude Sonnet 5Route-ready | anthropic/claude-sonnet-5 | 1,000K | $3.00 | $15.00 | Global | Provider-reported |
| MiniMax M2.7Route-ready | MiniMaxAI/MiniMax-M2.7 | 205K | $0.25 | $1.00 | — | Provider-reported |
| Qwen3 Embedding 8BRoute-ready | Qwen/Qwen3-Embedding-8B | 33K | $0.010 | — | Global | Provider-reported |
| phi-4Route-ready | microsoft/phi-4 | 16K | $0.070 | $0.14 | Global | Provider-reported |
| DeepSeek V3Route-ready | deepseek-ai/DeepSeek-V3 | 164K | $0.32 | $0.89 | Global | Provider-reported |
| Claude Opus 4.8Route-ready | anthropic/claude-opus-4-8 | 1,000K | $5.00 | $25.00 | Global | Provider-reported |
| gpt-oss-20bRoute-ready | openai/gpt-oss-20b | 131K | $0.030 | $0.14 | Global | Provider-reported |
| GLM 5.2Route-ready | zai-org/GLM-5.2 | 1,049K | $0.75 | $2.40 | Global | Provider-reported |
| Qwen3.5 397B A17BRoute-ready | Qwen/Qwen3.5-397B-A17B | 262K | $0.45 | $3.00 | Global | Provider-reported |
| DeepSeek V4 Pro 0813Route-ready | deepseek-ai/DeepSeek-V4-Pro-0813 | 1,049K | $1.30 | $2.60 | Global | Provider-reported |
| Kimi K2.7 CodeRoute-ready | moonshotai/Kimi-K2.7-Code | 262K | $0.68 | $3.40 | Global | Provider-reported |
| Kimi K2.6Route-ready | moonshotai/Kimi-K2.6 | 262K | $0.75 | $3.50 | Global | Provider-reported |
Routing Contract
https://api.deepinfra.com/v1/openaiThese public route targets identify where and how a model can be requested. Model Markets does not hold provider keys or send inference traffic from this interface.
Provider records describe a serving surface, not the underlying model. Pricing, quantization, region, service tier, retention policy, and measured performance remain endpoint-specific.
Questions
Deepinfra Questions
Which models does Deepinfra offer?+
The current source snapshot includes 49 model endpoint for Deepinfra: GLM 5.3, DeepSeek V4.1 Flash, Hy4 preview, Claude Opus 5.5, DeepSeek V4 Flash, DeepSeek V4 Pro, Qwen3.8 Flash, MiniMax M3, Inkling Small, Granite 4.2 3B, DeepSeek V3.2, Granite 4.2 30B, Qwen3.5 35B A3B, GLM 5.1, Qwen3.8 27B, Inkling, Kimi K2.5, gpt-oss-120b, Gemma 4 E4B, GLM 5, Granite 4.2 8B, Claude Fable 5, Hy3, Qwen3.8 2.4T A95B, Claude Opus 5, Muse Glimmer 30B, DeepSeek V4 Flash Vision Exp, Kimi K3, Claude Haiku 4.5, Qwen3.7 Max, Llama 4 Scout 17B 16E Instruct, Qwen3.8 Max, GLM 5.3 Flash, Claude Sonnet 4.6, Claude Opus 4.7, Gemma 4 26B A4B, Gemma 4 31B, Claude Sonnet 5, MiniMax M2.7, Qwen3 Embedding 8B, phi-4, DeepSeek V3, Claude Opus 4.8, gpt-oss-20b, GLM 5.2, Qwen3.5 397B A17B, DeepSeek V4 Pro 0813, Kimi K2.7 Code, Kimi K2.6. Browse all models →
How much does Deepinfra cost?+
For GLM 5.3, the cited source reports $0.90 input and $4.00 output per million tokens.
Is Deepinfra the fastest provider?+
Model Markets has not run approved independent probes for this delivery, so it does not make a fastest-provider claim.
How current is Deepinfra data?+
The cited source snapshot was observed Oct 19, 2026; availability may have changed since then.
How does Model Markets verify Deepinfra?+
Catalog and price claims retain their source classification; independent measurements are labeled separately when available. Read the methodology →