All 317 LLM API prices
Every model in the dataset, grouped by provider, with the input and output price per 1M tokens. Prices last verified 2026-08-30. Click through to a model for full specs, monthly cost at real volumes, and cheaper alternatives.
AI21 Labs
| Model | Tier | Context | $/1M in | $/1M out |
|---|---|---|---|---|
| Jamba Large | Flagship | — | $2.00 | $8.00 |
| Jamba Mini | Small | — | $0.20 | $0.40 |
Alibaba Qwen
| Model | Tier | Context | $/1M in | $/1M out |
|---|---|---|---|---|
| Qwen3.8-Max | Flagship | 1M | $2.00 | $6.00 |
| Qwen-Plus | Mid | 1M | $0.40 | $1.20 |
| Qwen-Turbo | Small | 1M | $0.05 | $0.20 |
| Qwen3.5-Flash | Small | 1M | $0.10 | $0.40 |
| Qwen3.8-Flash | Small | 1M | $0.15 | $0.47 |
Amazon (Nova)
| Model | Tier | Context | $/1M in | $/1M out |
|---|---|---|---|---|
| Amazon Nova Premier | Flagship | 1M | $2.50 | $12.50 |
| Amazon Nova Pro | Mid | 300K | $0.80 | $3.20 |
| Amazon Nova 2 Lite | Small | 1M | $0.30 | $2.50 |
| Amazon Nova Lite | Small | 300K | $0.06 | $0.24 |
| Amazon Nova Micro | Small | 128K | $0.035 | $0.14 |
Anthropic
| Model | Tier | Context | $/1M in | $/1M out |
|---|---|---|---|---|
| Claude Opus 5 | Flagship | 1M | $5.00 | $25.00 |
| Claude Fable 5 | Reasoning | 1M | $10.00 | $50.00 |
| Claude Sonnet 5 | Mid | 1M | $2.00 | $10.00 |
| Claude Haiku 4.5 | Small | 200K | $1.00 | $5.00 |
Azure OpenAI Service
| Model | Tier | Context | $/1M in | $/1M out |
|---|---|---|---|---|
| GPT-4.1-2025-04-14 | Flagship | 1M | $2.00 | $8.00 |
| GPT-4.5-Preview-2025-02-27 | Flagship | 128K | $75.00 | $150.00 |
| GPT-4o-2024-0513 | Flagship | 128K | $5.00 | $15.00 |
| GPT-4o-2024-08-06 | Flagship | 128K | $2.50 | $10.00 |
| GPT-4o-2024-1120 | Flagship | 128K | $2.50 | $10.00 |
| GPT-5 (2025-08-07) | Flagship | — | $1.25 | $10.00 |
| GPT-5 chat | Flagship | — | $1.25 | $10.00 |
| GPT-5 Pro | Flagship | — | $15.00 | $120.00 |
| GPT-5.1 | Flagship | — | $1.25 | $10.00 |
| GPT-5.1-chat | Flagship | — | $1.25 | $10.00 |
| GPT-5.2 | Flagship | — | $1.75 | $14.00 |
| GPT-5.2-chat latest | Flagship | — | $1.75 | $14.00 |
| GPT-5.3 Chat | Flagship | — | $1.75 | $14.00 |
| GPT-5.4 (<272k context length) | Flagship | — | $2.50 | $15.00 |
| GPT-5.4 (>272k context length) | Flagship | — | $5.00 | $22.50 |
| GPT-5.4 Pro (<272k context length) | Flagship | — | $30.00 | $180.00 |
| GPT-5.4 Pro (>272k context length) | Flagship | — | $60.00 | $270.00 |
| GPT-5.5 | Flagship | — | $5.00 | $30.00 |
| GPT-5.5 Long Context | Flagship | — | $10.00 | $45.00 |
| GPT-5.6-sol (long context) | Flagship | — | $10.00 | $45.00 |
| GPT-5.6-sol (short context) | Flagship | — | $5.00 | $30.00 |
| GPT-Chat Latest 05052026 | Flagship | — | $5.00 | $30.00 |
| GPT-5 Codex | Reasoning | — | $1.25 | $10.00 |
| GPT-5.1-codex | Reasoning | — | $1.25 | $10.00 |
| GPT-5.1-codex-max | Reasoning | — | $1.25 | $10.00 |
| GPT-5.1-codex-mini | Reasoning | — | $0.25 | $2.00 |
| GPT-5.2 Codex | Reasoning | — | $1.75 | $14.00 |
| GPT-5.3 Codex | Reasoning | — | $1.75 | $14.00 |
| o1 (2024-12-17) | Reasoning | 200K | $15.00 | $60.00 |
| o1 preview (2024-09-12) | Reasoning | — | $15.00 | $60.00 |
| o1-mini (2024-09-12) | Reasoning | 128K | $1.10 | $4.40 |
| o3 (2025-04-16) | Reasoning | 200K | $2.00 | $8.00 |
| o3 mini (2025-01-31) | Reasoning | 200K | $1.10 | $4.40 |
| o3-deep research | Reasoning | — | $10.00 | $40.00 |
| o4-mini (2025-04-16) | Reasoning | 200K | $1.10 | $4.40 |
| GPT-4.1-mini-2025-04-14 | Mid | 1M | $0.40 | $1.60 |
| GPT-5-mini | Mid | — | $0.25 | $2.00 |
| GPT-5.4 mini | Mid | — | $0.75 | $4.50 |
| GPT-5.6-terra (long context) | Mid | — | $4.00 | $18.00 |
| GPT-5.6-terra (short context) | Mid | — | $2.00 | $12.00 |
| GPT-4.1-nano-2025-04-14 | Small | 1M | $0.10 | $0.40 |
| GPT-4o-mini-0718 | Small | 128K | $0.15 | $0.60 |
| GPT-5-nano | Small | — | $0.05 | $0.40 |
| GPT-5.4 nano | Small | — | $0.20 | $1.25 |
| GPT-5.6-luna (long context) | Small | — | $0.40 | $1.80 |
| GPT-5.6-luna (short context) | Small | — | $0.20 | $1.20 |
Baseten
| Model | Tier | Context | $/1M in | $/1M out |
|---|---|---|---|---|
| DeepSeek V4 Pro | Flagship | — | $1.74 | $3.48 |
| DeepSeek V4 Pro 0813 | Flagship | — | $1.32 | $3.96 |
| GLM-5.2 | Flagship | — | $1.40 | $4.40 |
| GLM-5.2 Fast | Flagship | — | $2.10 | $6.60 |
| GLM-5.3 | Flagship | — | $1.40 | $4.40 |
| Kimi K2.6 | Flagship | — | $0.95 | $4.00 |
| Kimi K2.7 Code | Flagship | — | $0.95 | $4.00 |
| Kimi K3 | Flagship | — | $3.00 | $15.00 |
| DeepSeek V4 Flash 0731 | Mid | — | $0.13 | $0.26 |
| GLM 4.7 | Mid | — | $0.60 | $2.20 |
| GLM-5.3-Flash | Mid | — | $0.15 | $0.50 |
| GPT OSS 120B | Mid | — | $0.10 | $0.50 |
Cerebras
| Model | Tier | Context | $/1M in | $/1M out |
|---|---|---|---|---|
| GPT OSS 120B | Mid | — | $0.35 | $0.75 |
| Gemma 4 31B | Small | — | $0.99 | $1.49 |
Cloudflare Workers AI
| Model | Tier | Context | $/1M in | $/1M out |
|---|---|---|---|---|
| DeepSeek V4 Pro (0813) | Flagship | — | $1.32 | $3.96 |
| GPT-OSS 120B | Flagship | — | $0.35 | $0.75 |
| Llama 3.3 70B Instruct (fp8-fast) | Flagship | — | $0.293 | $2.25 |
| DeepSeek R1 Distill Qwen 32B | Reasoning | — | $0.497 | $4.88 |
| QwQ 32B | Reasoning | — | $0.66 | $1.00 |
| DeepSeek V4 Flash (0731) | Mid | — | $0.44 | $1.32 |
| Llama 4 Scout 17B 16E Instruct | Mid | — | $0.27 | $0.85 |
| Mistral Small 3.1 24B Instruct | Mid | — | $0.351 | $0.555 |
| Qwen2.5 Coder 32B Instruct | Mid | — | $0.66 | $1.00 |
| GPT-OSS 20B | Small | — | $0.20 | $0.30 |
| Llama 3.1 8B Instruct (fp8-fast) | Small | — | $0.045 | $0.384 |
Cohere
| Model | Tier | Context | $/1M in | $/1M out |
|---|---|---|---|---|
| Command R | Mid | 128K | $0.15 | $0.60 |
| Command R7B | Small | 128K | $0.0375 | $0.15 |
DeepInfra
| Model | Tier | Context | $/1M in | $/1M out |
|---|---|---|---|---|
| DeepSeek-V4-Pro | Flagship | 1.02M | $1.30 | $2.60 |
| Kimi-K3 | Flagship | 1.02M | $2.85 | $14.25 |
| Llama-3.3-70B-Instruct-Turbo | Mid | 128K | $0.10 | $0.32 |
| Llama-4-Maverick-17B-128E | Mid | 1.02M | $0.20 | $0.80 |
| Qwen3-Max | Mid | 250K | $1.20 | $6.00 |
| Meta-Llama-3.1-8B-Instruct-Turbo | Small | 128K | $0.02 | $0.04 |
DeepSeek
| Model | Tier | Context | $/1M in | $/1M out |
|---|---|---|---|---|
| DeepSeek V4 Pro | Flagship | 1M | $1.32 | $3.96 |
| DeepSeek V4 Flash | Small | 1M | $0.44 | $1.32 |
| DeepSeek V4 Flash Vision (Exp) | Small | 1M | $0.44 | $1.32 |
Fireworks AI
| Model | Tier | Context | $/1M in | $/1M out |
|---|---|---|---|---|
| DeepSeek V4 Pro | Flagship | — | $1.74 | $3.48 |
| Kimi K3 | Flagship | — | $3.00 | $15.00 |
| GLM 5.3 | Mid | — | $1.40 | $4.40 |
| GPT-OSS 120B | Mid | 131K | $0.15 | $0.60 |
| Qwen3.8 Max | Mid | — | $2.00 | $6.00 |
| GPT-OSS 20B | Small | 131K | $0.07 | $0.30 |
| Model | Tier | Context | $/1M in | $/1M out |
|---|---|---|---|---|
| Gemini 2.5 Pro | Flagship | 1.05M | $1.25 | $10.00 |
| Gemini 3.1 Pro | Flagship | 1M | $2.00 | $12.00 |
| Gemini 2.5 Flash | Mid | 1M | $0.30 | $2.50 |
| Gemini 3.5 Flash | Mid | 1.05M | $1.50 | $9.00 |
| Gemini 3.6 Flash | Mid | 1.05M | $0.75 | $3.75 |
| Gemini 3.7 Flash | Mid | 1M | $0.75 | $3.75 |
| Gemini 2.5 Flash-Lite | Small | 1.05M | $0.10 | $0.40 |
| Gemini 3 Flash Preview | Small | 1.05M | $0.50 | $3.00 |
| Gemini 3.1 Flash-Lite | Small | 1.05M | $0.25 | $1.50 |
| Gemini 3.5 Flash-Lite | Small | 1.05M | $0.30 | $2.50 |
Groq
| Model | Tier | Context | $/1M in | $/1M out |
|---|---|---|---|---|
| GPT-OSS 120B | Flagship | 131K | $0.15 | $0.60 |
| Qwen3.6 27B | Mid | 131K | $0.60 | $3.00 |
| Qwen3.8 27B | Mid | 131K | $0.80 | $4.00 |
| GPT-OSS 20B | Small | 131K | $0.075 | $0.30 |
inference.net
| Model | Tier | Context | $/1M in | $/1M out |
|---|---|---|---|---|
| Claude Fable 5 | Flagship | 1M | $10.00 | $50.00 |
| Claude Opus 4.6 | Flagship | 1M | $5.00 | $25.00 |
| Claude Opus 4.7 | Flagship | 1M | $5.00 | $25.00 |
| Claude Opus 4.8 | Flagship | 1M | $5.00 | $25.00 |
| Claude Opus 5 | Flagship | 1M | $5.00 | $25.00 |
| DeepSeek V4 Pro | Flagship | 1.05M | $0.435 | $0.87 |
| DeepSeek V4 Pro (0813) | Flagship | 1.05M | $1.32 | $3.96 |
| Gemini 2.5 Pro | Flagship | 1.05M | $1.25 | $10.00 |
| Gemini 3.1 Pro Preview | Flagship | 1.05M | $2.00 | $12.00 |
| GLM-5.2 | Flagship | 1M | $1.30 | $4.40 |
| GLM-5.2 Fast | Flagship | 1M | $2.60 | $8.80 |
| GLM-5.3 | Flagship | 1M | $1.75 | $5.50 |
| GPT-5.4 | Flagship | 1.05M | $2.50 | $15.00 |
| GPT-5.5 | Flagship | 1.05M | $5.00 | $30.00 |
| GPT-5.6 Sol | Flagship | 1.05M | $5.00 | $30.00 |
| Kimi K3 | Flagship | 1.05M | $3.00 | $15.00 |
| Kimi K3 Fast | Flagship | 1.05M | $4.50 | $22.50 |
| Claude Sonnet 4.6 | Mid | 1M | $3.00 | $15.00 |
| Gemini 2.5 Flash | Mid | 1.05M | $0.30 | $2.50 |
| Gemini 3 Flash Preview | Mid | 1.05M | $0.50 | $3.00 |
| Gemini 3.5 Flash | Mid | 1.05M | $1.50 | $9.00 |
| Gemini 3.6 Flash | Mid | 1.05M | $1.50 | $7.50 |
| Gemini 3.7 Flash | Mid | 1.05M | $1.50 | $7.50 |
| GPT-4.1 | Mid | 1.05M | $2.00 | $8.00 |
| GPT-4o | Mid | 128K | $2.50 | $10.00 |
| GPT-5.6 Terra | Mid | 1.05M | $2.00 | $12.00 |
| Grok 4.5 | Mid | 500K | $2.00 | $6.00 |
| Grok 4.6 | Mid | 500K | $2.00 | $6.00 |
| Claude Haiku 4.5 | Small | 200K | $1.00 | $5.00 |
| DeepSeek V4 Flash | Small | 164K | $0.14 | $0.28 |
| DeepSeek V4 Flash (0731) | Small | 256K | $0.168 | $0.336 |
| Gemini 2.5 Flash Lite | Small | 1.05M | $0.10 | $0.40 |
| Gemini 3.1 Flash Lite | Small | 1.05M | $0.25 | $1.50 |
| Gemini 3.5 Flash-Lite | Small | 1.05M | $0.30 | $2.50 |
| GLM-5.3 Flash | Small | 1M | $0.54 | $1.80 |
| GPT-4.1 Mini | Small | 1.05M | $0.40 | $1.60 |
| GPT-4.1 Nano | Small | 1.05M | $0.10 | $0.40 |
| GPT-4o Mini | Small | 128K | $0.15 | $0.60 |
| GPT-5 Mini | Small | 400K | $0.25 | $2.00 |
| GPT-5 Nano | Small | 400K | $0.05 | $0.40 |
| GPT-5.6 Luna | Small | 1.05M | $0.20 | $1.20 |
| schematron-v2-small | Small | 128K | $0.05 | $0.25 |
| schematron-v2-turbo | Small | 128K | $0.03 | $0.15 |
Mistral AI
| Model | Tier | Context | $/1M in | $/1M out |
|---|---|---|---|---|
| GLM-5.2 (on Mistral) | Flagship | 1M | $1.40 | $4.40 |
| Mistral Large 3 | Flagship | 256K | $0.50 | $1.50 |
| Mistral Medium 3.5 | Mid | 256K | $1.50 | $7.50 |
| Codestral | Small | 128K | $0.30 | $0.90 |
| Ministral 3 14B | Small | 256K | $0.20 | $0.20 |
| Ministral 3 3B | Small | 256K | $0.10 | $0.10 |
| Ministral 3 8B | Small | 256K | $0.15 | $0.15 |
| Mistral Small 4 | Small | 256K | $0.15 | $0.60 |
Moonshot AI
| Model | Tier | Context | $/1M in | $/1M out |
|---|---|---|---|---|
| Kimi K3 | Flagship | 1.05M | $3.00 | $15.00 |
| Kimi K2.6 | Mid | 262K | $0.95 | $4.00 |
| Kimi K2.7 Code | Mid | 262K | $0.95 | $4.00 |
| Moonshot v1 128K | Small | 131K | $2.00 | $5.00 |
| Moonshot v1 8K | Small | 8K | $0.20 | $2.00 |
Novita AI
| Model | Tier | Context | $/1M in | $/1M out |
|---|---|---|---|---|
| DeepSeek V3.1 Terminus | Flagship | 128K | $0.27 | $1.00 |
| GLM 4.6 | Flagship | 200K | $0.55 | $2.20 |
| Kimi K2 Instruct | Flagship | 128K | $0.57 | $2.30 |
| Llama 4 Maverick Instruct | Flagship | 1M | $0.27 | $0.85 |
| Qwen3 235B A22B Instruct 2507 | Flagship | 128K | $0.09 | $0.58 |
| Qwen3 Coder 480B A35B Instruct | Flagship | 256K | $0.38 | $1.55 |
| DeepSeek R1 0528 | Reasoning | 160K | $0.70 | $2.50 |
| Kimi K2 Thinking | Reasoning | 256K | $0.60 | $2.50 |
| GPT-OSS 120B | Mid | 128K | $0.05 | $0.25 |
| Llama 4 Scout Instruct | Mid | 128K | $0.18 | $0.59 |
| GPT-OSS 20B | Small | 128K | $0.04 | $0.15 |
| Mistral Nemo | Small | 59K | $0.04 | $0.17 |
OpenAI
| Model | Tier | Context | $/1M in | $/1M out |
|---|---|---|---|---|
| GPT-5.6 Sol | Flagship | 1.05M | $4.00 | $20.00 |
| GPT-5.6 Cyber | Reasoning | 400K | $12.50 | $75.00 |
| o4-mini | Reasoning | 200K | $1.10 | $4.40 |
| GPT-5.6 Terra | Mid | 1.05M | $2.00 | $12.00 |
| GPT-5.6 Luna | Small | 1.05M | $0.20 | $1.20 |
OpenRouter
| Model | Tier | Context | $/1M in | $/1M out |
|---|---|---|---|---|
| DeepSeek V4 Pro | Flagship | 1.05M | $0.680862 | $1.36 |
| GLM-5.3 | Flagship | 1.31M | $1.40 | $4.40 |
| Kimi K3 | Flagship | 1.05M | $3.00 | $15.00 |
| MiniMax M3 | Flagship | 1.05M | $0.30 | $1.20 |
| Qwen3.8-Max | Flagship | 1M | $2.00 | $6.00 |
| Sonar Pro | Flagship | 200K | $3.00 | $15.00 |
| ERNIE 4.5 VL 424B A47B | Mid | 123K | $0.42 | $1.25 |
| GPT-OSS 120B | Mid | 131K | $0.037 | $0.17 |
| Hy3 | Mid | 262K | $0.132 | $0.528 |
| Llama 3.3 70B | Mid | 131K | $0.71 | $0.71 |
| Llama 4 Maverick | Mid | 1.05M | $0.20 | $0.80 |
| Nemotron 3 Super | Mid | 1M | $0.085 | $0.40 |
| GPT-OSS 20B | Small | 131K | $0.03 | $0.13 |
| Granite 4.1 8B | Small | 131K | $0.05 | $0.10 |
| Llama 3.1 8B | Small | 131K | $0.05 | $0.08 |
| MiMo V2.5 | Small | 1.05M | $0.14 | $0.28 |
| Seed 2.0 Lite | Small | 262K | $0.25 | $2.00 |
| Solar Pro 4 | Small | 524K | $0.03 | $0.12 |
| Sonar | Small | 127K | $1.00 | $1.00 |
Parasail
| Model | Tier | Context | $/1M in | $/1M out |
|---|---|---|---|---|
| DeepSeek V4 Pro | Flagship | — | $1.74 | $3.48 |
| GLM-5.1 | Flagship | — | $1.40 | $4.40 |
| GLM-5.2 | Flagship | — | $1.40 | $4.40 |
| GLM-5.3 | Flagship | — | $1.40 | $4.40 |
| Kimi K3 | Flagship | — | $3.00 | $15.00 |
| Nemotron 3 Ultra 550B (NVFP4) | Flagship | — | $0.50 | $2.50 |
| Qwen3 235B-A22B (2507) | Flagship | — | $0.14 | $0.80 |
| Qwen3-VL 235B-A22B | Flagship | — | $0.21 | $1.90 |
| Qwen3.5 397B-A17B | Flagship | — | $0.50 | $3.60 |
| Trinity Large (Thinking) | Reasoning | — | $0.22 | $0.85 |
| GLM-5 | Mid | — | $1.00 | $3.20 |
| gpt-oss-120b | Mid | — | $0.10 | $0.75 |
| gpt-oss-120b (Fast) | Mid | — | $0.15 | $0.60 |
| Kimi K2.6 | Mid | — | $0.75 | $3.50 |
| Kimi K2.7 Code | Mid | — | $0.75 | $3.50 |
| Llama 3.3 70B (FP8) | Mid | — | $0.22 | $0.50 |
| Llama 4 Maverick (FP8) | Mid | — | $0.35 | $1.00 |
| MiniMax M2.5 | Mid | — | $0.30 | $1.20 |
| MiniMax M3 | Mid | — | $0.30 | $1.20 |
| Qwen2.5-VL 72B | Mid | — | $0.80 | $1.00 |
| Qwen3-Coder-Next | Mid | — | $0.12 | $0.80 |
| Qwen3-Next 80B | Mid | — | $0.10 | $1.10 |
| Cydonia 24B v4.1 | Small | — | $0.30 | $0.50 |
| DeepSeek V4 Flash | Small | — | $0.14 | $0.28 |
| Gemma 3 27B | Small | — | $0.08 | $0.45 |
| Gemma 4 26B-A4B | Small | — | $0.13 | $0.40 |
| Gemma 4 31B | Small | — | $0.15 | $0.40 |
| GLM-5.3 Flash | Small | — | $0.15 | $0.50 |
| gpt-oss-20b | Small | — | $0.04 | $0.20 |
| MiMo v2.5 | Small | — | $0.14 | $0.28 |
| Mistral Small 3.2 24B | Small | — | $0.09 | $0.30 |
| Qwen3-VL 8B | Small | — | $0.25 | $0.75 |
| Qwen3.5 35B-A3B | Small | — | $0.15 | $1.00 |
| Qwen3.6 35B-A3B | Small | — | $0.15 | $1.00 |
| Skyfall 31B v4.2 | Small | — | $0.55 | $0.80 |
| Skyfall 36B v2 (FP8) | Small | — | $0.55 | $0.80 |
| UI-TARS 1.5 7B | Small | — | $0.10 | $0.20 |
Perplexity
| Model | Tier | Context | $/1M in | $/1M out |
|---|---|---|---|---|
| Sonar Pro | Flagship | — | $3.00 | $15.00 |
| Sonar Deep Research | Reasoning | — | $2.00 | $8.00 |
| Sonar Reasoning Pro | Reasoning | — | $2.00 | $8.00 |
| Sonar | Small | — | $1.00 | $1.00 |
Replicate
SambaNova
| Model | Tier | Context | $/1M in | $/1M out |
|---|---|---|---|---|
| DeepSeek-V3.2 | Flagship | — | $3.00 | $4.50 |
| Llama-4-Maverick-17B-128E-Instruct | Flagship | — | $0.63 | $1.80 |
| Qwen3-235B-A22B-Instruct-2507 | Flagship | — | $0.40 | $0.80 |
| DeepSeek-R1-0528 | Reasoning | — | $5.00 | $7.00 |
| DeepSeek-R1-Distill-Llama-70B | Reasoning | — | $0.70 | $1.40 |
| gpt-oss-120b | Mid | — | $0.22 | $0.59 |
| Meta-Llama-3.3-70B-Instruct | Mid | — | $0.60 | $1.20 |
| MiniMax-M2.7 | Mid | — | $0.60 | $2.40 |
| MiniMax-M3 | Mid | — | $0.60 | $2.40 |
| Qwen3-32B | Mid | — | $0.40 | $0.80 |
| gemma-4-31B-it | Small | — | $0.38 | $1.15 |
Together AI
| Model | Tier | Context | $/1M in | $/1M out |
|---|---|---|---|---|
| DeepSeek V4 Pro 0813 | Flagship | — | $1.32 | $3.96 |
| GLM-5.3 | Flagship | — | $1.40 | $4.40 |
| Kimi K3 | Flagship | — | $3.00 | $15.00 |
| Llama 4 Maverick | Flagship | 1.05M | $0.27 | $0.85 |
| Qwen3.5-397B-A17B | Flagship | — | $0.60 | $3.60 |
| gpt-oss-120B | Mid | — | $0.15 | $0.60 |
| Llama 3.1 70B | Mid | 128K | $0.88 | $0.88 |
| Llama 3.3 70B | Mid | 128K | $1.04 | $1.04 |
| Llama 4 Scout | Mid | 1M | $0.18 | $0.59 |
| MiniMax M3 | Mid | — | $0.30 | $1.20 |
| Qwen3 235B A22B Instruct 2507 FP8 Throughput | Mid | — | $0.20 | $0.60 |
| DeepSeek V4 Flash 0731 | Small | — | $0.14 | $0.28 |
| GLM-5.3-Flash | Small | — | $0.15 | $0.50 |
| gpt-oss-20B | Small | — | $0.05 | $0.20 |
| Llama 3 8B Instruct Lite | Small | 8K | $0.14 | $0.14 |
| Llama 3.1 8B | Small | 128K | $0.18 | $0.18 |
xAI
| Model | Tier | Context | $/1M in | $/1M out |
|---|---|---|---|---|
| Grok 4.5 | Flagship | 500K | $2.00 | $6.00 |
| Grok 4.6 | Flagship | 500K | $2.00 | $6.00 |
| Grok 4.3 | Mid | 1M | $1.25 | $2.50 |
| Grok Build | Small | 256K | $1.00 | $2.00 |
Z.ai
| Model | Tier | Context | $/1M in | $/1M out |
|---|---|---|---|---|
| GLM-5.3 | Flagship | 1M | $1.40 | $4.40 |
| GLM-4.5 | Mid | 128K | $0.60 | $2.20 |
| GLM-4.6 | Mid | 200K | $0.60 | $2.20 |
| GLM-4.5-Air | Small | 128K | $0.20 | $1.10 |
| GLM-5.3-Flash | Small | 1M | $0.075 | $0.25 |