Structured output LLM API pricing
All 612 models that return schema-constrained output (guaranteed JSON), so responses parse reliably without prompt-engineering the format, cheapest input from $0.01 per 1M tokens. Sort by price, context window or benchmark, filter by maker, and copy the exact model ID for any serving provider. Listed prices from LiteLLM, OpenRouter and Vercel.
Models
612
with structured output
Cheapest input
$0.01
per 1M tokens
Cheapest output
$0.02
per 1M tokens
Max context
5M
tokens
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower. An OpenRouter routed quote is the price of whichever upstream provider OpenRouter prefers today, so it moves day to day.
Maker
| gpt-oss-120b | Released Aug 5, 2025 | 131K | from $0.03 via Wandb | from $0.17 via DeepInfra | 11.6 | 26% | 78% | 23 providers | |
| GLM 5.2 | Released Jun 13, 2026 | 1M | from $0.05 Routed quote | from $1.98 via Scx AI | 33.7 | 78% | 89% | 20 providers | |
| DeepSeek V4 Flash 0423 | Released Apr 24, 2026 | 1M | from $0.09 via DeepInfra | from $0.18 via DeepInfra | 24.2 | 62% | 89% | 18 providers | |
| Llama 3.3 70B Instruct | First listed Dec 2024 | 131K | from $0.12 via Hyperbolic | from $0.20 via Crusoe | 7.7 | 5% | 50% | 18 providers | |
| Llama 3.1 8B Instruct | First listed Jul 2024 | 200K | from $0.02 via Nebius | from $0.03 via Nscale | 6.9 | 1% | 26% | 17 providers | |
| DeepSeek V4 Flash 0731 | Released Jul 31, 2026 | 1M | from $0.016 Routed quote | from $0.153 Routed quote | 34.3 | 79% | 91% | 16 providers | |
| GLM 5.3 | Released Aug 14, 2026 | 1M | from $0.079 Routed quote | from $3.08 via Sail | 44.8 | 84% | 92% | 16 providers | |
| DeepSeek V4 Pro 0423 | Released Apr 24, 2026 | 1M | from $0.435 via Tencent | from $0.87 via Tencent | 30.4 | 65% | 89% | 16 providers | |
| Kimi K2.7 Code | Released Jun 13, 2026 | 262K | from $0.671 Routed quote | from $3.35 Routed quote | 25.8 | 67% | 90% | 16 providers | |
| gpt-oss-20b | Released Mar 1, 2026 | 131K | from $0.0145 via Darkbloom | from $0.07 via Darkbloom | 9.0 | 14% | 69% | 15 providers | |
| Kimi K2.6 | First listed Apr 2026 | 262K | from $0.65 via Wandb | from $3.40 via Novita | 27.0 | 66% | 91% | 15 providers | |
| R1 | Released Jan 1, 2025 | 164K | from $0.40 via Hyperbolic | from $0.40 via Hyperbolic | 11.4 | 19% | 71% | 14 providers | |
| Kimi K3 | Released Jul 16, 2026 | 1M | from $0.70 Routed quote | from $12.50 via Sail | 43.6 | 85% | 94% | 14 providers | |
| Gemma 4 31B | Released Apr 2, 2026 | 262K | from $0.09 Routed quote | from $0.34 via Wandb | n/a | n/a | n/a | 13 providers | |
| GLM 5.3 Flash | Released Aug 26, 2026 | 1M | from $0.11 via Sail | from $0.35 via Sail | 41.8 | 84% | 91% | 13 providers | |
| DeepSeek V4.1 Flash | Released Sep 10, 2026 | 1M | from $0.01 via Coralbricks | from $0.60 via Sail | 39.5 | n/a | n/a | 12 providers | |
| DeepSeek V3 0324 | Released Mar 24, 2025 | 164K | from $0.20 via Lambda AI | from $0.40 via Hyperbolic | 9.7 | 14% | 65% | 12 providers | |
| DeepSeek V4 Pro 0813 | Released Aug 14, 2026 | 1M | from $0.66 Routed quote | from $1.98 Routed quote | 36.0 | 79% | 93% | 12 providers | |
| GLM 5.1 | Released Apr 7, 2026 | 205K | from $1.05 via DeepInfra | from $3.50 via DeepInfra | 26.1 | 62% | 87% | 12 providers | |
| Llama 3.2 3B Instruct | First listed Sep 2024 | 131K | from $0.015 via Lambda AI | from $0.02 via DeepInfra | 5.7 | n/a | 25% | 11 providers | |
| Qwen3 Next 80B A3B Instruct | First listed Sep 2025 | 262K | from $0.09 via DeepInfra | from $0.90 via Fireworks AI | 9.6 | n/a | 74% | 11 providers | |
| DeepSeek R1 Distill Llama 70B | Released Jan 1, 2025 | 131K | from $0.20 via DeepInfra | from $0.375 via Nscale | 7.9 | n/a | 40% | 11 providers | |
| MiniMax M3 | Released Jun 1, 2026 | 1M | from $0.23 via Wandb | from $0.96 via Wandb | 29.2 | 65% | 93% | 11 providers | |
| DeepSeek V3.1 | Released Jan 1, 2025 | 164K | from $0.25 via DeepInfra | from $0.95 via DeepInfra | 13.7 | n/a | 74% | 11 providers | |
| DeepSeek V3.2 | Released Dec 1, 2025 | 164K | from $0.259 Routed quote | from $0.38 via DeepInfra | 16.0 | 47% | 75% | 11 providers | |
| Kimi K2.5 | Released Jan 27, 2026 | 262K | from $0.45 via DeepInfra | from $2.25 via DeepInfra | 23.5 | 46% | 88% | 11 providers | |
| Claude Haiku 4.5 | Released Oct 15, 2025 | 200K | from $1.00 via Anthropic | from $5.00 via Anthropic | n/a | n/a | n/a | 11 providers | |
| Gemma 4 26B A4B | Released Apr 2, 2026 | 262K | from $0.07 via DeepInfra | from $0.255 Routed quote | n/a | n/a | n/a | 10 providers | |
| Qwen3 32B | First listed May 2025 | 131K | from $0.08 via DeepInfra | from $0.23 via Ovhcloud | 7.3 | 5% | 54% | 10 providers | |
| Qwen3 Next 80B A3B Thinking | First listed Sep 2025 | 262K | from $0.14 via DeepInfra | from $0.90 via Fireworks AI | n/a | n/a | n/a | 10 providers | |
| DeepSeek V3 | Released Dec 26, 2024 | 164K | from $0.20 via Hyperbolic | from $0.20 via Hyperbolic | 8.5 | 17% | 56% | 10 providers | |
| R1 0528 | Released May 28, 2025 | 164K | from $0.20 via Lambda AI | from $0.25 via Hyperbolic | 13.1 | n/a | 81% | 10 providers | |
| MiniMax M2.5 | Released Jan 15, 2025 | 1M | from $0.27 Routed quote | from $1.08 Routed quote | 22.8 | n/a | 85% | 10 providers | |
| GLM 4.7 | First listed Jan 2026 | 205K | from $0.40 via DeepInfra | from $1.75 via DeepInfra | 22.2 | 45% | 86% | 10 providers | |
| Kimi K2 Thinking | Released Nov 6, 2025 | 262K | from $0.60 via Moonshot | from $1.20 via Gmi | 22.0 | n/a | 84% | 10 providers | |
| Qwen3.8 Max | Released Aug 3, 2026 | 1M | from $1.65 via DeepInfra | from $4.95 via DeepInfra | 40.1 | 81% | 93% | 10 providers | |
| Qwen3.6 35B A3B | Released Jul 20, 2026 | 262K | from $0.05 via Sail | from $0.40 via Sail | 18.2 | 45% | 84% | 9 providers | |
| Llama 3.1 405B Instruct | First listed Jul 2024 | 131K | from $0.12 via Hyperbolic | from $0.30 via Hyperbolic | 7.3 | n/a | 52% | 9 providers | |
| Llama 3 70B Instruct | Released Apr 18, 2024 | 131K | from $0.12 via Hyperbolic | from $0.30 via Hyperbolic | 5.5 | n/a | 38% | 9 providers | |
| Qwen3 VL 235B A22B Instruct | Released Sep 23, 2025 | 262K | from $0.20 via DeepInfra | from $0.88 via DeepInfra | 9.9 | n/a | 71% | 9 providers | |
| GPT-5 Mini | Released Aug 7, 2025 | 1M | from $0.25 via Databricks | from $1.20 via Snowflake | 16.8 | 4% | 83% | 9 providers | |
| MiniMax M2.7 | Released Mar 18, 2026 | 1M | from $0.25 via DeepInfra | from $0.55 via Pinstripes | 22.8 | 55% | 87% | 9 providers | |
| GLM 4.6 | First listed Oct 2025 | 205K | from $0.50 via DeepInfra | from $2.00 via DeepInfra | 14.9 | 49% | 63% | 9 providers | |
| GLM 5 | Released Feb 12, 2026 | 1M | from $0.60 via DeepInfra | from $1.92 Routed quote | 27.9 | n/a | 82% | 9 providers | |
| GPT-5 | Released Aug 7, 2025 | 410K | from $1.25 via Databricks | from $10.00 via Databricks | 23.0 | 35% | 85% | 9 providers | |
| Claude Sonnet 5 | Released Jun 30, 2026 | 1M | from $2.00 via Anthropic | from $10.00 via Anthropic | 38.2 | 81% | 91% | 9 providers | |
| Claude Sonnet 4.6 | Released Feb 17, 2026 | 1M | from $3.00 via Databricks | from $15.00 via Anthropic | 24.7 | 71% | 80% | 9 providers | |
| Claude Opus 5 | Released Jul 24, 2026 | 1M | from $5.00 via Anthropic | from $25.00 via Anthropic | 50.8 | 89% | 93% | 9 providers | |
| Claude Fable 5 | Released Jun 9, 2026 | 1M | from $10.00 via Anthropic | from $50.00 via Anthropic | 49.6 | 85% | 93% | 9 providers | |
| Llama 3.2 1B Instruct | First listed Sep 2024 | 131K | from $0.02 via Novita | from $0.02 via Novita | 4.8 | n/a | 20% | 8 providers |
Input $/1M
from$0.03
via WandbOutput $/1M
from$0.17
via DeepInfraIntelligence11.623 providers
Input $/1M
from$0.05
Routed quoteOutput $/1M
from$1.98
via Scx AIIntelligence33.720 providers
Input $/1M
from$0.09
via DeepInfraOutput $/1M
from$0.18
via DeepInfraIntelligence24.218 providers
Input $/1M
from$0.12
via HyperbolicOutput $/1M
from$0.20
via CrusoeIntelligence7.718 providers
Input $/1M
from$0.02
via NebiusOutput $/1M
from$0.03
via NscaleIntelligence6.917 providers
Input $/1M
from$0.016
Routed quoteOutput $/1M
from$0.153
Routed quoteIntelligence34.316 providers
Input $/1M
from$0.079
Routed quoteOutput $/1M
from$3.08
via SailIntelligence44.816 providers
Input $/1M
from$0.435
via TencentOutput $/1M
from$0.87
via TencentIntelligence30.416 providers
Input $/1M
from$0.671
Routed quoteOutput $/1M
from$3.35
Routed quoteIntelligence25.816 providers
Input $/1M
from$0.0145
via DarkbloomOutput $/1M
from$0.07
via DarkbloomIntelligence9.015 providers
Input $/1M
from$0.65
via WandbOutput $/1M
from$3.40
via NovitaIntelligence27.015 providers
Input $/1M
from$0.40
via HyperbolicOutput $/1M
from$0.40
via HyperbolicIntelligence11.414 providers
Input $/1M
from$0.70
Routed quoteOutput $/1M
from$12.50
via SailIntelligence43.614 providers
Input $/1M
from$0.09
Routed quoteOutput $/1M
from$0.34
via WandbIntelligencen/a13 providers
Input $/1M
from$0.11
via SailOutput $/1M
from$0.35
via SailIntelligence41.813 providers
Input $/1M
from$0.01
via CoralbricksOutput $/1M
from$0.60
via SailIntelligence39.512 providers
Input $/1M
from$0.20
via Lambda AIOutput $/1M
from$0.40
via HyperbolicIntelligence9.712 providers
Input $/1M
from$0.66
Routed quoteOutput $/1M
from$1.98
Routed quoteIntelligence36.012 providers
Input $/1M
from$1.05
via DeepInfraOutput $/1M
from$3.50
via DeepInfraIntelligence26.112 providers
Input $/1M
from$0.015
via Lambda AIOutput $/1M
from$0.02
via DeepInfraIntelligence5.711 providers
Input $/1M
from$0.09
via DeepInfraOutput $/1M
from$0.90
via Fireworks AIIntelligence9.611 providers
Input $/1M
from$0.20
via DeepInfraOutput $/1M
from$0.375
via NscaleIntelligence7.911 providers
Input $/1M
from$0.23
via WandbOutput $/1M
from$0.96
via WandbIntelligence29.211 providers
Input $/1M
from$0.25
via DeepInfraOutput $/1M
from$0.95
via DeepInfraIntelligence13.711 providers
Input $/1M
from$0.259
Routed quoteOutput $/1M
from$0.38
via DeepInfraIntelligence16.011 providers
Input $/1M
from$0.45
via DeepInfraOutput $/1M
from$2.25
via DeepInfraIntelligence23.511 providers
Input $/1M
from$1.00
via AnthropicOutput $/1M
from$5.00
via AnthropicIntelligencen/a11 providers
Input $/1M
from$0.07
via DeepInfraOutput $/1M
from$0.255
Routed quoteIntelligencen/a10 providers
Input $/1M
from$0.08
via DeepInfraOutput $/1M
from$0.23
via OvhcloudIntelligence7.310 providers
Input $/1M
from$0.14
via DeepInfraOutput $/1M
from$0.90
via Fireworks AIIntelligencen/a10 providers
Input $/1M
from$0.20
via HyperbolicOutput $/1M
from$0.20
via HyperbolicIntelligence8.510 providers
Input $/1M
from$0.20
via Lambda AIOutput $/1M
from$0.25
via HyperbolicIntelligence13.110 providers
Input $/1M
from$0.27
Routed quoteOutput $/1M
from$1.08
Routed quoteIntelligence22.810 providers
Input $/1M
from$0.40
via DeepInfraOutput $/1M
from$1.75
via DeepInfraIntelligence22.210 providers
Input $/1M
from$0.60
via MoonshotOutput $/1M
from$1.20
via GmiIntelligence22.010 providers
Input $/1M
from$1.65
via DeepInfraOutput $/1M
from$4.95
via DeepInfraIntelligence40.110 providers
Input $/1M
from$0.05
via SailOutput $/1M
from$0.40
via SailIntelligence18.29 providers
Input $/1M
from$0.12
via HyperbolicOutput $/1M
from$0.30
via HyperbolicIntelligence7.39 providers
Input $/1M
from$0.12
via HyperbolicOutput $/1M
from$0.30
via HyperbolicIntelligence5.59 providers
Input $/1M
from$0.20
via DeepInfraOutput $/1M
from$0.88
via DeepInfraIntelligence9.99 providers
Input $/1M
from$0.25
via DatabricksOutput $/1M
from$1.20
via SnowflakeIntelligence16.89 providers
Input $/1M
from$0.25
via DeepInfraOutput $/1M
from$0.55
via PinstripesIntelligence22.89 providers
Input $/1M
from$0.50
via DeepInfraOutput $/1M
from$2.00
via DeepInfraIntelligence14.99 providers
Input $/1M
from$0.60
via DeepInfraOutput $/1M
from$1.92
Routed quoteIntelligence27.99 providers
Input $/1M
from$1.25
via DatabricksOutput $/1M
from$10.00
via DatabricksIntelligence23.09 providers
Input $/1M
from$2.00
via AnthropicOutput $/1M
from$10.00
via AnthropicIntelligence38.29 providers
Input $/1M
from$3.00
via DatabricksOutput $/1M
from$15.00
via AnthropicIntelligence24.79 providers
Input $/1M
from$5.00
via AnthropicOutput $/1M
from$25.00
via AnthropicIntelligence50.89 providers
Input $/1M
from$10.00
via AnthropicOutput $/1M
from$50.00
via AnthropicIntelligence49.69 providers
Input $/1M
from$0.02
via NovitaOutput $/1M
from$0.02
via NovitaIntelligence4.88 providers
1–50 of 674 models
Page 1 of 14
Listed prices from LiteLLM, OpenRouter and Vercel · catalogue refreshed Oct 14, 2026 · 252 prices older, back to Jul 19, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI